GET /api/experiments/
HTTP 200 OK
Allow: GET
Content-Type: application/json
Vary: Accept

[
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-i",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 72h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 72h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-i-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-b",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Geldanamycin",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-b-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2021-03-10",
        "modification_date": "2021-04-15",
        "urn": "urn:mavedb:00000062-a",
        "publish_date": "2021-04-15",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study tested the impact of CYP2C9 variants on the abundance of this protein in HEK293T. The authors fused the target protein with green fluorescent protein (GFP) and used the intensity of GPF as the indicator of target protein abundance.",
        "method_text": "This study used nicking mutagenesis method and generated CYP2C9 variant library which contained 109 missense mutations for each. Target protein was linked with green fluorescent protein (GFP) and co-expressed with mCherry as control. The variant library was introduced to HEK293T cells by a landing pad. After 5 days' growth, the cells were sorted to 4 bins by FACS according to the relative intensity of GFP and mCherry, and the variant frequency in each bin was determined by high-throughput sequencing which was then used to calculate the abundance score for each variant. The experiments are repeated four times.",
        "short_description": "This study tested the protein abundance of CYP2C9 variants by fusing green fluorescent protein.",
        "title": "Abundance of CYP2C9 variants",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1111/cts.12758",
                "url": "https://doi.org/10.1111/cts.12758",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32004414",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32004414",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000062-a-1"
        ],
        "experimentset": "urn:mavedb:00000062"
    },
    {
        "creation_date": "2019-02-18",
        "modification_date": "2019-08-09",
        "urn": "urn:mavedb:00000013-b",
        "publish_date": "2019-02-18",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study demonstrated variant abundance by massively parallel sequencing (VAMP-seq), a technique for measuring the effect of protein variants on abundance using fluorescence. VAMP-seq is a generally-applicable assay for protein stability that can identify loss-of-function variants.",
        "method_text": "Barcoded variant libraries were created using inverse PCR. Barcodes were associated with full-length variants using Pacific Biosciences SMRT sequencing to generate long reads. Each protein variant is fused to EGFP so that its abundance can be tracked using fluorescence. Cells were sorted into bins using FACS based on the ratio of EGFP to mCherry.",
        "short_description": "Variant abundance by massively parallel sequencing (VAMP-seq) applied to TPMT.",
        "title": "TMPT VAMP-seq",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "SMRT sequencing"
            },
            {
                "text": "VAMP-seq"
            },
            {
                "text": "FACS"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA428380",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA428380",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29785012",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29785012",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000013-b-1"
        ],
        "experimentset": "urn:mavedb:00000013"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000027-b",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of PKLR promoter, 48h post-transfection in K562 cells.",
        "title": "Saturation mutagenesis MPRA of PKLR promoter, 48h",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "PKLR"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444728",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444728",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000027-b-1"
        ],
        "experimentset": "urn:mavedb:00000027"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000025-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of MYC enhancer (rs6983267) in HEK293T cells.",
        "title": "Saturation mutagenesis MPRA of MYC enhancer (rs6983267)",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "rs6983267"
            },
            {
                "text": "MYC"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444727",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444727",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000025-a-1"
        ],
        "experimentset": "urn:mavedb:00000025"
    },
    {
        "creation_date": "2020-08-07",
        "modification_date": "2021-01-18",
        "urn": "urn:mavedb:00000059-a",
        "publish_date": "2021-01-18",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "To comprehensively characterize the consequences of the p53 mutation spectrum, the author generated ~10,000 variants on the DNA-binding domain (DBD) of p53 variants in human cells and measured the relative growth rate of each mutant through selection.",
        "method_text": "The designed variant library of p53 are separated to 4 groups and synthesized using Agilent microarrays which contains a contiguous mutated region. The sequences are transformed into a lentiviral vector. The packaged virus then infected p53-null H1299 cells. The cells were incubated for 14 days and the variant frequency change for the cells are determined on day 2, 6, 9 and 14 using next-generation sequencing.\r\nMissense mutations are grouped according to the position of substitution: 1-48 in sub-library DBDA, 49-96 in sub-library DBDB, 97-144 in sub-library DBDC and the rest are in DBDD.",
        "short_description": "The impact of p53 variant is represented by the frequency change of cells harboring that mutation over several time point.",
        "title": "p53 variant effect measured by cell growth",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29979965",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29979965",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000059-a-1"
        ],
        "experimentset": "urn:mavedb:00000059"
    },
    {
        "creation_date": "2019-01-24",
        "modification_date": "2019-07-26",
        "urn": "urn:mavedb:00000008-a",
        "publish_date": "2019-01-24",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study described the functional consequence of over 100,000 enhancer variants *in vivo* in mouse liver. Two human enhancers (ALDOB, ECR11) and one mouse enhancer (LTV1) were known to be active in mouse liver and therefore variants in these enhancers should show a measurable difference in transcription. The results were broadly consistent with evolutionary data and transcription factor binding sites, but were not always concordant demonstrating the importance of measuring the effect of enhancer variants directly.\r\n\r\nThis MaveDB entry describes the LTV1 enhancer data. Datasets for other enhancers described in the same publication are also available: [ALDOB](https://www.mavedb.org/experiment/urn:mavedb:00000006-a/) [ECR11](https://www.mavedb.org/experiment/urn:mavedb:00000007-a/)",
        "method_text": "Variants were constructed using doped oligo with 1% of each non-target base included at each position (ratio of 97:1:1:1). Full-length enhancer haplotypes were assembled and cloned into tagged pGL4.23 plasmids. Each variant haplotype was tagged with a 20-bp sequence, with multiple tags per haplotype in each replicate in most cases. Each single nucleotide change was present in at least 42 haplotypes. \r\n\r\nThe enhancers were injected into the mouse tail vein and mouse livers were harvested after 24h. RNA was isolated from fresh mouse livers, subjected to DNAseI treatment to remove any DNA contamination, reverse-transcribed into cDNA, and sequenced.\r\n\r\nTwo sets of sequencing reactions were performed. One used short Illumina reads (42 total cycles) to sequence the tag sequence used for quantifying each enhancer's activity. The other used subassembly synthetic long read sequencing to associate the tags with the full-length enhancer haplotypes.",
        "short_description": "Massively parallel functional dissection of the LTV1 enhancer in a mouse liver transcription assay.",
        "title": "Massively parallel functional dissection of LTV1 enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "doped oligo synthesis"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "liver"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRA049159",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRA049159",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "22371081",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/22371081",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000008-a-1",
            "urn:mavedb:00000008-a-2"
        ],
        "experimentset": "urn:mavedb:00000008"
    },
    {
        "creation_date": "2021-03-14",
        "modification_date": "2021-04-15",
        "urn": "urn:mavedb:00000063-a",
        "publish_date": "2021-04-15",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study tested the variant effects of <i>E.coli</i> dihydrofolate reductase (DHFR) whose function is necessary for the survival of the bacteria. The study cultured the bacteria in an early Log phase growth period under the control of Lon protease and determined the variant frequency change after cultivation, indicating the impact of DHFR variants.",
        "method_text": "The variant library in this study is generated by parallel inverse PCR reactions. An <i>E.coli</i> strain with functioning Lon gene is introduced with the variant library and cultivated. The growth rates of the bacteria harbouring each variant at several timepoints are determined by Illumina NextSeq, and the results are analyzed by Enrich2. The experiments are repeated three times in total and the final fitness values are the average of them.",
        "short_description": "Growth rate of E.coli with mutated dihydrofolate reductase (DHFR) with functioning Lon protease",
        "title": "Growth rate of mutated DHFR with functioning Lon",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA590072",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA590072",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.7554/eLife.53476",
                "url": "https://doi.org/10.7554/eLife.53476",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32701056",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32701056",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000063-a-1"
        ],
        "experimentset": "urn:mavedb:00000063"
    },
    {
        "creation_date": "2018-06-29",
        "modification_date": "2019-08-08",
        "urn": "urn:mavedb:00000001-b",
        "publish_date": "2018-06-29",
        "created_by": "0000-0003-1628-9390",
        "modified_by": "0000-0003-1628-9390",
        "extra_metadata": {},
        "abstract_text": "Although we now routinely sequence human genomes, we can confidently identify only a fraction of the sequence variants that have a functional impact. Here, we developed a deep mutational scanning framework that produces exhaustive maps for human missense variants by combining random codon mutagenesis and multiplexed functional variation assays with computational imputation and refinement. We applied this framework to four proteins corresponding to six human genes: UBE2I (encoding SUMO E2 conjugase), SUMO1 (small ubiquitin-like modifier), TPK1 (thiamin pyrophosphokinase), and CALM1/2/3 (three genes encoding the protein calmodulin). The resulting maps recapitulate known protein features and confidently identify pathogenic variation. Assays potentially amenable to deep mutational scanning are already available for 57% of human disease genes, suggesting that DMS could ultimately map functional variation for all human disease genes.",
        "method_text": "A Deep Mutational Scan of SUMO1 using functional complementation in yeast was performed using DMS-TileSeq and a machine-learning method was used to impute the effects of missing variants and refine measurements of lower confidence. See [**Weile *et al.* 2017**](http://msb.embopress.org/content/13/12/957) for details.",
        "short_description": "A Deep Mutational Scan of the human SUMO1 using functional complementation in yeast.",
        "title": "SUMO1 yeast complementation",
        "keywords": [
            {
                "text": "sumoylation"
            },
            {
                "text": "imputation"
            },
            {
                "text": "DMS-TileSeq"
            },
            {
                "text": "complementation"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRP109119",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP109119",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29269382",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29269382",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1628-9390"
        ],
        "scoresets": [
            "urn:mavedb:00000001-b-2",
            "urn:mavedb:00000001-b-1"
        ],
        "experimentset": "urn:mavedb:00000001"
    },
    {
        "creation_date": "2018-07-10",
        "modification_date": "2019-07-28",
        "urn": "urn:mavedb:00000003-a",
        "publish_date": "2018-07-10",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "These experiments measured the functional consequences of mutations in the BRCA1 RING domain, where most clinically-relevant single nucleotide variants reside. One goal of the study was to create a \"look-up table\" of single nucleotide variants for clinical use, by prospectively measuring the impact of all possible variants that are likely to appear in patients. The study combines two different assays - one based on E3 ubiquitin ligase activity and one based on BRCA1-BARD1 heterodimer formation - and makes one of the first attempts to combine data from different MAVEs on the same target.\r\n\r\nThis entry describes the phage autoubiquitination assay, which tested the E3 ubiquitin ligase activity of BRCA1 variants.",
        "method_text": "Variants were constructed using PALS (Programmed Allelic Series) [Hiatt et al.]. Full-length variant sequences were associated with 16-base DNA barcodes using the subassembly method [Kitzman et al.]. Barcodes were sequenced and counted for each of six time points in six replicates, and the barcode counts were used to quantify variant enrichment/depletion.",
        "short_description": "Deep mutational scan of the BRCA1 RING domain using a phage autoubiquitination assay.",
        "title": "BRCA1 E3",
        "keywords": [
            {
                "text": "subassembly"
            },
            {
                "text": "RING domain"
            },
            {
                "text": "Phage display"
            },
            {
                "text": "ubiquitin"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "20081835",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/20081835",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "25559584",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/25559584",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "25823446",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/25823446",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2870-5099"
        ],
        "scoresets": [
            "urn:mavedb:00000003-a-2",
            "urn:mavedb:00000003-a-1"
        ],
        "experimentset": "urn:mavedb:00000003"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-01-17",
        "urn": "urn:mavedb:00000057-c",
        "publish_date": "2021-01-17",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors used saturation mutagenesis to study the variant effect of Ras, with the regulation of GTPase activating protein (GAP) and guanine nucleotide exchange factor (GEF). The variants were selected by bacterial two-hybrid strategy.",
        "method_text": "The RAS mutant library was generated by oligonucleotide-directed mutagenesis. The mutant library was transfected into bacteria with the regulation of GAP as well as GEF. The functioning RAS protein which will bind to GTP as well as Raf. The binding of these molecules can trigger the transcription of an antibiotic resistant factor. The library was separated to three sub-libraries in order to cover the whole RAS gene length which ranges from the residue 2-56, 57-111, and 112-166. These samples were selected individually. The samples in different sub-libraries were barcoded and pooled together for MiSeq sequencing.",
        "short_description": "In the presence of a GAP and a GEF, selection result on the mutated H-Ras.",
        "title": "Regulated-Ras",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "28686159",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/28686159",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000057-c-1"
        ],
        "experimentset": "urn:mavedb:00000057"
    },
    {
        "creation_date": "2019-02-18",
        "modification_date": "2019-08-09",
        "urn": "urn:mavedb:00000013-a",
        "publish_date": "2019-02-18",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study demonstrated variant abundance by massively parallel sequencing (VAMP-seq), a technique for measuring the effect of protein variants on abundance using fluorescence. VAMP-seq is a generally-applicable assay for protein stability that can identify loss-of-function variants.",
        "method_text": "Barcoded variant libraries were created using inverse PCR. Barcodes were associated with full-length variants using Pacific Biosciences SMRT sequencing to generate long reads. Each protein variant is fused to EGFP so that its abundance can be tracked using fluorescence. Cells were sorted into bins using FACS based on the ratio of EGFP to mCherry.",
        "short_description": "Variant abundance by massively parallel sequencing (VAMP-seq) applied to PTEN.",
        "title": "PTEN VAMP-seq",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "SMRT sequencing"
            },
            {
                "text": "VAMP-seq"
            },
            {
                "text": "FACS"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA428380",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA428380",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29785012",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29785012",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000013-a-1"
        ],
        "experimentset": "urn:mavedb:00000013"
    },
    {
        "creation_date": "2019-08-07",
        "modification_date": "2019-08-09",
        "urn": "urn:mavedb:00000039-a",
        "publish_date": "2019-08-07",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured the effects of yeast HSP90 variants under the control of different promoters to explore the relationship between protein sequence and expression level. The results showed that reduced expression level (compared to wild-type expression) revealed new partial loss of function mutations.",
        "method_text": "Fully randomized codons (NNN codons) were generated for each position and inserted into plasmids using a cassette ligation strategy. Constructs were generated with one of four constitutive promoters (GPD, TEF, ADH, or CYC), with or without the 3'UTR from the CYC gene. Constructs without the 3'UTR had the plasmid backbone as their UTR sequence, and are designated '$\\Delta$ter' or 'dter'. Yeast were grown in synthetic dextrose media lacking tryptophan. Time points for Illumina sequencing were taken at 12, 16, 20, 24, 32, 40, and 48 hours for GPD, TEF and TEF$\\Delta$ter, and at 16, 20, 24, 32, 40, and 48 hours for CYC, ADH, CYC$\\Delta$ter, and ADH$\\Delta$ter due to slower overall growth rates.",
        "short_description": "Deep mutational scan of all single mutants in a nine-amino acid region of Hsp90 (Hsp82) in Saccharomyces cerevisiae under the control of different promoters.",
        "title": "Deep mutational scan of HSP90 under multiple promoters",
        "keywords": [
            {
                "text": "NNN mutagenesis"
            },
            {
                "text": "EMPIRIC"
            },
            {
