{ "_id": "6ad5dafd4a34890ab4938f56", "Package": "GenomeScaleEmbeddings", "Title": "Exploring Genome-Scale Embeddings in 'Parquet' Files", "Version": "0.0.0.9000", "Authors@R": "c(\nperson(given = \"Sounkou Mahamane\", family = \"Toure\", email = \"sounkoutoure@gmail.com\", role = c(\"aut\", \"cre\"))\n)", "Description": "Provides tools to explore genome-scale variant embeddings\nstored in 'Parquet' files, including data access, matrix\nconversion, principal component analysis, summaries, and\nvisualization. The datasets accompany Niu et al. (2025),\n\"Incorporating Large Language Model (LLM) Embeddings for\nVariation Across the Human Genome\"\n.", "License": "LGPL (>= 3)", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "Remotes": [ "HervePerdry/houba", "fbertran/bigPCAcpp" ], "Config/roxygen2/version": "8.0.0", "Config/pak/sysreqs": "xz-utils", "Repository": "https://sounkou-bioinfo.r-universe.dev", "Date/Publication": "2026-07-21 20:11:18 UTC", "RemoteUrl": "https://github.com/sounkou-bioinfo/GenomeScaleEmbeddings", "RemoteRef": "HEAD", "RemoteSha": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "NeedsCompilation": "no", "Packaged": { "Date": "2026-10-19 08:51:51 UTC", "User": "root" }, "Author": "Sounkou Mahamane Toure [aut, cre]", "Maintainer": "Sounkou Mahamane Toure ", "_user": "sounkou-bioinfo", "_type": "src", "_file": "GenomeScaleEmbeddings_0.0.0.9000.tar.gz", "_fileid": "https://r2.ropensci.org/cae57038217fe3a17278f273b78cd73b65a66c696b187f48b4efabdf507af24f", "_filesize": 981148, "_sha256": "cae57038217fe3a17278f273b78cd73b65a66c696b187f48b4efabdf507af24f", "_expires": "2027-01-27T08:55:23.000Z", "_created": "2026-10-19T08:51:51.000Z", "_published": "2026-10-19T08:55:24.963Z", "_buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 117971785254, "time": 113, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12173772710" }, { "job": 117971785007, "time": 115, "config": "linux-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12173059738" }, { "job": 117971785040, "time": 111, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "12173742813" }, { "job": 117971785081, "time": 81, "config": "macos-release-arm64", "r": "4.6.1", "check": "OK", "artifact": "12172864413" }, { "job": 117970130995, "time": 251, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12173054772" }, { "job": 117971784983, "time": 182, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12173881446" }, { "job": 117971785059, "time": 69, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "12174320562" }, { "job": 117971785197, "time": 62, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "OK", "artifact": "12173522445" }, { "job": 117971785053, "time": 76, "config": "windows-release-x86_64", "r": "4.6.1", "check": "OK", "artifact": "12173547195" } ], "_upstream": "https://github.com/sounkou-bioinfo/GenomeScaleEmbeddings", "_commit": { "id": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "author": "sounkou-bioinfo ", "committer": "sounkou-bioinfo ", "message": "Fix package check warnings and dependencies\n", "time": 1784664678 }, "_maintainer": { "name": "Sounkou Mahamane Toure", "email": "sounkoutoure@gmail.com", "login": "sounkou-bioinfo", "mastodon": "@bioinfhotep@genomic.social", "description": "Sequences and Consequences.", "uuid": 56392505 }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.4.0", "role": "Depends" }, { "package": "bigmemory", "role": "Imports" }, { "package": "bigPCAcpp", "role": "Imports" }, { "package": "DBI", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "duckdb", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "houba", "role": "Imports" }, { "package": "jsonlite", "role": "Imports" } ], "_owner": "sounkou-bioinfo", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-42", "n": 50 }, { "week": "2025-48", "n": 1 }, { "week": "2026-30", "n": 1 } ], "_tags": [], "_stars": 0, "_contributors": [ { "user": "sounkou-bioinfo", "count": 52, "uuid": 56392505 } ], "_userbio": { "uuid": 56392505, "type": "user", "name": "Sounkou Mahamane Toure", "followers": 59, "description": "Sequences and Consequences." }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/GenomeScaleEmbeddings" }, "_devurl": "https://github.com/sounkou-bioinfo/genomescaleembeddings", "_searchresults": 2, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/GenomeScaleEmbeddings.html", "extra/manual.pdf", "extra/readme.html", "extra/readme.md" ], "_cranurl": false, "_exports": [ "attachHoubaBigMatrix", "CopyParquetToDuckDB", "correlatePCWithPosition", "DatasetParquetUrlList", "embeddingSummary", "getPcaScores", "houbaPCA", "infoSummary", "IterateEmbeddingsMatrixBatches", "OpenRemoteParquetView", "plotPcaDims", "plotPCSpatialCorrelation", "writeEmbeddingsHoubaFromDuckDB" ], "_help": [ { "page": "attachHoubaBigMatrix", "title": "Attach