{ "_id": "6aca1aa3fe5cc25786e84b31", "Package": "ProteinGymR", "Title": "Programmatic access to ProteinGym datasets in R/Bioconductor", "Version": "1.7.0", "Authors@R": "c(person(\"Tram\", \"Nguyen\",\nrole = c(\"aut\", \"cre\"),\nemail = \"tram22.nguyen@gmail.com\",\ncomment = c(ORCID = \"0000-0003-4809-6227\")),\nperson(\"Pascal\", \"Notin\",\nrole = \"aut\"),\nperson(\"Aaron\", \"Kollasch\",\nrole = \"aut\"),\nperson(\"Debora\", \"Marks\",\nrole = \"aut\"),\nperson(\"Ludwig\", \"Geistlinger\",\nrole = \"aut\"))", "Description": "The ProteinGymR package provides analysis-ready data\nresources from ProteinGym, generated by Notin et al., 2023, as\nwell as built-in functionality to visualize the data.\nProteinGym comprises a collection of benchmarks for evaluating\nthe performance of models predicting the effect of point\nmutations. This package provides access to 1. deep mutational\nscanning (DMS) scores from 217 assays measuring the impact of\nall possible amino acid substitutions across 186 proteins, 2.\nmodel performance metrics and prediction scores from 79 variant\nprediction models in the zero-shot setting and 12 models in the\nsemi-supervised setting.", "License": "Artistic-2.0", "URL": "https://github.com/ccb-hms/ProteinGymR", "BugReports": "https://github.com/ccb-hms/ProteinGymR/issues", "VignetteBuilder": "knitr", "Encoding": "UTF-8", "biocViews": "ExperimentData, ExperimentHub, PackageTypeData,\nHomo_sapiens_Data, ReproducibleResearch, CellCulture,\nSequencingData, Proteome", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "Config/testthat/edition": "3", "Config/pak/sysreqs": "libicu-dev libpng-dev libssl-dev zlib1g-dev", "Repository": "https://bioc.r-universe.dev", "Date/Publication": "2026-04-28 12:37:44 UTC", "RemoteUrl": "https://github.com/bioc/ProteinGymR", "RemoteRef": "HEAD", "RemoteSha": "c3b8833ed0775ea2f82d2898d980c11561a1b21c", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-10 10:47:50 UTC", "User": "root" }, "Author": "Tram Nguyen [aut, cre] (ORCID: ),\nPascal Notin [aut],\nAaron Kollasch [aut],\nDebora Marks [aut],\nLudwig Geistlinger [aut]", "Maintainer": "Tram Nguyen ", "_user": "bioc", "_type": "src", "_file": "ProteinGymR_1.7.0.tar.gz", "_fileid": "https://r2.ropensci.org/f21ca23789af9d9994d66737ab6379f8b73f12dd96455a61d2747b26d3fb826d", "_filesize": 1515517, "_sha256": "f21ca23789af9d9994d66737ab6379f8b73f12dd96455a61d2747b26d3fb826d", "_expires": "2027-01-18T10:59:41.000Z", "_created": "2026-10-10T10:47:50.000Z", "_published": "2026-10-10T10:59:47.417Z", "_buildurl": "https://github.com/r-universe/bioc/actions/runs/38045793240", "_status": "success", "_host": "GitHub-Actions", "_bioccheck": { "error": 0, "warning": 1, "note": 9 }, "_upstream": "https://github.com/bioc/ProteinGymR", "_commit": { "id": "c3b8833ed0775ea2f82d2898d980c11561a1b21c", "author": "lshep ", "committer": "lshep ", "message": "bump x.y.z version to odd y following creation of RELEASE_3_23 branch\n", "time": 1777379864 }, "_maintainer": { "name": "Tram Nguyen", "email": "tram22.nguyen@gmail.com", "login": "tram-nguyen-n", "orcid": "0000-0003-4809-6227", "description": "Data Scientist, Computational Biologist at Tempus AI", "uuid": 150388074 }, "_distro": "resolute", "_jobs": [ { "job": 114196088430, "time": 181, "config": "bioc-checks", "r": "4.6.1", "check": "WARNING", "artifact": "11666704108" }, { "job": 114196088429, "time": 656, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "NOTE", "artifact": "11667945850" }, { "job": 114196088397, "time": 