                "text": "growth assay"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "23825969",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23825969",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000039-a-1",
            "urn:mavedb:00000039-a-2",
            "urn:mavedb:00000039-a-3",
            "urn:mavedb:00000039-a-4",
            "urn:mavedb:00000039-a-5",
            "urn:mavedb:00000039-a-6",
            "urn:mavedb:00000039-a-7"
        ],
        "experimentset": "urn:mavedb:00000039"
    },
    {
        "creation_date": "2021-04-12",
        "modification_date": "2021-04-15",
        "urn": "urn:mavedb:00000064-b",
        "publish_date": "2021-04-15",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study tested the variant effects of _E.coli_ LamB which facilitates the transportation of maltodextrin. The bacteria are cultured in the media that maltodextrin is the only carbon source and the growth rate for each mutant is determined to indicate its impact on maltodextrin transportation function.",
        "method_text": "The variant library in this study is generated by error-prone PCR and expressed in a lamB knockout _E.coli_ strain. The bacteria are cultured either in media containing glucose as control group and media containing maltodextrin as the only carbon source as selection group. The frequency for each variant in those groups is determined by Illumina NextSeq using the Nextera kit.",
        "short_description": "Growth rate of E.coli with mutated LamB where maltodextrin is the sole carbon source",
        "title": "Maltose transportation of LamB",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA604031",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA604031",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1099/mgen.0.000364",
                "url": "https://doi.org/10.1099/mgen.0.000364",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32238226",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32238226",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000064-b-1"
        ],
        "experimentset": "urn:mavedb:00000064"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-a",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 2h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 2h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-a-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000029-b",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of SORT1 enhancer (reversed orientation) in HepG2 cells.",
        "title": "Saturation mutagenesis MPRA of SORT1 enhancer, flipped",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "SORT1"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444731",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444731",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000029-b-1"
        ],
        "experimentset": "urn:mavedb:00000029"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000030-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of TCF7L2 enhancer in MIN6 cells.",
        "title": "Saturation mutagenesis MPRA of TCF7L2 enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "TCF7L2"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444733",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444733",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000030-a-1"
        ],
        "experimentset": "urn:mavedb:00000030"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000014-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of BCL11A enhancer in HEL 92.1.7 cells.",
        "title": "Saturation mutagenesis MPRA of BCL11A enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "BCL11A"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444714",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444714",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000014-a-1"
        ],
        "experimentset": "urn:mavedb:00000014"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-l",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\n\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Brefeldin A",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-l-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-d",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 8h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 8h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-d-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2019-09-26",
        "modification_date": "2020-04-22",
        "urn": "urn:mavedb:00000043-a",
        "publish_date": "2019-10-08",
        "created_by": "0000-0001-7684-5841",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The single transmembrane domain of the human thrombopoietin receptor (TpoR/MPL), encoded by exon 10 of the MPL gene, is a hotspot for somatic mutations associated with myeloproliferative neoplasms. One experiment was designed to identify all single-amino-acid substitutions in the human TpoR transmembrane and partial juxtamembrane regions (488-516) that could independently confer factor-free growth. A second experiment was designed to determine mutations that enhance the constitutive activity of the patient-derived S505N mutation.",
        "method_text": "The DMS library was encoded in the retroviral expression system pMX-GW-PGK-PuroR-GFP. Each codon for amino acid positions 488-516 of the human TpoR protein, encompassing the TM and partial JM regions, was independently randomised using degenerate (NNN) primers (IDT) to encode all 64 possible codons. Plasmid preparations for all positions (488-516) were pooled together in equal amounts to obtain a library containing all 1,856 possible DNA variants. The frequencies of variants in each library were determined by Illumina sequencing, which confirmed 100% representation across the randomised region and constitutes the unselected control sample.\r\n\r\nThe library was transfected into HEK293T cells along with retroviral packaging vectors using calcium phosphate transfection. After 48 hrs, supernatants containing virus were harvested and sterile filtered for transduction into Ba/F3 cells.  The pooled retroviral library was used to transduce 10^6 Ba/F3 cells at a multiplicity of infection ~0.1, generating ~10^5 transductants for each of six biological replicates. These six cultures were treated with 5 μg/ml puromycin (on IL-3) for 48 hours to yield pure virus-positive cells. Cells for each replicate were split in half and cultured in the continued presence of IL-3, or were washed to remove IL-3, and subjected to another 48 hours culture. mRNA was prepared from the live cells that remained at the end of this procedure.\r\n\r\ncDNA was prepared from 1 μg of total RNA using the TpoR-specific reverse transcription primer containing a 16 bp unique molecular identifier (UMI) and an Illumina adapter. cDNA was amplified to add illumina adapters and indexes for sequencing using an Illumina NextSeq kit with 140 cycles in the forward direction and 160 cycles in the reverse direction.\r\n\r\nThe paired-end reads from Illumina sequencing runs were separated into samples based on Illumina index sequences using Cutadapt v1.157. De-duplication based on the UMI was performed using UMI Tools v1.15 after sample separation. Reads were trimmed to the region of interest and filtered for length using Cutadapt prior to analysis with Enrich2 v1.2.0. \r\n\r\nTo determine mutations that confer constitutive activity log ratio enrichment scores were calculated for each of the six replicates by comparing the variant counts in the unselected plasmid library with those remaining in Ba/F3 cells after 2 days of culture in growth factor free media using “wild-type” (all synonymous DNA sequences encoding the WT amino acid sequence) count normalisation. To determine mutations that confer increased activity on the S505N background six replicates of library-containing BaF3 cells grown in IL-3 were compared to six replicates of library-containing BaF3 cells grown without growth factors.  Log ratios were calculated similarly.",
        "short_description": "Evaluation of all possible single-amino-acid substitutions in the human Thrombopoietin Receptor (Mpl) transmembrane domain for their ability to confer cytokine-independent growth or enhance S505N constitutive activity in Ba/F3 cells.",
        "title": "Novel Drivers and Modifiers of MPL-dependent Oncogenic Transformation Identified by Deep Mutational Scanning",
        "keywords": [
            {
                "text": "Thrombopoietin Receptor"
            },
            {
                "text": "Transmembrane"
            },
            {
                "text": "Enrich2"
            },
            {
                "text": "mRNA"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRR10193506",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRR10193506",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "31697803",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31697803",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-7684-5841"
        ],
        "scoresets": [
            "urn:mavedb:00000043-a-1",
            "urn:mavedb:00000043-a-2"
        ],
        "experimentset": "urn:mavedb:00000043"
    },
    {
        "creation_date": "2019-01-23",
        "modification_date": "2019-07-26",
        "urn": "urn:mavedb:00000006-a",
        "publish_date": "2019-01-24",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study described the functional consequence of over 100,000 enhancer variants *in vivo* in mouse liver. Two human enhancers (ALDOB, ECR11) and one mouse enhancer (LTV1) were known to be active in mouse liver and therefore variants in these enhancers should show a measurable difference in transcription. The results were broadly consistent with evolutionary data and transcription factor binding sites, but were not always concordant demonstrating the importance of measuring the effect of enhancer variants directly.\r\n\r\nThis MaveDB entry describes the ALDOB enhancer data. Datasets for other enhancers described in the same publication are also available: [ECR11](https://www.mavedb.org/experiment/urn:mavedb:00000007-a/) [LTV1](https://www.mavedb.org/experiment/urn:mavedb:00000008-a/)",
        "method_text": "Variants were constructed using doped oligo with 1% of each non-target base included at each position (ratio of 97:1:1:1). Full-length enhancer haplotypes were assembled and cloned into tagged pGL4.23 plasmids. Each variant haplotype was tagged with a 20-bp sequence, with one tag per haplotype in almost all cases. Each single nucleotide change was present in at least 42 haplotypes. \r\n\r\nThe enhancers were injected into the mouse tail vein and mouse livers were harvested after 24h. RNA was isolated from fresh mouse livers, subjected to DNAseI treatment to remove any DNA contamination, reverse-transcribed into cDNA, and sequenced.\r\n\r\nTwo sets of sequencing reactions were performed. One used short Illumina reads (42 total cycles) to sequence the tag sequence used for quantifying each enhancer's activity. The other used subassembly synthetic long read sequencing to associate the tags with the full-length enhancer haplotypes.",
        "short_description": "Massively parallel functional dissection of the ALDOB enhancer in a mouse liver transcription assay.",
        "title": "Massively parallel functional dissection of ALDOB enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "doped oligo synthesis"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "liver"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRA049159",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRA049159",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "22371081",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/22371081",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000006-a-1"
        ],
        "experimentset": "urn:mavedb:00000006"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-e",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Menadione",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-e-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2020-08-23",
        "modification_date": "2021-01-18",
        "urn": "urn:mavedb:00000058-a",
        "publish_date": "2021-01-18",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment measured the molecular determinants of A$\\beta$ 42 aggregation in a cell-based system, by combining a yeast DHFR aggregation assay with deep mutational scanning. The effect of 791 of the 798 possible single amino acid substitutions on the aggregation propensity of A$\\beta$ 42 was measured using a yeast growth-based aggregation assay.",
        "method_text": "The variant library was cloned using in vivo assembly. To measure A$\\beta$ aggregation by yeast growth rate, A$\\beta$ was fused to dihydrofolate reductase (DHFR) via a short peptide linker. DHFR is required for growth and the activity of the fusion protein depends on the solubility of A$\\beta$. When treated with DHFR inhibitor methotrexate, yeast with soluble A$\\beta$ variants grow more rapidly that those with aggregating A$\\beta$ variants. High-throughput DNA sequencing was used to measure the frequency of each variant. Six time points (including the starting time point) were measured during the course of the assay. Three replicate assays were performed.",
        "short_description": "Molecular determinants of Aβ aggregation with Deep Mutational Scanning",
        "title": "Variants of Aβ42 affecting aggregation",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA578530",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA578530",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "31558564",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31558564",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000058-a-1"
        ],
        "experimentset": "urn:mavedb:00000058"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-i",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\n\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Rapamycin",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-i-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2020-11-11",
        "modification_date": "2020-11-11",
        "urn": "urn:mavedb:00000048-c",
        "publish_date": "2020-11-11",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment utilised site-saturation mutagenesis (SSM) to measure the functional consequences of mutations in the human chemokine receptor, CXCR4 and to map ligand interaction sites. Cells were selected for binding to Ab 12G5.",
        "method_text": "The human CXCR4 sequence was generated by oligo assembly and fused to a c-myc tag. SSM libraries were generated by overlapping PCR using primers with an NNK codon, as described by Procko et al, 2013.\r\nThe SSM library was transfected into CXCR4-knockout human Expi293F cells using pCEP4. \r\nSurface receptor expression was measured by anti-myc-FITC staining and cells were sorted on a BD FACSAria II.\r\nTo test the validity of deep mutational scanning for mapping GPCR interactions sites, cells were selected for binding to fluorescent Ab 12G5, a previously mapped (by small-scale alanine mutagenesis) interacting ligand. \r\nTotal RNA was extracted and PCR-amplified before sequencing by Illumina MiSeq v 3 or HiSeq 2500. \r\n\r\nRaw data available from GEO under accession [GSE100368](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100368).",
        "short_description": "Deep mutational scan selecting for CXCR4 binding to Ab 12G5 in Expi293F cells.",
        "title": "CXCR4 Ab 12G5 binding",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29678950",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29678950",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23827138",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23827138",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-6681-7994"
        ],
        "scoresets": [
            "urn:mavedb:00000048-c-1"
        ],
        "experimentset": "urn:mavedb:00000048"
    },
    {
        "creation_date": "2019-08-08",
        "modification_date": "2019-08-08",
        "urn": "urn:mavedb:00000041-a",
        "publish_date": "2019-08-08",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study infers the activity of variants in Src kinases's catalytic domain by measuring their effects on yeast growth, and therefore phosphotransferase activity. The resulting dataset includes variants classified as gain of function, loss of function. or neutral.",
        "method_text": "Variants in the Src catalytic domain were generated using NNK mutagenesis. Barcodes were associated with each variant and barcode-variant mapping was determined using subassembly. Variants were transformed into yeast on plasmids and the plasmid barcodes were sequenced at three time points determined by OD. Barcodes were sequenced on an Illumina NextSeq.",
        "short_description": "Deep mutational scan of the Src kinase catalytic domain.",
        "title": "Deep mutational scan of Src CD",
        "keywords": [
            {
                "text": "subassembly"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "kinase"
            },
            {
                "text": "NNK mutagenesis"
            },
            {
                "text": "growth assay"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA464305",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA464305",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "30956043",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/30956043",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000041-a-1"
        ],
        "experimentset": "urn:mavedb:00000041"
    },
    {
        "creation_date": "2018-06-26",
        "modification_date": "2019-08-08",
        "urn": "urn:mavedb:00000001-a",
        "publish_date": "2018-06-26",
        "created_by": "0000-0003-1628-9390",
        "modified_by": "0000-0003-1628-9390",
        "extra_metadata": {},
        "abstract_text": "Although we now routinely sequence human genomes, we can confidently identify only a fraction of the sequence variants that have a functional impact. Here, we developed a deep mutational scanning framework that produces exhaustive maps for human missense variants by combining random codon mutagenesis and multiplexed functional variation assays with computational imputation and refinement. We applied this framework to four proteins corresponding to six human genes: UBE2I (encoding SUMO E2 conjugase), SUMO1 (small ubiquitin-like modifier), TPK1 (thiamin pyrophosphokinase), and CALM1/2/3 (three genes encoding the protein calmodulin). The resulting maps recapitulate known protein features and confidently identify pathogenic variation. Assays potentially amenable to deep mutational scanning are already available for 57% of human disease genes, suggesting that DMS could ultimately map functional variation for all human disease genes.",
        "method_text": "A Deep Mutational Scan of UBE2I using functional complementation in yeast was performed using two different methods: DMS-BarSeq and DMS-TileSeq, both datasets were combined and a machine-learning method was used to impute the effects of missing variants and refine measurements of lower confidence. See [**Weile *et al.* 2017**](http://msb.embopress.org/content/13/12/957) for details.",
        "short_description": "A Deep Mutational Scan of the human SUMO E2 conjugase UBE2I using functional complementation in yeast.",
        "title": "UBE2I yeast complementation",
        "keywords": [
            {
                "text": "E2"
            },
            {
                "text": "sumoylation"
            },
            {
                "text": "imputation"
            },
            {
                "text": "complementation"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRP109101",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP109101",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRP109119",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP109119",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29269382",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29269382",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1628-9390"
        ],
        "scoresets": [
            "urn:mavedb:00000001-a-2",
            "urn:mavedb:00000001-a-3",
            "urn:mavedb:00000001-a-4",
            "urn:mavedb:00000001-a-1"
        ],
        "experimentset": "urn:mavedb:00000001"
    },
    {
        "creation_date": "2020-11-11",