a houba file and return the bigmemory::big.matrix", "topics": [ "attachHoubaBigMatrix" ] }, { "page": "CopyParquetToDuckDB", "title": "Copy remote parquet files into a local DuckDB database file", "topics": [ "CopyParquetToDuckDB" ] }, { "page": "correlatePCWithPosition", "title": "Compute correlation between PC scores and genomic position, per chromosome", "topics": [ "correlatePCWithPosition" ] }, { "page": "DatasetParquetUrlList", "title": "List of the huggingface datasets for the paper \"Incorporating LLM Embeddings for Variation Across the Human Genome\"", "topics": [ "DatasetParquetUrlList" ] }, { "page": "embeddingSummary", "title": "Quick summary for houba mmatrix", "topics": [ "embeddingSummary" ] }, { "page": "getPcaScores", "title": "Get PCA scores from houbaPCA result", "topics": [ "getPcaScores" ] }, { "page": "houbaPCA", "title": "PCA using bigPCAcpp on houba mmatrix or bigmemory::big.matrix", "topics": [ "houbaPCA" ] }, { "page": "infoSummary", "title": "Quick summary for houba info mmatrix", "topics": [ "infoSummary" ] }, { "page": "IterateEmbeddingsMatrixBatches", "title": "Iterate over embeddings as matrix batches from a local DuckDB file", "topics": [ "IterateEmbeddingsMatrixBatches" ] }, { "page": "OpenRemoteParquetView", "title": "Open remote parquet files as a DuckDB VIEW and return as tibble (minimal, http(s) only)", "topics": [ "OpenRemoteParquetView" ] }, { "page": "plotPcaDims", "title": "Plot PCA dimensions using ggplot2, colored by annotation", "topics": [ "plotPcaDims" ] }, { "page": "plotPCSpatialCorrelation", "title": "Plot spatial correlation between PC scores and genomic position, faceted by chromosome", "topics": [ "plotPCSpatialCorrelation" ] }, { "page": "print.HoubaEmbeddings", "title": "Print a Houba embeddings object", "topics": [ "print.HoubaEmbeddings" ] }, { "page": "writeEmbeddingsHoubaFromDuckDB", "title": "Write embeddings to houba mmatrix and return info as data.frame from a local DuckDB file", "topics": [ "writeEmbeddingsHoubaFromDuckDB" ] } ], "_readme": "https://github.com/sounkou-bioinfo/GenomeScaleEmbeddings/raw/HEAD/README.md", "_rundeps": [ "BH", "bigmemory", "bigmemory.sri", "bigPCAcpp", "cli", "cpp11", "DBI", "dplyr", "duckdb", "farver", "generics", "ggplot2", "glue", "gtable", "houba", "isoband", "jsonlite", "labeling", "lifecycle", "magrittr", "pillar", "pkgconfig", "R6", "RColorBrewer", "Rcpp", "rlang", "S7", "scales", "tibble", "tidyselect", "utf8", "uuid", "vctrs", "viridisLite", "withr" ], "_score": 2.1760912590556813, "_indexed": true, "_nocasepkg": "genomescaleembeddings", "_universes": [ "sounkou-bioinfo" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.0.0.9000", "date": "2026-10-19T08:53:51.000Z", "distro": "resolute", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/b45481e3012fbbe44193f7ee20581b2ecfc51a9b2098e359722c3438dd0cb204", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.6.1", "os": "linux", "version": "0.0.0.9000", "date": "2026-10-19T08:53:52.000Z", "distro": "resolute", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/f1fb6fe4f84167412f66f39f05825ad024a0778f05736939ba204708319bd503", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.5.3", "os": "mac", "version": "0.0.0.9000", "date": "2026-10-19T08:53:52.000Z", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/bf88bb709d676c832da949d404542426a42d367670f086566ec4801146782ac0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.6.1", "os": "mac", "version": "0.0.0.9000", "date": "2026-10-19T08:53:25.000Z", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/6fd23e84a454e5c19f9ec95ef28dc515e8c840c9720a72159ee0e363bdf0f242", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.6.0", "os": "wasm", "version": "0.0.0.9000", "date": "2026-10-19T08:55:07.000Z", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/4d6a8a91f6b718f2f1485cef2549ee0c06d386493e08c5397215aafe76c40bf2", "status": "success", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.7.0", "os": "win", "version": "0.0.0.9000", "date": "2026-10-19T08:53:04.000Z", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/ee6e63336aa9d4173e054fb5d7f19c7f3ca1a151f5cded43637bb37454fb6475", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.5.3", "os": "win", "version": "0.0.0.9000", "date": "2026-10-19T08:52:58.000Z", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/503f3369d06d457630e565b8f4b9886e43d63b266ecc1c929fb69e49b7b15d1e", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" }, { "r": "4.6.1", "os": "win", "version": "0.0.0.9000", "date": "2026-10-19T08:53:10.000Z", "commit": "c5b01269e2ad03da66d450bda8e3aa077e1912fa", "fileid": "https://r2.ropensci.org/d6ad2b7cae45f05ea73b71108f804e44e6d9aeed255019f38f4c91fd9f7b5ed7", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/sounkou-bioinfo/actions/runs/39225298649" } ] }