617, "config": "linux-release-x86_64", "r": "4.6.1", "check": "NOTE", "artifact": "11668040615" }, { "job": 114194991483, "time": 377, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "11666843841" } ], "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.4.0", "role": "Depends" }, { "package": "ExperimentHub", "role": "Imports" }, { "package": "AnnotationHub", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "queryup", "role": "Imports" }, { "package": "spdl", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "tidyselect", "role": "Imports" }, { "package": "stringr", "role": "Imports" }, { "package": "lifecycle", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "htmltools", "role": "Imports" }, { "package": "tibble", "role": "Suggests" }, { "package": "BiocStyle", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "ComplexHeatmap", "role": "Suggests" }, { "package": "circlize", "role": "Suggests" }, { "package": "pals", "role": "Suggests" }, { "package": "ggplot2", "version": ">= 3.5.0", "role": "Suggests" }, { "package": "grDevices", "role": "Suggests" }, { "package": "ggExtra", "role": "Suggests" }, { "package": "bio3d", "role": "Suggests" }, { "package": "r3dmol", "role": "Suggests" }, { "package": "forcats", "role": "Suggests" }, { "package": "ggdist", "version": ">= 3.3.0", "role": "Suggests" } ], "_owner": "bioc", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-41", "n": 3 }, { "week": "2026-15", "n": 3 }, { "week": "2026-18", "n": 2 } ], "_tags": [], "_bioc": [ { "branch": "devel", "version": "1.7.0", "bioc": "3.24", "repository": "data/experiment" }, { "branch": "release", "version": "1.6.0", "bioc": "3.23", "repository": "data/experiment" } ], "_topics": [ "experimentdata", "experimenthub", "packagetypedata", "homo_sapiens_data", "reproducibleresearch", "cellculture", "sequencingdata", "proteome", "datapkg" ], "_stars": 0, "_contributors": [ { "user": "tram-nguyen-n", "count": 308, "uuid": 150388074 }, { "user": "lshep", "count": 6, "uuid": 18724380 }, { "user": "lgeistlinger", "count": 1, "uuid": 11871050 } ], "_userbio": { "uuid": 2286807, "type": "organization", "name": "Bioconductor", "followers": 476, "description": "Software for the analysis and comprehension of high-throughput genomic data" }, "_devurl": "https://github.com/ccb-hms/proteingymr", "_searchresults": 5, "_datapkg": true, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/ProteinGymR.html", "extra/readme.html", "extra/readme.md" ], "_cranurl": false, "_exports": [ "am_scores", "available_models", "benchmark_models", "dms_corr_plot", "dms_substitutions", "model_corr_plot", "plot_dms_heatmap", "plot_structure", "plot_zeroshot_heatmap", "supervised_available_models", "supervised_metrics", "supervised_substitutions", "zeroshot_DMS_metrics", "zeroshot_substitutions" ], "_help": [ { "page": "am_scores", "title": "AlphaMissense scores for ProteinGym variants", "topics": [ "am_scores" ] }, { "page": "benchmark_models", "title": "Benchmark Variant Effect Prediction Models", "topics": [ "available_models", "benchmark_models", "supervised_available_models" ] }, { "page": "dms_corr_plot", "title": "Integrate ProteinGym DMS and Model Prediction Scores", "topics": [ "dms_corr_plot" ] }, { "page": "ProteinGym_DMS", "title": "ProteinGym Deep Mutational Scanning (DMS) Scores for Substitutions", "topics": [ "dms_substitutions" ] }, { "page": "model_corr_plot", "title": "Compare Prediction Scores for ProteinGym Models", "topics": [ "model_corr_plot" ] }, { "page": "plot_dms_heatmap", "title": "Visualize