        "modification_date": "2020-11-11",
        "urn": "urn:mavedb:00000047-b",
        "publish_date": "2020-11-11",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment utilised site-saturation mutagenesis (SSM) to measure the functional consequences of mutations in the human chemokine receptor, CCR5 and to map ligand interaction sites. Cells were selected for binding to Ab 2D7.",
        "method_text": "The CCR5 variant library was generated by overlapping PCR using primers with an NNK codon, as described by Procko et al, 2013 and transfected into human Expi293F cells (a cell line lacking CCR5) using pCEP4.\r\nTo test the validity of deep mutational scanning for mapping GPCR interactions sites, cells were selected for binding to fluorescent Ab 2D7, a previously mapped (by small-scale mutagenesis) interacting ligand. \r\nSurface expression was measured using anti-myc-FITC.\r\nCell sorting was performed using a BD FACSAria II.\r\nTotal RNA was extracted and PCR-amplified before sequencing by Illumina MiSeq v3 or HiSeq 2500. \r\nTwo replicate selections were performed.\r\n\r\nRaw data available from GEO under accession [GSE100368](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100368).",
        "short_description": "Deep mutational scan selecting for CCR5 binding to Ab 2D7 in Expi293F cells.",
        "title": "CCR5 Ab 2D7 binding",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29678950",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29678950",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23827138",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23827138",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-6681-7994"
        ],
        "scoresets": [
            "urn:mavedb:00000047-b-1"
        ],
        "experimentset": "urn:mavedb:00000047"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000019-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of HBG1 promoter in HEL 92.1.7 cells.",
        "title": "Saturation mutagenesis MPRA of HBG1 promoter",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            },
            {
                "text": "HBG1"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444719",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444719",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000019-a-1"
        ],
        "experimentset": "urn:mavedb:00000019"
    },
    {
        "creation_date": "2020-11-11",
        "modification_date": "2020-11-11",
        "urn": "urn:mavedb:00000047-c",
        "publish_date": "2020-11-11",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment utilised site-saturation mutagenesis (SSM) to measure the functional consequences of mutations in the human chemokine receptor, CCR5 and to map ligand interaction sites. Cells were selected for binding to HIV-1~BaL~ gp120-CD4.",
        "method_text": "The CCR5 variant library was generated by overlapping PCR using primers with an NNK codon, as described by Procko et al, 2013 and transfected into human Expi293F cells (a cell line lacking CCR5) using pCEP4.\r\nCCR5 interactions with chemokines (CCL3, CCL4, CCL5) were unable to be characterised by deep mutational scanning. Instead, cells were selected for interaction with an important protein ligand, the HIV-1 Env subunit gp120 following incubation with HIV-1~BaL~ gp120 fused to CD4 domains D1-D2.\r\nSurface expression was measured using anti-myc-Alexa 647.\r\nCell sorting was performed using a BD FACSAria II.\r\nTotal RNA was extracted and PCR-amplified before sequencing by Illumina MiSeq v3 or HiSeq 2500 to quantify variants. \r\nTwo replicate selections were performed.\r\n\r\nRaw data available from GEO under accession [GSE100368](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100368).",
        "short_description": "Deep mutational scan selecting for CCR5 binding to HIV-1(BaL) gp120-CD4 in Expi293F cells.",
        "title": "CCR5 HIV binding",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29678950",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29678950",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23827138",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23827138",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-6681-7994"
        ],
        "scoresets": [
            "urn:mavedb:00000047-c-1"
        ],
        "experimentset": "urn:mavedb:00000047"
    },
    {
        "creation_date": "2021-01-28",
        "modification_date": "2021-01-29",
        "urn": "urn:mavedb:00000060-a",
        "publish_date": "2021-01-29",
        "created_by": "0000-0002-9712-9163",
        "modified_by": "0000-0002-9712-9163",
        "extra_metadata": {},
        "abstract_text": "Insoluble protein aggregates are the hallmarks of many neurodegenerative diseases. For example, aggregates of TDP-43 occur in nearly all cases of amyotrophic lateral sclerosis (ALS). However, whether aggregates cause cellular toxicity is still not clear, even in simpler cellular systems. We reasoned that deep mutagenesis might be a powerful approach to disentangle the relationship between aggregation and toxicity. We generated >50,000 mutations in the prion-like domain (PRD) of TDP-43 and quantified their toxicity in yeast cells. Surprisingly, mutations that increase hydrophobicity and aggregation strongly decrease toxicity. In contrast, toxic variants promote the formation of dynamic liquid-like condensates. Mutations have their strongest effects in a hotspot that genetic interactions reveal to be structured in vivo, illustrating how mutagenesis can probe the in vivo structures of unstructured proteins. Our results show that aggregation of TDP-43 is not harmful but protects cells, most likely by titrating the protein away from a toxic liquid-like phase.",
        "method_text": "Variants for TDP-43 were constructed using a \"doped\" oligo for each of the TDP-43 libraries (290-331 and 332-373). Libraries were transformed in Saccharomyces cerevisiae and TDP-43 expression was induced for 5-6 generations. Variant counts were processed with DiMSum (Faure et al. 2020) to obtain a toxicity score for each variant. \r\nSee Bolognesi et al. 2019 for details.",
        "short_description": "Deep mutational scanning of TDP-43 prion-like domain using a toxicity assay.",
        "title": "TDP-43 toxicity",
        "keywords": [
            {
                "text": "intrisic disorder"
            },
            {
                "text": "prion-like domain"
            },
            {
                "text": "TDP-43"
            },
            {
                "text": "toxicity"
            }
        ],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-12101-z",
                "url": "https://doi.org/10.1038/s41467-019-12101-z",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31519910",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31519910",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0002-9712-9163",
            "0000-0002-6632-947X"
        ],
        "scoresets": [
            "urn:mavedb:00000060-a-1",
            "urn:mavedb:00000060-a-2"
        ],
        "experimentset": "urn:mavedb:00000060"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000018-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of HBB promoter in HEL 92.1.7 cells.",
        "title": "Saturation mutagenesis MPRA of HBB promoter",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "HBB"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444718",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444718",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000018-a-1"
        ],
        "experimentset": "urn:mavedb:00000018"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000028-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of RET enhancer in Neuro-2a cells.",
        "title": "Saturation mutagenesis MPRA of RET enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            }
        ],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000028-a-1"
        ],
        "experimentset": "urn:mavedb:00000028"
    },
    {
        "creation_date": "2021-01-03",
        "modification_date": "2021-01-03",
        "urn": "urn:mavedb:00000054-a",
        "publish_date": "2021-01-03",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured variant lipid phosphatase activity using massively parallel functional testing with a humanised yeast assay. It measured the effects of PTEN mutation on lipid phosphatase activity in vivo, which is vital for preventing the accumulation of phospholipids, and is therefore required for cell survival.",
        "method_text": "Variant libraries were created using tiles and inverse PCR in a mutagenesis process similar to the mutagenesis integrated tiles (MITE) approach. PCR products were incorporated into plasmids using SLiCE-mediated recombination. Plasmid libraries were normalized and pooled to represent saturation mutagenesis for each quadrant of PTEN. p110$\\alpha$-CAAX-mediated selection was completed on each pool. Samples were then normalised, combined into a common pool, and sequenced across multiple runs using pair-ended 300 base-pair reads on Illumina MiSeq platform (v.3 reagent kit). Two biological replicates were performed, each with three technical replicate selections.",
        "short_description": "PTEN activity measured using a lipid phosphatase assay in a humanized yeast model.",
        "title": "PTEN Lipid Phosphatase",
        "keywords": [
            {
                "text": "phosphatase"
            },
            {
                "text": "humanized yeast"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA437337",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA437337",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29706350",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29706350",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-9955-0656"
        ],
        "scoresets": [
            "urn:mavedb:00000054-a-1"
        ],
        "experimentset": "urn:mavedb:00000054"
    },
    {
        "creation_date": "2018-06-29",
        "modification_date": "2019-08-08",
        "urn": "urn:mavedb:00000001-d",
        "publish_date": "2018-06-29",
        "created_by": "0000-0003-1628-9390",
        "modified_by": "0000-0003-1628-9390",
        "extra_metadata": {},
        "abstract_text": "Although we now routinely sequence human genomes, we can confidently identify only a fraction of the sequence variants that have a functional impact. Here, we developed a deep mutational scanning framework that produces exhaustive maps for human missense variants by combining random codon mutagenesis and multiplexed functional variation assays with computational imputation and refinement. We applied this framework to four proteins corresponding to six human genes: UBE2I (encoding SUMO E2 conjugase), SUMO1 (small ubiquitin-like modifier), TPK1 (thiamin pyrophosphokinase), and CALM1/2/3 (three genes encoding the protein calmodulin). The resulting maps recapitulate known protein features and confidently identify pathogenic variation. Assays potentially amenable to deep mutational scanning are already available for 57% of human disease genes, suggesting that DMS could ultimately map functional variation for all human disease genes.",
        "method_text": "A Deep Mutational Scan of TPK1 (thiamin pyrophosphokinase) using functional complementation in yeast was performed using DMS-TileSeq and a machine-learning method was used to impute the effects of missing variants and refine measurements of lower confidence. See [**Weile *et al.* 2017**](http://msb.embopress.org/content/13/12/957) for details.",
        "short_description": "A Deep Mutational Scan of human thiamin pyrophosphokinase (TPK1) using functional complementation in yeast.",
        "title": "TPK1 yeast complementation",
        "keywords": [
            {
                "text": "imputation"
            },
            {
                "text": "DMS-TileSeq"
            },
            {
                "text": "complementation"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRP109119",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP109119",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29269382",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29269382",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1628-9390"
        ],
        "scoresets": [
            "urn:mavedb:00000001-d-1",
            "urn:mavedb:00000001-d-2"
        ],
        "experimentset": "urn:mavedb:00000001"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000031-d",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of TERT promoter in glioblastoma SF7996 (GBM) cells, siRNA scrambled control.",
        "title": "Saturation mutagenesis MPRA of TERT promoter, GBM siRNA control",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            },
            {
                "text": "TERT"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444734",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444734",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000031-d-1"
        ],
        "experimentset": "urn:mavedb:00000031"
    },
    {
        "creation_date": "2020-08-23",
        "modification_date": "2020-12-10",
        "urn": "urn:mavedb:00000051-c",
        "publish_date": "2020-12-10",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study mutated the residues on GpA helix region of the bacterial inner membrane. The experiment links the insertion and self-association property of the tested region to the survive of bacteria and studied the membrane-protein energetics landscape of missense mutations of the target.",
        "method_text": "The helix region of GpA is used as the membrane-spanning segment for dsT$\\beta$L in this experiment. The authors created forward and reverse primers of lengths 40-85 base pairs with the central codon replaced by NNS which encodes all possible amino acid substitutions on the target sequence. They leveraged a traditional assay, the TOXCAT-$\\beta$-lactamase (T$\\beta$L) screen, and adapted it to deep mutational scanning studies (dsT$\\beta$L). The tested sequence is expressed in between a chimera of ToxR dimerization-dependent transcriptional activator of a chloramphenicol-resistance gene and $\\beta$-lactamase. In this construct, the membrane integration of target sequence determines the bacterial resistance to ampicillin and the self-association correlates with the chloramphenicol resistance. Besides, the orientation to the membrane of this chimera is also crucial for survival. The selection result was determined by deep-sequencing using Illumina.",
        "short_description": "A deep mutational scanning experiment targeting the GpA helix region on the bacterial inner membrane.",
        "title": "Helix region of Glycophorin A (GpA)",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.7554/eLife.12125",
                "url": "https://doi.org/10.7554/eLife.12125",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "26824389",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/26824389",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000051-c-1"
        ],
        "experimentset": "urn:mavedb:00000051"
    },
    {
        "creation_date": "2020-11-11",
        "modification_date": "2020-11-11",
        "urn": "urn:mavedb:00000047-a",
        "publish_date": "2020-11-11",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment utilised site-saturation mutagenesis (SSM) to measure the functional consequences of mutations in the human chemokine receptor, CCR5 and to map ligand interaction sites. Cells were selected for CCR5 surface expression.",
        "method_text": "Two libraries were generated independently by overlapping PCR using primers with an NNK codon, as described by Procko et al, 2013 and transfected into human Expi293F cells (a cell line lacking CCR5) using pCEP4.\r\nThe CCR5 combinatorial library was sorted for surface receptor expression by anti-myc staining.\r\nReplicates from one library used anti-myc-FITC and the other used anti-myc-Alexa 647.\r\nCell sorting was performed using a BD FACSAria II.\r\nTotal RNA was extracted and PCR-amplified before sequencing by Illumina MiSeq v3 or HiSeq 2500. \r\nTwo replicate selections were performed for each library (four total replicates).\r\n\r\nRaw data available from GEO under accession [GSE100368](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100368).",
        "short_description": "Deep mutational scan selecting for cell surface expression of CCR5 in Expi293F cells.",
        "title": "CCR5 surface expression",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29678950",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29678950",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23827138",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23827138",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-6681-7994"
        ],
        "scoresets": [
            "urn:mavedb:00000047-a-1"
        ],
        "experimentset": "urn:mavedb:00000047"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000015-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of F9 promoter in HepG2 cells.",
        "title": "Saturation mutagenesis MPRA of F9 promoter",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "F9"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444715",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444715",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000015-a-1"
        ],
        "experimentset": "urn:mavedb:00000015"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2020-12-10",
        "urn": "urn:mavedb:00000052-b",
        "publish_date": "2020-12-10",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study generated thousands of mutated sequence on Gcn4 activation domain which contains one or several amino acid substitutions. They used a high-throughput fluorescent reporter assay to identify the transcription ability of mutated Gcn4 sequences through cell sorting in nutrient stress condition.",
        "method_text": "The designed mutated Gcn4 activation domain was combined to a synthetic transcription factor and expressed in yeast. The transcription factor is fused to mCherry and functioning transcription factor is able to facilitate the expression of GFP, which is the genome-integrated reporter gene. The cells are cultured under nutrient stress condition. Cells with distinct Gcn4 activity are sorted by fluorescence-activated cell sorting system to several bins according to the ratio of GFP and mCherry fluorescence. The cells are sorted into 8 bins: bin 1 with low GFP or mCherry level; bin 2 with low GFP level and normal mCherry level; and the other bins are evenly partitioned according to the ratio of the two fluorscence. The variant abundance is determined by high-throughput sequencing in an Illumina platform.",
        "short_description": "Mutagenesis study of Gcn4 activation domain in starvation media using fluorescent reporter assay.",
        "title": "Gcn4 activation domain induction ratio",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.17632/rbfr6m4733.1",
                "url": "https://doi.org/10.17632/rbfr6m4733.1",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "29525204",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29525204",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000052-b-1"
        ],
        "experimentset": "urn:mavedb:00000052"
    },
    {
        "creation_date": "2019-02-27",
        "modification_date": "2020-11-20",
        "urn": "urn:mavedb:00000049-a",
        "publish_date": "2020-11-20",
        "created_by": "0000-0003-1628-9390",
        "modified_by": "0000-0003-1628-9390",
        "extra_metadata": {},
        "abstract_text": "",
        "method_text": "",
        "short_description": "Deep mutational scan of human MTHFR based on functional complementation in yeast, at three different concentrations of folate (12, 25 and 100 ug/ml ) and in two genetic backgrounds (WT / A222V)",
        "title": "MTHFR DMS",
        "keywords": [
            {
                "text": "imputation"
            },
            {
                "text": "homocystinuria"
            },
            {
                "text": "DMS-TileSeq"
            },
            {
                "text": "complementation"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0003-1628-9390",
            "0000-0002-9219-4310",
            "0000-0002-2550-2141",
            "0000-0001-6465-5776"
        ],
        "scoresets": [
