{ "_id": "6a1e84e41d7bb097a0a66cfe", "Package": "ulrb", "Type": "Package", "Title": "Unsupervised Learning Based Definition of Microbial Rare\nBiosphere", "Version": "0.1.8", "Authors@R": "c(\nperson(\"Francisco\", \"Pascoal\",,\"fpascoal1996@gmail.com\", role = c(\"aut\",\"cre\"), comment = c(ORCID = \"0000-0003-2315-358X\")),\nperson(\"Paula\", \"Branco\",,\"paobranco@gmail.com\", role = c(\"aut\"), comment = c(ORCID = \"0000-0002-9917-3694\")),\nperson(\"Luís\", \"Torgo\",,\"ltorgo@dal.ca\", role = c(\"aut\"), comment = c(ORCID = \"0000-0002-6892-8871\")),\nperson(\"Rodrigo\", \"Costa\",,\"rodrigoscosta@tecnico.ulisboa.pt\", role = c(\"aut\"), comment = c(ORCID = \"0000-0002-5932-4101\")),\nperson(\"Catarina\", \"Magalhães\",,\"catarinamagalhaes1972@gmail.com\", role = c(\"aut\"), comment = c(ORCID = \"0000-0001-9576-2398\")))", "Maintainer": "Francisco Pascoal ", "Date": "2025-07-07", "Description": "A tool to define the rare biosphere. 'ulrb' solves the\nproblem of the definition of rarity by replacing arbitrary\nthresholds with an unsupervised machine learning algorithm\n(partitioning around medoids, or k-medoids). This algorithm\nworks for any type of microbiome data, provided there is an\nabundance table. This method also works for non-microbiome\ndata.", "License": "GPL (>= 3)", "Encoding": "UTF-8", "LazyData": "true", "Config/testthat/edition": "3", "RoxygenNote": "7.3.1", "VignetteBuilder": "knitr", "Roxygen": "list(markdown = TRUE)", "URL": "https://pascoalf.github.io/ulrb/", "BugReports": "https://github.com/pascoalf/ulrb/issues", "Config/pak/sysreqs": "libicu-dev", "Repository": "https://pascoalf.r-universe.dev", "Date/Publication": "2025-07-07 08:03:29 UTC", "RemoteUrl": "https://github.com/pascoalf/ulrb", "RemoteRef": "HEAD", "RemoteSha": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-02 07:18:49 UTC", "User": "root" }, "Author": "Francisco Pascoal [aut, cre] (ORCID:\n),\nPaula Branco [aut] (ORCID: ),\nLuís Torgo [aut] (ORCID: ),\nRodrigo Costa [aut] (ORCID: ),\nCatarina Magalhães [aut] (ORCID:\n)", "MD5sum": "bea16c0f4f3bd37c07993410fab4b453", "_user": "pascoalf", "_type": "src", "_file": "ulrb_0.1.8.tar.gz", "_fileid": "09c004b94763a8b61a1fde66a8a8d5950ee965479375177c3a76c9d0b215e091", "_filesize": 3898044, "_sha256": "09c004b94763a8b61a1fde66a8a8d5950ee965479375177c3a76c9d0b215e091", "_created": "2026-06-02T07:18:49.000Z", "_published": "2026-06-02T07:23:16.015Z", "_distro": "noble", "_jobs": [ { "job": 79019356924, "time": 210, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7351398475" }, { "job": 79019356932, "time": 217, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7351400448" }, { "job": 79019356869, "time": 221, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7351390312" }, { "job": 79019356913, "time": 173, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7351380773" }, { "job": 79018677082, "time": 287, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7351333796" }, { "job": 79019356944, "time": 118, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7351371623" }, { "job": 79019356873, "time": 161, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7351384034" }, { "job": 79019356882, "time": 183, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7351390655" }, { "job": 79019356911, "time": 155, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7351382645" } ], "_buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/pascoalf/ulrb", "_commit": { "id": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "author": "pascoalf ", "committer": "pascoalf ", "message": "Fix url\n", "time": 1751875409 }, "_maintainer": { "name": "Francisco Pascoal", "email": "fpascoal1996@gmail.com", "login": "pascoalf", "orcid": "0000-0003-2315-358X", "description": "I am a researcher at CIIMAR. My research applies data science to study microbial ecology.", "uuid": 88724962 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 2.10", "role": "Depends" }, { "package": "cluster", "role": "Imports" }, { "package": "dplyr", "role": "Imports" }, { "package": "ggplot2", "role": "Imports" }, { "package": "purrr", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "tidyr", "role": "Imports" }, { "package": "clusterSim", "role": "Imports" }, { "package": "gridExtra", "role": "Imports" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "stringr", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "vegan", "role": "Suggests" } ], "_owner": "pascoalf", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2025-28", "n": 4 } ], "_tags": [], "_stars": 6, "_contributors": [ { "user": "pascoalf", "count": 