DMS Scores Along a Protein", "topics": [ "plot_dms_heatmap" ] }, { "page": "plot_structure", "title": "Visualize DMS and Model Scores on 3D Protein Structures", "topics": [ "plot_structure" ] }, { "page": "plot_zeroshot_heatmap", "title": "Visualize Zero Shot Scores Along a Protein", "topics": [ "plot_zeroshot_heatmap" ] }, { "page": "supervised_scores", "title": "Load Semi-Supervised Model Predictions for Substitutions in 217 Assays", "topics": [ "supervised_metrics", "supervised_substitutions" ] }, { "page": "zeroshot_scores", "title": "Load Zero-shot Model Predictions and Metrics for Substitutions in 217 DMS Assays", "topics": [ "zeroshot_DMS_metrics", "zeroshot_substitutions" ] } ], "_readme": "https://github.com/bioc/ProteinGymR/raw/HEAD/README.md", "_rundeps": [ "AnnotationDbi", "AnnotationHub", "askpass", "base64enc", "Biobase", "BiocBaseUtils", "BiocFileCache", "BiocGenerics", "BiocManager", "BiocVersion", "Biostrings", "bit", "bit64", "blob", "cachem", "cli", "cpp11", "crayon", "curl", "DBI", "dbplyr", "digest", "dplyr", "ExperimentHub", "fastmap", "filelock", "generics", "glue", "htmltools", "httr", "httr2", "IRanges", "jsonlite", "KEGGREST", "lifecycle", "magrittr", "memoise", "mime", "openssl", "pillar", "pkgconfig", "png", "purrr", "queryup", "R6", "rappdirs", "Rcpp", "RcppSpdlog", "rlang", "RSQLite", "S4Vectors", "Seqinfo", "spdl", "stringi", "stringr", "sys", "tibble", "tidyr", "tidyselect", "utf8", "vctrs", "withr", "XVector", "yaml" ], "_vignettes": [ { "source": "data_import_and_representation.Rmd", "filename": "data_import_and_representation.html", "title": "Import and representation of ProteinGym data", "author": "Tram Nguyen, Pascal Notin, Aaron W Kollasch, Debora Marks, Ludwig Geistlinger", "engine": "knitr::rmarkdown", "headings": [ "Installation", "Setup", "Introduction", "Available datasets", "Data import", "DMS data", "Model benchmarking", "Session Info", "References" ], "created": "2024-08-14 17:02:11", "modified": "2025-06-18 15:49:19", "commits": 24 }, { "source": "visualization_exploration.Rmd", "filename": "visualization_exploration.html", "title": "Visualization and exploration", "author": "Tram Nguyen, Pascal Notin, Aaron W Kollasch, Debora Marks, Ludwig Geistlinger", "engine": "knitr::rmarkdown", "headings": [ "Setup", "Introduction", "Visualize DMS scores along a protein sequence", "Visualize model scores along a protein", "3D protein structure", "Correlate DMS scores with model scores", "Correlate prediction scores between two models.", "Session Info", "References" ], "created": "2025-03-13 18:22:41", "modified": "2025-07-17 13:31:20", "commits": 20 } ], "_score": 4.778151250383644, "_indexed": true, "_nocasepkg": "proteingymr", "_universes": [ "bioc", "tram-nguyen-n", "ccb-hms" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "1.7.0", "date": "2026-10-10T10:52:02.000Z", "distro": "resolute", "commit": "c3b8833ed0775ea2f82d2898d980c11561a1b21c", "fileid": "https://r2.ropensci.org/5e2a8c3c8f259aaa803930d0ff2b456606de9718f2d88e27cd80053cb19ad41d", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/bioc/actions/runs/38045793240" }, { "r": "4.6.1", "os": "linux", "version": "1.7.0", "date": "2026-10-10T10:51:25.000Z", "distro": "resolute", "commit": "c3b8833ed0775ea2f82d2898d980c11561a1b21c", "fileid": "https://r2.ropensci.org/a3b5a7b0943b590f16219a6343e947d73ab38d0e17d442a933ece269fad605ae", "status": "success", "check": "NOTE", "buildurl": "https://github.com/r-universe/bioc/actions/runs/38045793240" } ] }