            "urn:mavedb:00000049-a-4",
            "urn:mavedb:00000049-a-6",
            "urn:mavedb:00000049-a-1",
            "urn:mavedb:00000049-a-5",
            "urn:mavedb:00000049-a-2",
            "urn:mavedb:00000049-a-3",
            "urn:mavedb:00000049-a-7",
            "urn:mavedb:00000049-a-8"
        ],
        "experimentset": "urn:mavedb:00000049"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-k",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\n\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The expression level of alpha-synuclein missense variants was determined by cell sorting of yeast expressing each variant fused to GFP.",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Expression Level in Yeast",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41589-020-0480-6",
                "url": "https://doi.org/10.1038/s41589-020-0480-6",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32152544",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32152544",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-k-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2019-02-18",
        "modification_date": "2019-07-26",
        "urn": "urn:mavedb:00000011-a",
        "publish_date": "2019-02-18",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This was the first dataset described that used the EMPIRIC approach (\"extremely methodical and parallel investigation of randomized individual codons\"). It generated experimental fitness measurements for a nine amino acid region of yeast Hsp90. The experimental design is based on calculating growth rates for yeast containing variant Hsp90 sequences as compared to yeast containing the wild type sequence.",
        "method_text": "Fully randomized codons (NNN codons) were generated for each position and inserted into plasmids using a cassette ligation strategy. These plasmids were transformed into yeast carrying a temperature-sensitive copy of Hsp90 (G170D). After being grown up at the permissive temperature of 25C, the transformed population was heated in a water bath to inactivate G170D Hsp90 and then grown at 36C. Time points for Illumina sequencing were taken at 12, 24, 36, 48, 60, 72, and 84h time points.",
        "short_description": "Deep mutational scan of all single mutants in a nine-amino acid region of Hsp90.",
        "title": "Deep mutational scan of HSP90",
        "keywords": [
            {
                "text": "NNN mutagenesis"
            },
            {
                "text": "EMPIRIC"
            },
            {
                "text": "growth assay"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "21464309",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/21464309",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000011-a-1"
        ],
        "experimentset": "urn:mavedb:00000011"
    },
    {
        "creation_date": "2021-03-10",
        "modification_date": "2021-04-15",
        "urn": "urn:mavedb:00000062-b",
        "publish_date": "2021-04-15",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study tested the impact of CYP2C19 variants on the abundance of this protein in HEK293T. The authors fused the target protein with green fluorescent protein (GFP) and used the intensity of GPF as the indicator of target protein abundance.",
        "method_text": "This study used nicking mutagenesis method and generated CYP2C19 variant library which contained 121 missense mutations for each. Target protein was linked with green fluorescent protein (GFP) and co-expressed with mCherry as control. The variant library was introduced to HEK293T cells by a landing pad. After 5 days' growth, the cells were sorted to 4 bins by FACS according to the relative intensity of GFP and mCherry, and the variant frequency in each bin was determined by high-throughput sequencing which was then used to calculate the abundance score for each variant. The experiments are repeated four times.",
        "short_description": "This study tested the protein abundance of CYP2C19 variants by fusing green fluorescent protein.",
        "title": "Abundance of CYP2C19 variants",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1111/cts.12758",
                "url": "https://doi.org/10.1111/cts.12758",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32004414",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32004414",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000062-b-1"
        ],
        "experimentset": "urn:mavedb:00000062"
    },
    {
        "creation_date": "2020-12-14",
        "modification_date": "2020-12-20",
        "urn": "urn:mavedb:00000053-a",
        "publish_date": "2020-12-20",
        "created_by": "0000-0002-2866-3880",
        "modified_by": "0000-0002-2866-3880",
        "extra_metadata": {},
        "abstract_text": "Deep mutational scanning (DMS) enables data-driven models of protein structure and function. Here, we adapted Saturated Programmable Insertion Engineering (SPINE) as a programmable DMS technique. We validate SPINE with a reference single mutant dataset in the PSD95 PDZ3 domain and then characterize most pairwise double mutants to study epistasis. We observe wide-spread proximal negative epistasis, which we attribute to mutations affecting thermodynamic stability, and strong long-range positive epistasis, which is enriched in an evolutionarily conserved and function-defining network of ‘sector’ and clade-specifying residues. Conditional neutrality of mutations in clade-specifying residues compensates for deleterious mutations in sector positions. This suggests that epistatic interactions between these position pairs facilitated the evolutionary expansion and specialization of PDZ domains. We propose that SPINE provides easy experimental access to reveal epistasis signatures in proteins that will improve our understanding of the structural basis for protein function and adaptation.",
        "method_text": "The bacterial two-hybrid assay is based on PDZ3 binding to the CRIPT ligand. PDZ3 variants with a high affinity for the CRIPT ligand will recruit RNA polymerase α-subunit initiating expression of chloramphenicol acetyltransferase. This is a positive selection for highly functional PDZ3 variants. This system replicates the work of Salinas et al. (DOI: 10.7554/eLife.34300) and all plasmid and cell reagents were received as a gift from Rama Ranganathan. Plasmid was purified from cells before selection and after selection and the region covering the PDZ3 sequence was PCR amplified for 12 cycles with Illumina sequencing adapters. Amplicon DNA was purified with 1% agarose gel. Libraries were sequenced using Illumina MiSEQ in 150 bp paired-end configuration.",
        "short_description": "Bacterial two-hybrid assay to measure binding fitness of PSD95 PDZ3 domain to the CRIPT peptide ligand",
        "title": "Pairwise mutation fitness of PSD95 PDZ3 domain",
        "keywords": [
            {
                "text": "Binding"
            },
            {
                "text": "PDZ"
            },
            {
                "text": "SPINE mutagenesis"
            },
            {
                "text": "DMS"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2866-3880",
            "0000-0001-7609-4873"
        ],
        "scoresets": [
            "urn:mavedb:00000053-a-2",
            "urn:mavedb:00000053-a-1"
        ],
        "experimentset": "urn:mavedb:00000053"
    },
    {
        "creation_date": "2018-10-14",
        "modification_date": "2019-07-28",
        "urn": "urn:mavedb:00000004-a",
        "publish_date": "2018-12-03",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study identified multiple gain-of-function mutations in the ubiquitination factor E4B U-box domain by measuring auto-ubiquitination in a phage display system. E4B is an E3 ligase, responsible for transferring a ubiquitin from an E2 ligase to the target (in this case the phage displaying E4B). Many of these mutations are not specific to one E2 enzyme and so may be generalizable for mutiple E2s and E3s.",
        "method_text": "The variant library was constructed using doped oligo synthesis, with a 2% error rate, corresponding to 0.225% of incorporating each incorrect base at each position. The phage display was performed using T7 phage and selected for Flag-Ub binding to anti-Flag beads. Full-length variant sequences were associated with 18-base DNA barcodes using the subassembly method [Hiatt et al.]. Barcodes were sequenced and counted for each of four time points in two replicates, and the barcode counts were used to quantify variant enrichment/depletion.",
        "short_description": "Deep mutational scan of the murine E4B (Ube4b) U-box domain using a phage display auto-ubiquitination assay.",
        "title": "Deep mutational scan of E4B (Ube4b) U-box domain auto-ubiquitination",
        "keywords": [
            {
                "text": "subassembly"
            },
            {
                "text": "U-box"
            },
            {
                "text": "E3"
            },
            {
                "text": "Phage display"
            },
            {
                "text": "doped oligo synthesis"
            },
            {
                "text": "ubiquitin"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "20081835",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/20081835",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23509263",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23509263",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2870-5099"
        ],
        "scoresets": [
            "urn:mavedb:00000004-a-1",
            "urn:mavedb:00000004-a-2",
            "urn:mavedb:00000004-a-3"
        ],
        "experimentset": "urn:mavedb:00000004"
    },
    {
        "creation_date": "2020-08-23",
        "modification_date": "2020-12-10",
        "urn": "urn:mavedb:00000051-b",
        "publish_date": "2020-12-10",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study mutated the residues on ErbB2 helix region of the bacterial inner membrane. The experiment links the insertion and self-association property of the tested region to the survive of bacteria and studied the membrane-protein energetics landscape of missense mutations of the target.",
        "method_text": "The helix region of ErbB2 is used as the membrane-spanning segment for dsT$\\beta$L in this experiment. The authors created forward and reverse primers of lengths 40-85 base pairs with the central codon replaced by NNS which encodes all possible amino acid substitutions on the target sequence. They leveraged a traditional assay, the TOXCAT-$\\beta$-lactamase (T$\\beta$L) screen, and adapted it to deep mutational scanning studies (dsT$\\beta$L). The tested sequence is expressed in between a chimera of ToxR dimerization-dependent transcriptional activator of a chloramphenicol-resistance gene and $\\beta$-lactamase. In this construct, the membrane integration of target sequence determines the bacterial resistance to ampicillin and the self-association correlates with the chloramphenicol resistance. Besides, the orientation to the membrane of this chimera is also crucial for survival. The selection result was determined by deep-sequencing using Illumina.",
        "short_description": "A deep mutational scanning experiment targeting ErbB2 helix region on the bacterial inner membrane.",
        "title": "Helix region of ErbB2",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.7554/eLife.12125",
                "url": "https://doi.org/10.7554/eLife.12125",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "26824389",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/26824389",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000051-b-1"
        ],
        "experimentset": "urn:mavedb:00000051"
    },
    {
        "creation_date": "2020-06-18",
        "modification_date": "2020-06-19",
        "urn": "urn:mavedb:00000044-b",
        "publish_date": "2020-06-19",
        "created_by": "0000-0001-6713-6904",
        "modified_by": "0000-0001-6713-6904",
        "extra_metadata": {},
        "abstract_text": "The receptor binding domain (RBD) of the SARS-CoV-2 spike glycoprotein mediates viral attachment to ACE2 receptor, and is a major determinant of host range and a dominant target of neutralizing antibodies. Here we experimentally measure how all amino-acid mutations to the RBD affect expression of folded protein and its affinity for ACE2. Most mutations are deleterious for RBD expression and ACE2 binding, and we identify constrained regions on the RBD's surface that may be desirable targets for vaccines and antibody-based therapeutics. But a substantial number of mutations are well tolerated or even enhance ACE2 binding, including at ACE2 interface residues that vary across SARS-related coronaviruses. However, we find no evidence that these ACE2-affinity enhancing mutations have been selected in current SARS-CoV-2 pandemic isolates. We present an interactive visualization and open analysis pipeline to facilitate use of our dataset for vaccine design and functional annotation of mutations observed during viral surveillance. See the [preprint](https://www.biorxiv.org/content/10.1101/2020.06.17.157982v1) for more information.",
        "method_text": "We constructed duplicate libraries of mutant variants of the SARS-CoV-2 receptor binding domain (RBD), and cloned the library into a yeast surface-display platform. We used FACS-seq assays to determine variant expression and binding scores: 1) We labeled RBD variants for cell surface expression levels (a correlate of folding stability), and/or binding of soluble ACE2 ligand across a range of ACE2 concentrations. 2) We used FACS to partition our library into bins of expression or binding. 3) We sequenced the variants from within each bin. 4) From the distribution of sequence reads across FACS bins, we can reconstruct each variant's mean expression. 5) For binding values, by comparing binding as a function of ACE2 concentration, we calculate binding constants from per-variant titration curves.\r\n\r\nWe provide our duplicate library measurements at the level of individual variants within our library, which are described by unique molecular identifier barcodes downstream from the variant RBD coding sequence. We also provide decomposed single-mutant scores, which are the primary mutation scores we use in our analysis of the data. In each of these datasets, the binding score is a delta-log<sub>10</sub>(_K_<sub>D,app</sub>) metric from the variant titration curves, and the expression score is a delta-log(mean fluorescence intensity) measurement of cell surface expression. Both metrics are relative to the unmutated SARS-CoV-2 reference sequence phenotype, polarized such that a positive value indicates higher affinity or expression compared to unmutated SARS-CoV-2, and a negative value indicates decreased affinity or expression compared to unmutated SARS-CoV-2.\r\n\r\nSee the [preprint](https://www.biorxiv.org/content/10.1101/2020.06.17.157982v1) or [GitHub repository](https://github.com/jbloomlab/SARS-CoV-2-RBD_DMS) for additional information.",
        "short_description": "This experiment measures the effects on binding of variants and individual mutations in the SARS-CoV-2 RBD",
        "title": "Effects on expression of mutations in the SARS-CoV-2 RBD",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA639956",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA639956",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0001-6713-6904",
            "0000-0001-9278-3644",
            "0000-0003-1267-3408"
        ],
        "scoresets": [
            "urn:mavedb:00000044-b-2",
            "urn:mavedb:00000044-b-1"
        ],
        "experimentset": "urn:mavedb:00000044"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000022-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of IRF6 enhancer in HaCaT cells.",
        "title": "Saturation mutagenesis MPRA of IRF6 enhancer",
        "keywords": [
            {
                "text": "IRF6"
            },
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444722",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444722",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000022-a-1"
        ],
        "experimentset": "urn:mavedb:00000022"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000024-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of MSMB promoter in HEK293T cells.",
        "title": "Saturation mutagenesis MPRA of MSMB promoter",
        "keywords": [
            {
                "text": "MSMB"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444725",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444725",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000024-a-1"
        ],
        "experimentset": "urn:mavedb:00000024"
    },
    {
        "creation_date": "2020-06-26",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-h",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson's. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3' to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\n\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "A comprehensive library of 2,600 missense variants of the protein alpha-synuclein, which is implicated in Parkinson's disease, were screened for relative toxicity in yeast, a cellular model for alpha-synuclein pathobiology. Additional experiments were performed in chemically perturbed backgrounds, and relative expression level was determined by cell sorting based on the fluorescence of a fusion protein reporter.",
        "title": "Deep Mutational Scanning of alpha-Synuclein in Yeast",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41589-020-0480-6",
                "url": "https://doi.org/10.1038/s41589-020-0480-6",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32152544",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32152544",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-h-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2020-09-02",
        "modification_date": "2021-05-26",
        "urn": "urn:mavedb:00000046-a",
        "publish_date": "2020-09-05",
        "created_by": "0000-0001-7684-5841",
        "modified_by": "0000-0001-7684-5841",
        "extra_metadata": {},
        "abstract_text": "The membrane-associated RING-CH (MARCH) proteins are E3 ubiquitin ligases that contain transmembrane (TM) domains and regulate the cell-surface levels of key immune-stimulatory ligands such as major histocompatibility complex (MHC) molecules and the T-cell costimulatory ligand CD86. Endogenous mammalian MARCHs act on these targets to regulate antigen presentation and activation of adaptive immunity, while virus-encoded homologs target the same molecules to evade immune responses. Substrate specificity is believed to be encoded in or near the membrane-embedded domains of MARCHs and the proteins they regulate, but exactly what sequences distinguish substrates from non-substrates is poorly understood. Here we examined the requirements for recognition of the costimulatory ligand CD86 by two different MARCH-family proteins, human MARCH1 and Kaposi’s sarcoma herpesvirus (KSHV) modulator of immune recognition (MIR)2, using a deep mutational scanning (DMS) approach. We identified a highly specific recognition surface in the hydrophobic core of the CD86 TM domain that is required by MARCH1 and prominently features a proline at position 254. In contrast, MIR2 requires no specific sequences in the CD86 TM domain but relies primarily on an aspartic acid at position 244 in the CD86 extracellular juxtamembrane region. Surprisingly, while MIR2 recognized CD86 with a TM domain composed entirely of valine, many different single-amino-acid substitutions in the context of the native TM sequence conferred MIR2 resistance. These results show that the human and viral proteins evolved completely different recognition modes for the same substrate and reveal that some TM sequences may be incompatible with MIR2 activity even when no specific recognition motif is required.",
        "method_text": "The DMS library was made using overlap PCR with primers (IDT) containing NNN mixed bases and cloned into pHAGE-eF1a-MCS-IRES-ZsGreen using T4 ligase (NEB). Ligation reactions were transformed into XL1-Blue E. coli and colonies counted to ensure each position had at least 200 transformants to provide good coverage of 64 possible DNA variants.  Colonies were washed directly from LB-Agar plates into LB broth and grown until cultures were turbid (~2 hours) before plasmid DNA was recovered by miniprep (Qiagen).  1 µg of DNA from each position was combined to provide a deep mutational scanning library with complete coverage along the CD86 TM domain.  \r\n\r\nLentivirus produced from the library was titrated to result in ~10-20% transduction efficiency of 300,000 HeLa cells resulting in 30-60,000 transduced cells in each replicate.  2 days post transduction, ZsGreen positive HeLa cells were sorted from each replicate.  These cells were expanded to fill one 6-well plate well (~1 million cells) before mRNA was harvested from half of the cells (Population I), with the remainder sorted for CD86 surface expression.  CD86 positive cells were again grown to confluence before mRNA was harvested from a third of the cells (Population II), with the remainder split in two and transduced with either MARCH1 or MIR2 transducing around half of the cells as measured by mCherry expression.  Cells were expanded to confluence and sorted on mCherry expression. This population was expanded and mRNA harvested from half of the cells (Population III).  The other half was incubated with 150 ng/ml of doxycycline for 48 hours to induce MARCH1/MIR2 expression.  Cells were stained for CD86 surface expression and cells containing CD86 variants that were resistant to MARCH1 or MIR2 recovered and expanded before mRNA was harvested (Population IV).\r\n\r\nEnrichment scores of Population II versus Population I were calculated to determine cell surface levels of variant CD86 molecules.  Enrichment scores of Population IV versus Population III were used to determine which variants were poor MARCH1 or MIR2 substrates.\r\n\r\nCount Data Column Titles in CD86 Surface Expression:\r\n\r\nReplicate_x_c_0 = GFP+ Population I\r\nReplicate_x_c_1 = CD86+ Population II\r\n\r\nCount Data Column Titles in score set CD86 susceptibility to MARCH1 :\r\n\r\nReplicate_x_c_0 = CD86+ Before MARCH1 expression - Population III\r\nReplicate_x_c_1 = CD86+ After MARCH1 expression - Population IV\r\n\r\nCount Data Column Titles in score set CD86 susceptibility to MIR2:\r\n\r\nReplicate_x_c_0 = CD86+ Before MARCH1 expression - Population III\r\nReplicate_x_c_3 = CD86+ After MARCH1 expression - Population IV",
        "short_description": "A deep mutational screen of the CD86 transmembrane domain (residues 244-270) to compare the features that are recognised by the human E3 ligase MARCH1 versus the KSHV E3 ligase MIR2.",
        "title": "MARCH1 and MIR2 recognize different features of human CD86",
        "keywords": [
            {
                "text": "MIR2"
            },
            {
                "text": "CD86"
            },
            {
                "text": "Flow Cytometry"
            },
            {
                "text": "DMS"
            },
            {
                "text": "mRNA"
            },
            {
                "text": "MARCH1"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA661137",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA661137",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0001-7684-5841"
        ],
        "scoresets": [
            "urn:mavedb:00000046-a-1",
            "urn:mavedb:00000046-a-3",
            "urn:mavedb:00000046-a-2"
        ],
        "experimentset": "urn:mavedb:00000046"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000029-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of SORT1 enhancer in HepG2 cells.",
        "title": "Saturation mutagenesis MPRA of SORT1 enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "SORT1"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444732",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444732",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444730",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444730",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000029-a-1",
            "urn:mavedb:00000029-a-2"
        ],
        "experimentset": "urn:mavedb:00000029"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000031-b",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of TERT promoter in glioblastoma SF7996 (GBM) cells.",
        "title": "Saturation mutagenesis MPRA of TERT promoter, GBM",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            },
            {
                "text": "TERT"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444734",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444734",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000031-b-1"
        ],
        "experimentset": "urn:mavedb:00000031"
    },
    {
        "creation_date": "2018-06-29",
        "modification_date": "2019-08-08",
        "urn": "urn:mavedb:00000001-c",
        "publish_date": "2018-06-29",
        "created_by": "0000-0003-1628-9390",
        "modified_by": "0000-0003-1628-9390",
        "extra_metadata": {},
        "abstract_text": "Although we now routinely sequence human genomes, we can confidently identify only a fraction of the sequence variants that have a functional impact. Here, we developed a deep mutational scanning framework that produces exhaustive maps for human missense variants by combining random codon mutagenesis and multiplexed functional variation assays with computational imputation and refinement. We applied this framework to four proteins corresponding to six human genes: UBE2I (encoding SUMO E2 conjugase), SUMO1 (small ubiquitin-like modifier), TPK1 (thiamin pyrophosphokinase), and CALM1/2/3 (three genes encoding the protein calmodulin). The resulting maps recapitulate known protein features and confidently identify pathogenic variation. Assays potentially amenable to deep mutational scanning are already available for 57% of human disease genes, suggesting that DMS could ultimately map functional variation for all human disease genes.",
        "method_text": "A Deep Mutational Scan of Calmodulin (*CALM1*) using functional complementation in yeast was performed using DMS-TileSeq and a machine-learning method was used to impute the effects of missing variants and refine measurements of lower confidence. See [**Weile *et al.* 2017**](http://msb.embopress.org/content/13/12/957) for details.",
        "short_description": "A Deep Mutational Scan of human Calmodulin using functional complementation in yeast.",
        "title": "Calmodulin yeast complementation",
        "keywords": [
            {
                "text": "sumoylation"
            },
            {
                "text": "imputation"
            },
            {
                "text": "DMS-TileSeq"
            },
            {
                "text": "complementation"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRP109119",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP109119",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29269382",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29269382",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1628-9390"
        ],
        "scoresets": [
            "urn:mavedb:00000001-c-1",
            "urn:mavedb:00000001-c-2"
        ],
        "experimentset": "urn:mavedb:00000001"
    },
    {
        "creation_date": "2021-01-12",
        "modification_date": "2021-01-12",
        "urn": "urn:mavedb:00000055-a",
        "publish_date": "2021-01-12",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment identified candidate pharmacogenomic variants in NUDT15 that could contribute to thiopurine toxicity. Two functional assays were performed on the same variant library, one for NUDT15 activity and one for protein stability.",
        "method_text": "The NUDT15 variant library was synthesized by Twist Biosciences. The library included all possible single amino acid changes across the gene's coding region. Each variant was tagged with a random sequence barcode and the association between barcodes and variants was determined using PacBio SMRT sequencing as previously described for VAMP-seq. The barcoded library was introduced into a HEK293T landing pad cell line.\r\n\r\nCells expressing NUDT15 variants fused to EGFP were sorted into 4 bins based on EGFP signal normalized to mCherry by FACS. Genomic DNA was extracted from each bin and barcodes were sequenced on an Illumina HiSeq 2000 to obtain binwise variant-barcode counts. An unspecified number of replicates were performed.",
        "short_description": "NUDT15 protein stability measured by VAMP-seq.",
        "title": "NUDT15 protein stability assay",
        "keywords": [
            {
                "text": "VAMP-seq"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29785012",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29785012",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "32094176",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32094176",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000055-a-1"
        ],
        "experimentset": "urn:mavedb:00000055"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-f",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 12h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 12h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-f-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-g",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Dopamine",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-g-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2021-01-12",
        "modification_date": "2021-01-12",
        "urn": "urn:mavedb:00000056-a",
        "publish_date": "2021-01-12",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment identified candidate pharmacogenomic variants in NUDT15 that could contribute to thiopurine toxicity. Two functional assays were performed on the same variant library, one for NUDT15 activity and one for protein stability.",
        "method_text": "The NUDT15 variant library was synthesized by Twist Biosciences. The library included all possible single amino acid changes across the gene's coding region. Each variant was tagged with a random sequence barcode and the association between barcodes and variants was determined using PacBio SMRT sequencing as previously described for VAMP-seq. The barcoded library was introduced into a HEK293T landing pad cell line.\r\n\r\nThiopurine cytotoxicity was measured by comparing cells that were treated with 3$\\mu$m 6-thioguanine or culture media for 6 days. After treatment, genomic DNA was extracted and barcodes were sequenced on an Illumina HiSeq 2000 to obtain variant-barcode counts. Each drug treatment had 4 replicates.",
        "short_description": "FLAGGED FOR REMOVAL",
        "title": "FLAGGED FOR REMOVAL",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "32094176",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32094176",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000056-a-1"
        ],
        "experimentset": "urn:mavedb:00000056"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000023-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of LDLR promoter in HepG2 cells.",
        "title": "Saturation mutagenesis MPRA of LDLR promoter",
        "keywords": [
            {
                "text": "LDLR"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444724",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444724",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000023-a-1",
            "urn:mavedb:00000023-a-2"
        ],
        "experimentset": "urn:mavedb:00000023"
    },
    {
        "creation_date": "2018-06-25",
        "modification_date": "2019-07-26",
        "urn": "urn:mavedb:00000002-a",
        "publish_date": "2018-07-10",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This was the first published deep mutational scan. The experiment quantified binding affinity between the human YAP65 (YAP1) WW domain and a peptide binding partner using phage display. The phage display selection was tuned such that the enrichment in each round was moderate, allowing inefficient binders to be maintained in the population and subsequently quantified.",
        "method_text": "The target sequence was a codon-optimized human YAP65 WW domain. The variant library was constructed using doped oligo synthesis, with 0.7% of each non-target base at each position. The phage display was performed using T7 phage and selection for binding to biotinylated GTPPPPYTVG peptide attached to streptavidin-coated magnetic beads. Paired-end Illumina sequencing was performed such that both forward and reverse reads fully overlapped the variable region.",
        "short_description": "Deep mutational scan of the hYAP65 WW domain using phage display.",
        "title": "YAP65 WW domain",
        "keywords": [
            {
                "text": "WW domain"
            },
            {
                "text": "Phage display"
            },
            {
                "text": "doped oligo synthesis"
            },
            {
                "text": "Binding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRP002725",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP002725",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "23035249",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23035249",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "20711194",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/20711194",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-7614-1713"
        ],
        "scoresets": [
            "urn:mavedb:00000002-a-1",
            "urn:mavedb:00000002-a-2"
        ],
        "experimentset": "urn:mavedb:00000002"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000034-b",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of ZRS enhancer in NIH3T3 cells. Co-transfected with Hoxd13 and Hand2.",
        "title": "Saturation mutagenesis MPRA of ZRS enhancer, Hoxd13+Hand2",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444737",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444737",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444909",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444909",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444910",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444910",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444911",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444911",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444810",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444810",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444811",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444811",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444812",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444812",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000034-b-1"
        ],
        "experimentset": "urn:mavedb:00000034"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000026-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of MYC enhancer (rs11986220) in LNCaP cells with 100nM DHT.",
        "title": "Saturation mutagenesis MPRA of MYC enhancer (rs11986220)",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "MYC"
            },
            {
                "text": "rs11986220"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444726",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444726",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000026-a-1"
        ],
        "experimentset": "urn:mavedb:00000026"
    },
    {
        "creation_date": "2020-08-23",
        "modification_date": "2020-12-10",
        "urn": "urn:mavedb:00000052-a",
        "publish_date": "2020-12-10",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study generated thousands of mutated sequence on Gcn4 activation domain which contains one or several amino acid substitutions. They used a high-throughput fluorescent reporter assay to identify the transcription ability of mutated Gcn4 sequences through cell sorting.",
        "method_text": "The designed mutated Gcn4 activation domain was combined to a synthetic transcription factor and expressed in yeast. The transcription factor is tailed with mCherry and functioning transcription factor is able to facilitate the expression of GFP which is the genome-integrated reporter gene. Cells with distinct Gcn4 activity are sorted by fluorescence-activated cell sorting system to several bins according to the ratio of GFP and mCherry fluorescence. The cells are sorted into 8 bins: bin 1 with low GFP or mCherry level; bin 2 with low GFP level and normal mCherry level; and the other bins are evenly partitioned according to the ratio of the two fluorscence. The variant abundance is determined by high-throughput sequencing in an Illumina platform. This process is repeated one more time.",
        "short_description": "Mutagenesis study of Gcn4 activation domain in complete media using fluorescent reporter assay.",
        "title": "Gcn4 activation domain activity",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.17632/rbfr6m4733.1",
                "url": "https://doi.org/10.17632/rbfr6m4733.1",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "29525204",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29525204",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000052-a-1"
        ],
        "experimentset": "urn:mavedb:00000052"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-c",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Miconazole",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-c-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2021-03-14",
        "modification_date": "2021-04-15",
        "urn": "urn:mavedb:00000063-b",
        "publish_date": "2021-04-15",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study tested the variant effects of <i>E.coli</i> dihydrofolate reductase (DHFR) whose function is necessary for the survival of bacteria. The study cultured the bacteria in an early Log phase growth period without the control of Lon protease and determined the variant frequency change after cultivation, indicating the impact of DHFR variants.",
        "method_text": "The variant library in this study is generated by parallel inverse PCR reactions. An <i>E.coli</i> strain with deficient Lon gene is introduced with the variant library and cultivated. The growth rates of the bacteria harbouring each variant at several timepoints are determined by Illumina NextSeq, and the results are analyzed by Enrich2. The experiments are repeated three times in total and the final fitness values are the average of them.",
        "short_description": "Growth rate of E.coli with mutated dihydrofolate reductase (DHFR) with deficient Lon protease",
        "title": "Growth rate of mutated DHFR with deficient Lon",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA590072",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA590072",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.7554/eLife.53476",
                "url": "https://doi.org/10.7554/eLife.53476",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32701056",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32701056",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000063-b-1"
        ],
        "experimentset": "urn:mavedb:00000063"
    },
    {
        "creation_date": "2019-08-08",
        "modification_date": "2019-08-08",
        "urn": "urn:mavedb:00000042-a",
        "publish_date": "2019-08-08",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This is a dataset demonstrating the use of landing pad cell lines to generate recombinant mammalian cells. The experiment measured the effect of mutating the start codon of an EGFP construct with an N-terminal ubiquitin fusion. Once the ubiquitin is removed by cellular DUBs, the protein exposes a new N-terminal amino acid, which may target the protein for degradation.",
        "method_text": "Plasmids with an NNN N-terminal codon were created and introduced into HEK293T cells. Cells were sorted into four equally sized bins based on fluorescence and the genomic DNA containing the NNN codon was sequenced using Illumina amplicon sequencing.",
        "short_description": "Mutagenesis of the start codon of EGFP and its effect on an N-terminal fusion.",
        "title": "EGFP N-terminal codon",
        "keywords": [
            {
                "text": "NNN mutagenesis"
            },
            {
                "text": "FACS"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRP095490",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRP095490",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "28335006",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/28335006",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000042-a-1"
        ],
        "experimentset": "urn:mavedb:00000042"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000016-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of FOXE1 promoter in HeLa cells.",
        "title": "Saturation mutagenesis MPRA of FOXE1 promoter",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "FOXE1"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444716",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444716",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000016-a-1"
        ],
        "experimentset": "urn:mavedb:00000016"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000020-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of HNF4A promoter in HEK293T cells.",
        "title": "Saturation mutagenesis MPRA of HNF4A promoter",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            },
            {
                "text": "HNF4A"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444720",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444720",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000020-a-1"
        ],
        "experimentset": "urn:mavedb:00000020"
    },
    {
        "creation_date": "2019-02-17",
        "modification_date": "2019-07-28",
        "urn": "urn:mavedb:00000009-a",
        "publish_date": "2019-02-18",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured the impact of nearly all possible point mutations in the *SUL1* promoter, which is frequently amplified under sulfate-limited growth conditions. The results demonstrated that the optimal set of observed point mutations were able to increase organismal fitness by 11%, which is far below the fitness increases previously measured for amplification of *SUL1* (35% or higher). These experiments also revealed the fitness effects of creating new transcription factor binding sites in the existing promoter sequence.",
        "method_text": "Variants were generated using error-prone PCR and linked to 12-base DNA barcodes. The relationship between barcode and variant sequence was determined using subassembly [Hiatt et al.]. Yeast strains with genomic SUl1 deletions were transformed with a centromeric plasmid containing SUL1 with a barcoded variant promoter. Cells were cultured in sulfate- or glucose- limited conditions using chemostats.",
        "short_description": "Comprehensive analysis of the SUL1 promoter of Saccharomyces cerevisiae under glucose and sulfate limited growth.",
        "title": "Comprehensive analysis of the SUL1 promoter",
        "keywords": [
            {
                "text": "subassembly"
            },
            {
                "text": "error-prone PCR"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA273419",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA273419",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "20081835",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/20081835",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "26936925",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/26936925",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000009-a-2",
            "urn:mavedb:00000009-a-1"
        ],
        "experimentset": "urn:mavedb:00000009"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-c",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 6h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 6h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-c-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2020-06-18",
        "modification_date": "2020-06-19",
        "urn": "urn:mavedb:00000044-a",
        "publish_date": "2020-06-19",
        "created_by": "0000-0001-6713-6904",
        "modified_by": "0000-0001-6713-6904",
        "extra_metadata": {},
        "abstract_text": "The receptor binding domain (RBD) of the SARS-CoV-2 spike glycoprotein mediates viral attachment to ACE2 receptor, and is a major determinant of host range and a dominant target of neutralizing antibodies. Here we experimentally measure how all amino-acid mutations to the RBD affect expression of folded protein and its affinity for ACE2. Most mutations are deleterious for RBD expression and ACE2 binding, and we identify constrained regions on the RBD's surface that may be desirable targets for vaccines and antibody-based therapeutics. But a substantial number of mutations are well tolerated or even enhance ACE2 binding, including at ACE2 interface residues that vary across SARS-related coronaviruses. However, we find no evidence that these ACE2-affinity enhancing mutations have been selected in current SARS-CoV-2 pandemic isolates. We present an interactive visualization and open analysis pipeline to facilitate use of our dataset for vaccine design and functional annotation of mutations observed during viral surveillance. See the [preprint](https://www.biorxiv.org/content/10.1101/2020.06.17.157982v1) for more information.",
        "method_text": "We constructed duplicate libraries of mutant variants of the SARS-CoV-2 receptor binding domain (RBD), and cloned the library into a yeast surface-display platform. We used FACS-seq assays to determine variant expression and binding scores: 1) We labeled RBD variants for cell surface expression levels (a correlate of folding stability), and/or binding of soluble ACE2 ligand across a range of ACE2 concentrations. 2) We used FACS to partition our library into bins of expression or binding. 3) We sequenced the variants from within each bin. 4) From the distribution of sequence reads across FACS bins, we can reconstruct each variant's mean expression. 5) For binding values, by comparing binding as a function of ACE2 concentration, we calculate binding constants from per-variant titration curves.\r\n\r\nWe provide our duplicate library measurements at the level of individual variants within our library, which are described by unique molecular identifier barcodes downstream from the variant RBD coding sequence. We also provide decomposed single-mutant scores, which are the primary mutation scores we use in our analysis of the data. In each of these datasets, the binding score is a delta-log<sub>10</sub>(_K_<sub>D,app</sub>) metric from the variant titration curves, and the expression score is a delta-log(mean fluorescence intensity) measurement of cell surface expression. Both metrics are relative to the unmutated SARS-CoV-2 reference sequence phenotype, polarized such that a positive value indicates higher affinity or expression compared to unmutated SARS-CoV-2, and a negative value indicates decreased affinity or expression compared to unmutated SARS-CoV-2.\r\n\r\nSee the [preprint](https://www.biorxiv.org/content/10.1101/2020.06.17.157982v1) or [GitHub repository](https://github.com/jbloomlab/SARS-CoV-2-RBD_DMS) for additional information.",
        "short_description": "This experiment measures the effects on binding of variants and individual mutations in the SARS-CoV-2 RBD",
        "title": "Effects on binding of mutations in the SARS-CoV-2 RBD",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA639956",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA639956",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0001-6713-6904",
            "0000-0001-9278-3644",
            "0000-0003-1267-3408"
        ],
        "scoresets": [
            "urn:mavedb:00000044-a-1",
            "urn:mavedb:00000044-a-2"
        ],
        "experimentset": "urn:mavedb:00000044"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-01-17",
        "urn": "urn:mavedb:00000057-b",
        "publish_date": "2021-01-17",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors used saturation mutagenesis to study the variant effect of Ras, with the regulation of GTPase activating protein (GAP) but in the absence of guanine nucleotide exchange factor (GEF). The variants were selected by bacterial two-hybrid strategy.",
        "method_text": "The RAS mutant library was generated by oligonucleotide-directed mutagenesis. The mutant library was transfected into bacteria without GEF expression and the functioning RAS protein which will bind to GTP as well as Raf. The binding of these molecules can trigger the transcription of an antibiotic resistant factor. The library was separated to three sub-libraries in order to cover the whole RAS gene length which ranges from the residue 2-56, 57-111, and 112-166. These samples were selected individually. The samples in different sub-libraries were barcoded and pooled together for MiSeq sequencing.",
        "short_description": "Selection result of Ras mutants expressed in the presence of the GAP, but without the GEF",
        "title": "Attenuated-Ras",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "28686159",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/28686159",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000057-b-1"
        ],
        "experimentset": "urn:mavedb:00000057"
    },
    {
        "creation_date": "2020-08-23",
        "modification_date": "2020-12-04",
        "urn": "urn:mavedb:00000051-a",
        "publish_date": "2020-12-02",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-2449-7034",
        "extra_metadata": {},
        "abstract_text": "This study mutated the residues on CLS helix region of the bacterial inner membrane. The experiment links the insertion and self-association property of the tested region to the survive of bacteria and studied the membrane-protein energetics landscape of missense mutations of the target.",
        "method_text": "The C-terminal of L-Selectin is used as the membrane-spanning segment for dsT$\\beta$L in this experiment. The authors created forward and reverse primers of lengths 40-85 base pairs with the central codon replaced by NNS which encodes all possible amino acid substitutions on the target sequence. They leveraged a traditional assay, the TOXCAT-$\\beta$-lactamase (T$\\beta$L) screen, and adapted it to deep mutational scanning studies (dsT$\\beta$L). The tested sequence is expressed in between a chimera of ToxR dimerization-dependent transcriptional activator of a chloramphenicol-resistance gene and $\\beta$-lactamase. In this construct, the membrane integration of target sequence determines the bacterial resistance to ampicillin and the self-association correlates with the chloramphenicol resistance. Besides, the orientation to the membrane of this chimera is also crucial for survival. The selection result was determined by deep-sequencing using Illumina.",
        "short_description": "A deep mutational scanning experiment targeting the CLS helix region on the bacterial inner membrane.",
        "title": "C-terminal of L-Selectin (CLS)",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.7554/eLife.12125",
                "url": "https://doi.org/10.7554/eLife.12125",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "26824389",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/26824389",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000051-a-1"
        ],
        "experimentset": "urn:mavedb:00000051"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000027-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of PKLR promoter, 24h post-transfection in K562 cells.",
        "title": "Saturation mutagenesis MPRA of PKLR promoter, 24h",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "PKLR"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444728",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444728",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000027-a-1"
        ],
        "experimentset": "urn:mavedb:00000027"
    },
    {
        "creation_date": "2019-07-10",
        "modification_date": "2019-07-15",
        "urn": "urn:mavedb:00000035-a",
        "publish_date": "2019-07-15",
        "created_by": "0000-0002-4998-4368",
        "modified_by": "0000-0002-4998-4368",
        "extra_metadata": {},
        "abstract_text": "Coronary heart disease (CHD) is a leading cause of death worldwide. The risk of CHD can be reduced by LDL-cholesterol-lowering medications called statins that potently inhibit HMG-CoA reductase (HMGCR), the enzyme that catalyzes the rate-limiting reaction of the mevalonate pathway. Proactive maps of human HMGCR may be able to model patient response to statins and identify the statin with the greatest likelihood of efficacy.",
        "method_text": "The yeast-based assay of HMGCR is a functional complementation assay that assesses the ability of human HMGCR to rescue the growth of an hmg1 hmg2 double deletion yeast strain in glucose media (Basson et al. 1988). We followed the TileSeq approach (Weile & Sun et al, MSB, 2017) to produce variant effect maps of HMGCR in glucose media without a statin, and media supplemented with atorvastatin or rosuvastatin.",
        "short_description": "A deep mutational scan of human HMG-CoA reductase (HMGCR) based on a functional complementation assay in yeast.",
        "title": "HMGCR yeast complementation",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-4998-4368"
        ],
        "scoresets": [
            "urn:mavedb:00000035-a-2",
            "urn:mavedb:00000035-a-3",
            "urn:mavedb:00000035-a-1"
        ],
        "experimentset": "urn:mavedb:00000035"
    },
    {
        "creation_date": "2019-08-07",
        "modification_date": "2019-08-07",
        "urn": "urn:mavedb:00000040-a",
        "publish_date": "2019-08-07",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured the effect of variants in yeast HSP90 under different combinations of temperature (30C or 36C) and presence/absence of salt (0.5 M NaCl). The results explore the adaptive potential of this essential gene.",
        "method_text": "Fully randomized codons (NNN codons) were generated for each position and inserted into plasmids using a cassette ligation strategy. Yeast were grown in a dextrose shutoff strain, which grows normally on galactose but turns off expression of endogenous HSP90 in dextrose media. Cells were grown in galactose media to near saturation, after which they were grown on dextrose for 8 hours before being split into four cultures, one for each experimental condition. Time points for Illumina sequencing were taken during the experiment at different times based the overall growth rate of that condition.",
        "short_description": "Deep mutational scan of all single mutants in a nine-amino acid region of Hsp90 (Hsp82) in Saccharomyces cerevisiae under different combinations of temperature and salinity.",
        "title": "Deep mutational scan of HSP90 varying temperature and salt",
        "keywords": [
            {
                "text": "NNN mutagenesis"
            },
            {
                "text": "EMPIRIC"
            },
            {
                "text": "growth assay"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "24299404",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/24299404",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000040-a-1",
            "urn:mavedb:00000040-a-2",
            "urn:mavedb:00000040-a-3",
            "urn:mavedb:00000040-a-4"
        ],
        "experimentset": "urn:mavedb:00000040"
    },
    {
        "creation_date": "2018-07-10",
        "modification_date": "2019-07-28",
        "urn": "urn:mavedb:00000003-b",
        "publish_date": "2018-07-10",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "These experiments measured the functional consequences of mutations in the BRCA1 RING domain, where most clinically-relevant single nucleotide variants reside. One goal of the study was to create a \"look-up table\" of single nucleotide variants for clinical use, by prospectively measuring the impact of all possible variants that are likely to appear in patients. The study combines two different assays - one based on E3 ubiquitin ligase activity and one based on BRCA1-BARD1 heterodimer formation - and makes one of the first attempts to combine data from different MAVEs on the same target.\r\n\r\nThis entry contains scores from the yeast two-hybrid assay, which tested the BRCA1-BARD1 heterodimer formation in BRCA1 variants.",
        "method_text": "Variants were constructed using PALS (Programmed Allelic Series) [Hiatt et al.]. Full-length variant sequences were associated with 16-base DNA barcodes using the subassembly method [Kitzman et al.]. Barcodes were sequenced and counted for each of four time points (0h, 16h, 41h, 64h) in three replicates, and the barcode counts were used to quantify variant enrichment/depletion.",
        "short_description": "Deep mutational scan of the BRCA1 RING domain using a yeast two-hybrid heterodimerization assay.",
        "title": "BRCA1 Y2H",
        "keywords": [
            {
                "text": "subassembly"
            },
            {
                "text": "RING domain"
            },
            {
                "text": "Yeast two-hybrid"
            },
            {
                "text": "ubiquitin"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "20081835",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/20081835",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "25559584",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/25559584",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "25823446",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/25823446",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2870-5099"
        ],
        "scoresets": [
            "urn:mavedb:00000003-b-2",
            "urn:mavedb:00000003-b-1"
        ],
        "experimentset": "urn:mavedb:00000003"
    },
    {
        "creation_date": "2019-07-29",
        "modification_date": "2019-07-29",
        "urn": "urn:mavedb:00000037-a",
        "publish_date": "2019-07-29",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study performed a bulk growth competition experiment measuring the effect of point mutations on ubiquitin structure and function. The results were consistent with previous studies of individual mutants as well as Alanine-scanning. Positions were clustered by their tolerance of mutations and highly sensitive regions were mapped.",
        "method_text": "Variant construction, DNA sequencing, and analysis was conducted using EMPIRIC [Hietpas et al.]. Variants were transformed into the Sub328 ubiquitin shutoff strain, which produces sufficient ubiquitin in galactose but not in dextrose. The competition assay was therefore performed in dextrose media, whereas the libraries were constructed and maintained in galactose media.",
        "short_description": "Deep mutational scan of ubiquitin in a yeast growth assay",
        "title": "Ubiquitin yeast growth",
        "keywords": [
            {
                "text": "ubiquitin"
            },
            {
                "text": "EMPIRIC"
            },
            {
                "text": "growth assay"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "21464309",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/21464309",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23376099",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23376099",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000037-a-1"
        ],
        "experimentset": "urn:mavedb:00000037"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-f",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Spermidine",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-f-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-j",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Tunicamycin",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-j-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2019-01-23",
        "modification_date": "2019-07-26",
        "urn": "urn:mavedb:00000007-a",
        "publish_date": "2019-01-24",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study described the functional consequence of over 100,000 enhancer variants *in vivo* in mouse liver. Two human enhancers (ALDOB, ECR11) and one mouse enhancer (LTV1) were known to be active in mouse liver and therefore variants in these enhancers should show a measurable difference in transcription. The results were broadly consistent with evolutionary data and transcription factor binding sites, but were not always concordant demonstrating the importance of measuring the effect of enhancer variants directly.\r\n\r\nThis MaveDB entry describes the ECR11 enhancer data. Datasets for other enhancers described in the same publication are also available: [ALDOB](https://www.mavedb.org/experiment/urn:mavedb:00000006-a/) [LTV1](https://www.mavedb.org/experiment/urn:mavedb:00000008-a/)",
        "method_text": "Variants were constructed using doped oligo with 1% of each non-target base included at each position (ratio of 97:1:1:1). Full-length enhancer haplotypes were assembled and cloned into tagged pGL4.23 plasmids. Each variant haplotype was tagged with a 20-bp sequence, with one tag per haplotype in almost all cases. Each single nucleotide change was present in at least 42 haplotypes. \r\n\r\nThe enhancers were injected into the mouse tail vein and mouse livers were harvested after 24h. RNA was isolated from fresh mouse livers, subjected to DNAseI treatment to remove any DNA contamination, reverse-transcribed into cDNA, and sequenced.\r\n\r\nTwo sets of sequencing reactions were performed. One used short Illumina reads (42 total cycles) to sequence the tag sequence used for quantifying each enhancer's activity. The other used subassembly synthetic long read sequencing to associate the tags with the full-length enhancer haplotypes.",
        "short_description": "Massively parallel functional dissection of the ECR11 enhancer in a mouse liver transcription assay.",
        "title": "Massively parallel functional dissection of ECR11 enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "doped oligo synthesis"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "liver"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRA049159",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRA049159",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "22371081",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/22371081",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000007-a-1"
        ],
        "experimentset": "urn:mavedb:00000007"
    },
    {
        "creation_date": "2020-11-11",
        "modification_date": "2020-11-11",
        "urn": "urn:mavedb:00000048-a",
        "publish_date": "2020-11-11",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment utilised site-saturation mutagenesis (SSM) to measure the functional consequences of mutations in the human chemokine receptor, CXCR4 and to map ligand interaction sites. Cells were selected for CXCR4 surface expression.",
        "method_text": "The human CXCR4 sequence was generated by oligo assembly and fused to a c-myc tag. SSM libraries were generated by overlapping PCR using primers with an NNK codon, as described by Procko et al, 2013.\r\nThe SSM library was transfected into CXCR4-knockout human Expi293F cells using pCEP4. \r\nSurface receptor expression was measured by anti-myc staining and cells were sorted on a BD FACSAria II.\r\nTwo replicates each were performed with anti-myc-FITC and anti-myc-Alexa.\r\nTotal RNA was extracted and PCR-amplified before sequencing by Illumina MiSeq v 3 or HiSeq 2500. \r\n\r\nRaw data available from GEO under accession [GSE100368](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100368).",
        "short_description": "Deep mutational scan selecting for cell surface expression of CXCR4 in Expi293F cells.",
        "title": "CXCR4 surface expression",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29678950",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29678950",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23827138",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23827138",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-6681-7994"
        ],
        "scoresets": [
            "urn:mavedb:00000048-a-1"
        ],
        "experimentset": "urn:mavedb:00000048"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000034-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of ZRS enhancer in NIH3T3 cells. Co-transfected with Hoxd13.",
        "title": "Saturation mutagenesis MPRA of ZRS enhancer, Hoxd13",
        "keywords": [
            {
                "text": "ZRS"
            },
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444737",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444737",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444815",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444815",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444814",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444814",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444813",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444813",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444908",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444908",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444907",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444907",
                "dbversion": null,
                "dbname": "SRA"
            },
            {
                "identifier": "SRX5444906",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444906",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000034-a-1"
        ],
        "experimentset": "urn:mavedb:00000034"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-e",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 10h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 10h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-e-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000032-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of UC88 (ultraconserved element) enhancer in Neuro-2a cells.",
        "title": "Saturation mutagenesis MPRA of UC88 enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "UC88"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444735",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444735",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000032-a-1"
        ],
        "experimentset": "urn:mavedb:00000032"
    },
    {
        "creation_date": "2019-02-17",
        "modification_date": "2019-07-28",
        "urn": "urn:mavedb:00000010-a",
        "publish_date": "2019-02-18",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured the sequence-function relationships for variants in a common, eukaryotic RNA binding domain, the RRM2 domain of yeast Pab1. The results identified clusters of residues with similar mutational patterns as well as highly-conserved residues that are critical for stability and/or function.",
        "method_text": "Mutants were tested by measuring the ability of Pab1 genes containing variants in RRM2 to complement *pab1*$\\Delta$. Variants were generated using doped oligo synthesis, with a 4% error rate. Variant RRM2 domains were sequenced such that the paired-end Illumina reads overlapped in the region of interest.",
        "short_description": "Deep mutational scan of the RRM2 domain of the Saccharomyces cerevisiae poly(A)-binding protein (Pab1).",
        "title": "Deep mutational scan of Pab1 RRM domain",
        "keywords": [
            {
                "text": "doped oligo synthesis"
            },
            {
                "text": "RNA-binding"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "24064791",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/24064791",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000010-a-1"
        ],
        "experimentset": "urn:mavedb:00000010"
    },
    {
        "creation_date": "2021-01-12",
        "modification_date": "2021-01-12",
        "urn": "urn:mavedb:00000055-b",
        "publish_date": "2021-01-12",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment identified candidate pharmacogenomic variants in NUDT15 that could contribute to thiopurine toxicity. Two functional assays were performed on the same variant library, one for NUDT15 activity and one for protein stability.",
        "method_text": "The NUDT15 variant library was synthesized by Twist Biosciences. The library included all possible single amino acid changes across the gene's coding region. Each variant was tagged with a random sequence barcode and the association between barcodes and variants was determined using PacBio SMRT sequencing as previously described for VAMP-seq. The barcoded library was introduced into a HEK293T landing pad cell line.\r\nThiopurine cytotoxicity was measured by comparing cells that were treated with 3$\\mu$m 6-thioguanine or culture media for 6 days. After treatment, genomic DNA was extracted and barcodes were sequenced on an Illumina HiSeq 2000 to obtain variant-barcode counts. Each drug treatment had 4 replicates.",
        "short_description": "NUDT15 activity scores measured by a thiopurine-cytotoxicity-based screen.",
        "title": "NUDT15 activity scores",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "32094176",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32094176",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000055-b-1"
        ],
        "experimentset": "urn:mavedb:00000055"
    },
    {
        "creation_date": "2020-10-15",
        "modification_date": "2020-11-25",
        "urn": "urn:mavedb:00000050-a",
        "publish_date": "2020-11-25",
        "created_by": "0000-0002-6145-882X",
        "modified_by": "0000-0002-6145-882X",
        "extra_metadata": {},
        "abstract_text": "In this study a massively parallel screen was performed in human cells to identify loss-of-function missense variants in the key DNA mismatch repair factor MSH2.",
        "method_text": "Massively parallel single codon mutagenesis was used to generate comprehensive libraries of MSH2 cDNA variants. The resulting libraries were cloned into inducible lentiviruses and used to transduce HAP1 MSH2-null cells at an MOI < 1 (one integrated copy/cell).  MSH2 functional complementation was tested by inducing the stably integrated MSH2 variants and selecting with the compound 6-TG which is selectively toxic to MMR deficient cells.  Deep amplicon sequencing was used to quantify enriched LOF alleles of MSH2 in the 6-TG selected condition relative to the starting population and to mock conditions.",
        "short_description": "Massively parallel functional testing of MSH2 missense variants conferring Lynch Syndrome risk",
        "title": "MSH2 deep mutational scan",
        "keywords": [
            {
                "text": "MSH2"
            },
            {
                "text": "deep mutational scanning"
            },
            {
                "text": "Lynch Syndrome"
            }
        ],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.06.03.133017",
                "url": "https://doi.org/10.1101/2020.06.03.133017",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-6145-882X"
        ],
        "scoresets": [
            "urn:mavedb:00000050-a-1"
        ],
        "experimentset": "urn:mavedb:00000050"
    },
    {
        "creation_date": "2020-11-11",
        "modification_date": "2020-11-11",
        "urn": "urn:mavedb:00000048-b",
        "publish_date": "2020-11-11",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment utilised site-saturation mutagenesis (SSM) to measure the functional consequences of mutations in the human chemokine receptor, CXCR4 and to map ligand interaction sites. Cells were selected for binding to the CXCR4 physiological ligand CXCL12.",
        "method_text": "The human CXCR4 sequence was generated by oligo assembly and fused to a c-myc tag. SSM libraries were generated by overlapping PCR using primers with an NNK codon, as described by Procko et al, 2013.\r\nThe SSM library was transfected into CXCR4-knockout human Expi293F cells using pCEP4. \r\nSurface receptor expression was measured by anti-myc-Alexa staining and cells were sorted on a BD FACSAria II.\r\nCells were incubated with CXCL12 fused to superfolder GFP (sf-GFP) and sorted for interaction with CXCL12-sfGFP. \r\nTotal RNA was extracted and PCR-amplified before sequencing by Illumina MiSeq v 3 or HiSeq 2500. \r\n\r\nRaw data available from GEO under accession [GSE100368](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100368).",
        "short_description": "Deep mutational scan selecting for CXCR4 binding to CXCL12 in Expi293F cells.",
        "title": "CXCR4 CXCL12 binding",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "29678950",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/29678950",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23827138",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23827138",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0001-6681-7994"
        ],
        "scoresets": [
            "urn:mavedb:00000048-b-1"
        ],
        "experimentset": "urn:mavedb:00000048"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000021-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of IRF4 enhancer in SK-MEL-28 cells.",
        "title": "Saturation mutagenesis MPRA of IRF4 enhancer",
        "keywords": [
            {
                "text": "IRF4"
            },
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444721",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444721",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000021-a-1"
        ],
        "experimentset": "urn:mavedb:00000021"
    },
    {
        "creation_date": "2019-07-10",
        "modification_date": "2019-07-15",
        "urn": "urn:mavedb:00000036-a",
        "publish_date": "2019-07-15",
        "created_by": "0000-0002-4998-4368",
        "modified_by": "0000-0002-4998-4368",
        "extra_metadata": {},
        "abstract_text": "Coronary heart disease (CHD) is a leading cause of death worldwide. A major risk factor of CHD is high low-density lipoprotein cholesterol (LDL-C), which is the defining feature of familial hypercholesterolemia, a genetic disorder characterized by mutations in genes involved in cholesterol uptake, such as LDLRAP1. Proactive maps of LDLRAP1 may identify pathogenic variation of autosomal recessive hypercholesterolemia (ARH) for early diagnosis of ARH.",
        "method_text": "The yeast-based assay of LDLRAP1 is a yeast two-hybrid assay that assesses the ability of human LDLRAP1 to interact with protein partners, which would activate the expression of HIS3 to allow histidine production and the growth of a yeast strain in selective media lacking histidine (Fields and Song 1989). We followed the TileSeq approach (Weile & Sun et al, MSB, 2017) to produce variant effect maps of LDLRAP1 based on its interaction with OBFC1 or AP2B1.",
        "short_description": "A deep mutational scan of low-density lipoprotein receptor adaptor protein 1 (LDLRAP1) based on a yeast two-hybrid assay.",
        "title": "LDLRAP1 Y2H",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-4998-4368"
        ],
        "scoresets": [
            "urn:mavedb:00000036-a-1",
            "urn:mavedb:00000036-a-2"
        ],
        "experimentset": "urn:mavedb:00000036"
    },
    {
        "creation_date": "2019-08-08",
        "modification_date": "2019-08-09",
        "urn": "urn:mavedb:00000041-b",
        "publish_date": "2019-08-08",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study infers the activity of variants in Src kinases's SH4 domain by measuring their effects on yeast growth, and therefore phosphotransferase activity. The resulting dataset includes variants classified as gain of function, loss of function. or neutral.",
        "method_text": "Variants in the Src SH4 domain were generated using NNK mutagenesis. Variants were transformed into yeast on plasmids and the plasmid barcodes were sequenced at three time points determined by OD. Overlapping paired-end reads were sequenced on Illumina NextSeq and assembled using PEAR.",
        "short_description": "Deep mutational scan of the Src kinase SH4 domain.",
        "title": "Deep mutational scan of Src SH4",
        "keywords": [
            {
                "text": "kinase"
            },
            {
                "text": "NNK mutagenesis"
            },
            {
                "text": "growth assay"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA464305",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA464305",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "30956043",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/30956043",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000041-b-1"
        ],
        "experimentset": "urn:mavedb:00000041"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000033-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of ZFAND3 enhancer in MIN6 cells.",
        "title": "Saturation mutagenesis MPRA of ZFAND3 enhancer",
        "keywords": [
            {
                "text": "enhancer"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "ZFAND3"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444736",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444736",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000033-a-1"
        ],
        "experimentset": "urn:mavedb:00000033"
    },
    {
        "creation_date": "2018-11-09",
        "modification_date": "2019-10-22",
        "urn": "urn:mavedb:00000005-a",
        "publish_date": "2019-10-22",
        "created_by": "0000-0003-1628-9390",
        "modified_by": "0000-0003-1628-9390",
        "extra_metadata": {},
        "abstract_text": "Classical homocystinuria--characterized by excessive levels of total homocysteine in plasma--is caused by primarily-rare variants in the cystathionine-beta-synthase (CBS) gene. With early detection, existing therapies are highly effective, e.g., most patients respond to vitamin B6 therapy. Functional CBS variants, or deleterious variants that respond to vitamin B6, can be detected based on their ability restore growth in yeast cells lacking CYS4 (the yeast ortholog of CBS). Here we describe a comprehensive missense variant effect map for CBS.",
        "method_text": "We reimplemented a previously validated humanized yeast model (Kruger & Cox, PNAS, 1994), confirming that expression of human CBS from the hORFeome collection restores the ability of a yeast cys4&Delta; strain to grow without supplementation of glutathione. Coupling this functional complementation with our recently developed framework for exhaustively mapping functional coding variants (Weile & Sun et al, MSB, 2017), we attempted to test the functional impact as well as the vitamin B6 remediability of all possible missense CBS variants in parallel. \r\n\r\nFirst, we constructed a library of CBS variants using our previously described POPCode mutagenesis method (Weile & Sun et al, MSB, 2017). The variant library, initially generated as a pool of amplicons, was transferred en masse into the appropriate yeast expression vector via two steps of recombinational subcloning.  The resulting library of variant expression clones was then transformed en masse into the yeast cys4 mutant strain. \r\n\r\nNext, pools of transformed yeast cys4 mutant strains were grown competitively in cysteine-lacking medium supplemented with low (0, 1ng/ml) or high (400 ng/ml) concentrations of vitamin B6. Allele frequencies of CBS variants before and after selection were determined by next-generation sequencing. To ensure accuracy of allele frequency estimates, we following the TileSeq approach (Weile & Sun et al, MSB, 2017) in which sequencing is applied to a tiling set of ~100 nt segments of the gene library, enabling sequencing reads from both forward and reverse strands of each template cluster on the flow cell.  Sequencing was performed such that both forward and reverse strands of each nucleotide position were covered by ~2M reads. \r\n\r\nThe sequence analysis code can be found at https://bitbucket.org/rothlabto/tileseq_package\r\n\r\nSee https://www.biorxiv.org/content/early/2018/11/19/473983 for more information.",
        "short_description": "A Deep Mutational Scan of the human Cystathionine beta-Synthase (CBS) using functional complementation in yeast",
        "title": "CBS yeast complementation",
        "keywords": [
            {
                "text": "imputation"
            },
            {
                "text": "Vitamin B6"
            },
            {
                "text": "homocystinuria"
            },
            {
                "text": "DMS-TileSeq"
            },
            {
                "text": "complementation"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [],
        "contributors": [
            "0000-0003-1628-9390"
        ],
        "scoresets": [
            "urn:mavedb:00000005-a-1",
            "urn:mavedb:00000005-a-2",
            "urn:mavedb:00000005-a-5",
            "urn:mavedb:00000005-a-6",
            "urn:mavedb:00000005-a-4",
            "urn:mavedb:00000005-a-3"
        ],
        "experimentset": "urn:mavedb:00000005"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-01-17",
        "urn": "urn:mavedb:00000057-a",
        "publish_date": "2021-01-17",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors used saturation mutagenesis to study the variant effect of Ras, without the regulation of GTPase activating protein (GAP) or guanine nucleotide exchange factor (GEF). The variants were selected using a bacterial two-hybrid strategy.",
        "method_text": "The RAS mutant library was generated by oligonucleotide-directed mutagenesis. The mutant library was transfected into bacteria without GAP or GEF expression and the functioning RAS protein which will bind to GTP as well as Raf. The binding of these molecules can trigger the transcription of an antibiotic resistant factor. The library was separated into three sub-libraries in order to cover the whole RAS gene length which ranges from the residue 2-56, 57-111, and 112-166. These samples were selected individually. The samples in different sub-libraries were barcoded and pooled together for MiSeq sequencing.",
        "short_description": "Selection result of Ras mutants expressed without the GAP or the GEF",
        "title": "Unregulated-Ras",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "28686159",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/28686159",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000057-a-1"
        ],
        "experimentset": "urn:mavedb:00000057"
    },
    {
        "creation_date": "2019-07-29",
        "modification_date": "2019-07-29",
        "urn": "urn:mavedb:00000038-b",
        "publish_date": "2019-07-29",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured the effect of single amino acid changes in ubiquitin on binding to E1 (Uba1). Combined with work from a previous study on the effect of ubiquitin mutations on yeast growth rate, this showed that ubiquitin-E1 binding was not linearly related to growth rate and that mutations in ubiquitin are likely to affect multiple function that modulate growth rate.",
        "method_text": "This experiment used the same library of ubiquitin variants as previously described in Roscoe et al. 2013. The ubiqutin variants were displayed as C-terminal fusions with Aga2-HA and reacted with E1. Bound cells were isolated using FACS and deep sequencing was used to quantify enrichment or depletion of cells in the bound population.\r\n\r\nThe excess E1 assay was performed on two separate sub-regions of ubiquitin.",
        "short_description": "Deep mutational scan of ubiquitin measuring binding to E1 with yeast display with excess E1.",
        "title": "Ubiquitin E1 binding, excess E1",
        "keywords": [
            {
                "text": "ubiquitin"
            },
            {
                "text": "E1"
            },
            {
                "text": "yeast display"
            },
            {
                "text": "Binding"
            },
            {
                "text": "FACS"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "24862281",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/24862281",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23376099",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23376099",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000038-b-1",
            "urn:mavedb:00000038-b-2"
        ],
        "experimentset": "urn:mavedb:00000038"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-d",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with Melatonin",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA564806",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA564806",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-d-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2020-06-29",
        "modification_date": "2020-06-29",
        "urn": "urn:mavedb:00000045-a",
        "publish_date": "2020-06-29",
        "created_by": "0000-0002-2020-2641",
        "modified_by": "0000-0002-2020-2641",
        "extra_metadata": {},
        "abstract_text": "alpha-Synuclein is a conformationally dynamic protein linked to a variety of neurodegenerative diseases, including Parkinson’s. Conformational transitions of this protein are believed to contribute to disease etiology, but the conformations that drive pathology remain unclear. To address this question, we screened an exhaustive library of alpha-synuclein missense variants for their toxicity in yeast, a well-validated cellular model for alpha-synuclein pathobiology. By examining the pattern of mutations that disrupts cellular toxicity, we were able to build a model for the structure of the toxic species.",
        "method_text": "A double-stranded DNA library based on human alpha-synuclein cDNA was produced by commercial oligonucleotide synthesis and assembly. The designed library encodes all single missense variants of alpha-synuclein, each encoded by a single codon. This library was cloned in frame with a C-terminal GFP fusion, and 26bp random barcodes were appended 3’ to the stop codon to facilitate repeated selection. This construct was cloned under control of an inducible promoter and transformed into E. coli. Following restrictive transformation, the final library diversity was ~60,000 unique clones, corresponding to ~20 barcodes per missense variant. The barcoded coding region was amplified and analyzed by long-read MiSeq in order to associate barcodes with coding sequences. The resulting lookup table expedites subsequent quantification of variant frequencies.\r\nThis plasmid library was then transformed into yeast. Selection was performed by inducing expression and collecting aliquots over time. Additional experiments were performed in yeast treated with small molecules. Finally, the expression level of each variant was estimated by cell sorting yeast cells based on the fluorescence of the GFP fusion.",
        "short_description": "The toxicity of alpha-synuclein missense variants was determined by measuring their change in frequency during yeast outgrowth",
        "title": "Deep Mutational Scanning of alpha-Synuclein based on Toxicity in Yeast Treated with MG-132",
        "keywords": [
            {
                "text": "alpha-synuclein"
            },
            {
                "text": "yeast"
            },
            {
                "text": "protein folding"
            }
        ],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1101/2020.05.01.072884",
                "url": "https://doi.org/10.1101/2020.05.01.072884",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [],
        "contributors": [
            "0000-0002-2020-2641"
        ],
        "scoresets": [
            "urn:mavedb:00000045-a-1"
        ],
        "experimentset": "urn:mavedb:00000045"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000017-a",
        "publish_date": "2019-02-19",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of GP1BB promoter in HEL 92.1.7 cells.",
        "title": "Saturation mutagenesis MPRA of GP1BB promoter",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "GP1BB"
            },
            {
                "text": "promoter"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444717",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444717",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000017-a-1"
        ],
        "experimentset": "urn:mavedb:00000017"
    },
    {
        "creation_date": "2021-04-12",
        "modification_date": "2021-04-15",
        "urn": "urn:mavedb:00000064-a",
        "publish_date": "2021-04-15",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study tested the variant effects of _E.coli_ LamB which is the binding protein of phage &lambda; prion during infection. The bacteria are cultured in the media contains phage &lambda; and the growth rate for each mutant is determined to indicate its resistance to phage invasion.",
        "method_text": "The variant library in this study is generated by error-prone PCR and expressed in a lamB knockout _E.coli_ strain. The bacteria are cultured either in LB media as control group and LB with phage &lambda; as selection group. The frequency for each variant in those groups is determined by Illumina NextSeq using the Nextera kit.",
        "short_description": "Growth rate of E.coli with mutated LamB cultured with rich phage λ",
        "title": "LamB resistance to phage λ",
        "keywords": [],
        "sra_ids": [
            {
                "identifier": "PRJNA604031",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA604031",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1099/mgen.0.000364",
                "url": "https://doi.org/10.1099/mgen.0.000364",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "32238226",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/32238226",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000064-a-1"
        ],
        "experimentset": "urn:mavedb:00000064"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-h",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 48h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 48h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-h-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2019-07-29",
        "modification_date": "2019-07-29",
        "urn": "urn:mavedb:00000038-a",
        "publish_date": "2019-07-29",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This study measured the effect of single amino acid changes in ubiquitin on binding to E1 (Uba1). Combined with work from a previous study on the effect of ubiquitin mutations on yeast growth rate, this showed that ubiquitin-E1 binding was not linearly related to growth rate and that mutations in ubiquitin are likely to affect multiple function that modulate growth rate.",
        "method_text": "This experiment used the same library of ubiquitin variants as previously described in Roscoe et al. 2013. The ubiqutin variants were displayed as C-terminal fusions with Aga2-HA and reacted with E1. Bound cells were isolated using FACS and deep sequencing was used to quantify enrichment or depletion of cells in the bound population.",
        "short_description": "Deep mutational scan of ubiquitin measuring binding to E1 with yeast display with limiting E1.",
        "title": "Ubiquitin E1 binding, limiting E1",
        "keywords": [
            {
                "text": "ubiquitin"
            },
            {
                "text": "E1"
            },
            {
                "text": "yeast display"
            },
            {
                "text": "Binding"
            },
            {
                "text": "FACS"
            }
        ],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "24862281",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/24862281",
                "dbversion": null,
                "dbname": "PubMed"
            },
            {
                "identifier": "23376099",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/23376099",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000038-a-1"
        ],
        "experimentset": "urn:mavedb:00000038"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-01-17",
        "urn": "urn:mavedb:00000057-d",
        "publish_date": "2021-01-17",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors used saturation mutagenesis to study the variant effect of Ras, on the oncogenic G12V background, without the regulation of GTPase activating protein (GAP) or guanine nucleotide exchange factor (GEF). The variants were selected by bacterial two-hybrid strategy.",
        "method_text": "The RAS mutant library was generated by oligonucleotide-directed mutagenesis on the oncogenic G12V background. The mutant library was transfected into bacteria without GAP or GEF expression and the functioning RAS protein which will bind to GTP as well as Raf. The binding of these molecules can trigger the transcription of an antibiotic resistant factor. The library was separated to three sub-libraries in order to cover the whole RAS gene length which ranges from the residue 2-56, 57-111, and 112-166. These samples were selected individually. The samples in different sub-libraries were barcoded and pooled together for MiSeq sequencing.",
        "short_description": "Selection on the oncogenic G12V mutated type of Ras",
        "title": "G12V mutated Ras",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "28686159",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/28686159",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000057-d-1"
        ],
        "experimentset": "urn:mavedb:00000057"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-b",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 4h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 4h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-b-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2019-02-19",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000031-a",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of TERT promoter in HEK293T cells.",
        "title": "Saturation mutagenesis MPRA of TERT promoter, HEK",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            },
            {
                "text": "TERT"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444734",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444734",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000031-a-1"
        ],
        "experimentset": "urn:mavedb:00000031"
    },
    {
        "creation_date": "2019-02-20",
        "modification_date": "2019-11-21",
        "urn": "urn:mavedb:00000031-c",
        "publish_date": "2019-02-20",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0002-2032-6679",
        "extra_metadata": {},
        "abstract_text": "This study performed saturation mutagenesis on disease-associated enhancer and promoter regions and measured the effect of each mutation using massively parallel reporter assays (MPRA). The data describe potentially pathogenic mutations as well as the density of putative functional bases in each of the regulatory elements.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "method_text": "Sequences containing mutations were generated using error-prone PCR. Each library contained 50,000-2,000,000 constructs per target, which included nearly all possible single nucleotide changes as well as many single base pair deletions. Variants were tagged with 15 or 20 base pair barcodes 3' of the target region. Promoters were inserted into pGL4.11 vectors and enhancers were inserted into pGL4.23 enhancers such that they would drive expression of the luciferase reporter gene. RNA barcodes were counted using targeted RT-PCR and Illumina sequencing, and DNA barcodes were counted using targeted PCR and Illumina sequencing. Long variant sequences were associate with barcodes using subassembly.\r\n\r\nAs described by <https://www.biorxiv.org/content/10.1101/505362v1>",
        "short_description": "Saturation mutagenesis MPRA of TERT promoter in glioblastoma SF7996 (GBM) cells, siRNA knockdown of GABPA.",
        "title": "Saturation mutagenesis MPRA of TERT promoter, GBM siRNA knockdown",
        "keywords": [
            {
                "text": "barcode sequencing"
            },
            {
                "text": "MPRA"
            },
            {
                "text": "promoter"
            },
            {
                "text": "TERT"
            }
        ],
        "sra_ids": [
            {
                "identifier": "SRX5444734",
                "url": "http://www.ebi.ac.uk/ena/data/view/SRX5444734",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [
            {
                "identifier": "10.1038/s41467-019-11526-w",
                "url": "https://doi.org/10.1038/s41467-019-11526-w",
                "dbversion": null,
                "dbname": "DOI"
            },
            {
                "identifier": "10.17605/OSF.IO/75B2M",
                "url": "https://doi.org/10.17605/OSF.IO/75B2M",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31395865",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31395865",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0002-2032-6679"
        ],
        "scoresets": [
            "urn:mavedb:00000031-c-1"
        ],
        "experimentset": "urn:mavedb:00000031"
    },
    {
        "creation_date": "2020-12-03",
        "modification_date": "2021-04-14",
        "urn": "urn:mavedb:00000061-g",
        "publish_date": "2021-04-14",
        "created_by": "0000-0003-2449-7034",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "The authors generated a library of RAF variant and use the PACS system to test KRAS4b/RAF protein-protein interaction (PPI). The experimental data revealed positions along the binding interface as well as which substitutions are tolerated at each position.",
        "method_text": "A library of RAF variants is generated by introducing mutations into the RAF gene using error prone PCR. The library was introduced into a PACS system. In this system, bacteriophages express mutated RAF proteins and bacteria express KRAS proteins. The KRAS and RAF proteins are engineered and will induce the production of gIII when they are binded which is essential for the replication of phages. The enrichment of RAF mutations are determined at 24h by Illumina sequencing.",
        "short_description": "Measuring the interaction of mutated RAF to RAS by a new phage-assisted continuous selection (PACS) system.",
        "title": "RAF variant selected after 24h",
        "keywords": [],
        "sra_ids": [],
        "doi_ids": [
            {
                "identifier": "10.1021/acschembio.9b00669",
                "url": "https://doi.org/10.1021/acschembio.9b00669",
                "dbversion": null,
                "dbname": "DOI"
            }
        ],
        "pubmed_ids": [
            {
                "identifier": "31808666",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/31808666",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X",
            "0000-0003-2449-7034"
        ],
        "scoresets": [
            "urn:mavedb:00000061-g-1"
        ],
        "experimentset": "urn:mavedb:00000061"
    },
    {
        "creation_date": "2019-02-14",
        "modification_date": "2019-08-09",
        "urn": "urn:mavedb:00000012-a",
        "publish_date": "2019-02-18",
        "created_by": "0000-0003-1474-605X",
        "modified_by": "0000-0003-1474-605X",
        "extra_metadata": {},
        "abstract_text": "This experiment demonstrated the programmed allelic series (PALS) method for site-directed mutagenesis using microarrays. The impact of nearly all singleton missense mutation in the Gal4 yeast transcription factor was measured in multiple selections.",
        "method_text": "Mutagenic PCR primers were synthesized on a DNA microarray and released into solution. These encoded all possible single amino acid changes in codons 2-65 of Gal4. Full length variants were tagged with random DNA barcodes. The relationship between barcode and variant was determined using synthetic long read subassembly sequencing.",
        "short_description": "Deep mutational scan of Gal4 DNA-binding domain using a yeast growth assay.",
        "title": "Deep mutational scan of Gal4 DNA-binding domain",
        "keywords": [
            {
                "text": "subassembly"
            },
            {
                "text": "barcode sequencing"
            },
            {
                "text": "DNA-binding"
            },
            {
                "text": "Yeast two-hybrid"
            }
        ],
        "sra_ids": [
            {
                "identifier": "PRJNA268398",
                "url": "http://www.ebi.ac.uk/ena/data/view/PRJNA268398",
                "dbversion": null,
                "dbname": "SRA"
            }
        ],
        "doi_ids": [],
        "pubmed_ids": [
            {
                "identifier": "25559584",
                "url": "http://www.ncbi.nlm.nih.gov/pubmed/25559584",
                "dbversion": null,
                "dbname": "PubMed"
            }
        ],
        "contributors": [
            "0000-0003-1474-605X"
        ],
        "scoresets": [
            "urn:mavedb:00000012-a-1",
            "urn:mavedb:00000012-a-2",
            "urn:mavedb:00000012-a-3",
            "urn:mavedb:00000012-a-4",
            "urn:mavedb:00000012-a-5",
            "urn:mavedb:00000012-a-6"
        ],
        "experimentset": "urn:mavedb:00000012"
    }
]