331, "uuid": 88724962 }, { "user": "slager", "count": 1, "uuid": 9014864 }, { "user": "teunbrand", "count": 1, "uuid": 49372158 } ], "_userbio": { "uuid": 88724962, "type": "user", "name": "Francisco Pascoal", "description": "I am a researcher at CIIMAR. My research applies data science to study microbial ecology." }, "_downloads": { "count": 201, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/ulrb" }, "_devurl": "https://github.com/pascoalf/ulrb", "_pkgdown": "https://pascoalf.github.io/ulrb/", "_searchresults": 14, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/readme.html", "extra/readme.md", "extra/ulrb.html", "manual.pdf" ], "_homeurl": "https://github.com/pascoalf/ulrb", "_realowner": "pascoalf", "_cranurl": true, "_releases": [ { "version": "0.1.3", "date": "2023-11-17" }, { "version": "0.1.5", "date": "2024-06-18" }, { "version": "0.1.6", "date": "2025-04-07" }, { "version": "0.1.8", "date": "2025-07-07" } ], "_exports": [ "check_avgSil", "check_CH", "check_DB", "define_rb", "evaluate_k", "evaluate_sample_k", "plot_ulrb", "plot_ulrb_clustering", "plot_ulrb_silhouette", "prepare_tidy_data", "suggest_k" ], "_datasets": [ { "name": "nice", "title": "V4-V5 16S rRNA gene amplicons, clean OTU table (N-ICE, 2015)", "object": "nice", "class": [ "data.frame" ], "fields": [ "ERR2044662", "ERR2044663", "ERR2044664", "ERR2044665", "ERR2044666", "ERR2044667", "ERR2044668", "ERR2044669", "ERR2044670", "OTU", "Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species" ], "rows": 524, "table": true, "tojson": true }, { "name": "nice_env", "title": "Metadata of samples from OTU tables (N-ICE, 2015)", "object": "nice_env", "class": [ "data.frame" ], "fields": [ "Sample", "Month", "Depth", "Region", "Water.mass", "Latitude", "Longitude", "ENA_ID" ], "rows": 9, "table": true, "tojson": true }, { "name": "nice_raw", "title": "V4-V5 16S rRNA gene amplicons, raw OTU table (N-ICE, 2015)", "object": "nice_raw", "class": [ "data.frame" ], "fields": [ "X.SampleID", "ERR2044670", "ERR2044671", "ERR2044662", "ERR2044672", "ERR2044663", "ERR2044673", "ERR2044664", "ERR2044674", "ERR2044665", "ERR2044675", "ERR2044666", "ERR2044676", "ERR2044667", "ERR2044677", "ERR2044668", "ERR2044678", "ERR2044669", "ERR2044679" ], "rows": 1003, "table": true, "tojson": true }, { "name": "nice_tidy", "title": "V4-V5 16S rRNA gene amplicons, clean OTU table in tidy/long format (N-ICE, 2015)", "object": "nice_tidy", "class": [ "tbl_df", "tbl", "data.frame" ], "fields": [ "OTU", "Domain", "Phylum", "Class", "Order", "Family", "Genus", "Species", "Sample", "Abundance" ], "rows": 4716, "table": true, "tojson": true } ], "_help": [ { "page": "ulrb-package", "title": "ulrb: Unsupervised Learning Based Definition of Microbial Rare Biosphere", "topics": [ "ulrb-package" ] }, { "page": "check_avgSil", "title": "Check average Silhouette score index", "topics": [ "check_avgSil" ] }, { "page": "check_CH", "title": "Check Calinski-Harabasz index", "topics": [ "check_CH" ] }, { "page": "check_DB", "title": "Check Davies-Bouldin Index", "topics": [ "check_DB" ] }, { "page": "define_rb", "title": "Define Rare Biosphere", "topics": [ "define_rb" ] }, { "page": "evaluate_k", "title": "Evaluate k from all samples in a dataset", "topics": [ "evaluate_k" ] }, { "page": "evaluate_sample_k", "title": "Evaluate sample k", "topics": [ "evaluate_sample_k" ] }, { "page": "nice", "title": "V4-V5 16S rRNA gene amplicons, clean OTU table (N-ICE, 2015)", "topics": [ "nice" ] }, { "page": "nice_env", "title": "Metadata of samples from OTU tables (N-ICE, 2015)", "topics": [ "nice_env" ] }, { "page": "nice_raw", "title": "V4-V5 16S rRNA gene amplicons, raw OTU table (N-ICE, 2015)", "topics": [ "nice_raw" ] }, { "page": "nice_tidy", "title": "V4-V5 16S rRNA gene amplicons, clean OTU table in tidy/long format (N-ICE, 2015)", "topics": [ "nice_tidy" ] }, { "page": "plot_ulrb", "title": "Plot ulrb clustering results and silhouette scores", "topics": [ "plot_ulrb" ] }, { "page": "plot_ulrb_clustering", "title": "Plot Rank Abundance Curve of classification results", "topics": [ "plot_ulrb_clustering" ] }, { "page": "plot_ulrb_silhouette", "title": "Plot silhouette scores from clustering results", "topics": [ "plot_ulrb_silhouette" ] }, { "page": "prepare_tidy_data", "title": "Prepare data in tidy format", "topics": [ "prepare_tidy_data" ] }, { "page": "suggest_k", "title": "Suggest k", "topics": [ "suggest_k" ] } ], "_pkglogo": "https://github.com/pascoalf/ulrb/raw/HEAD/man/figures/logo.png", "_readme": "https://github.com/pascoalf/ulrb/raw/HEAD/README.md", "_rundeps": [ "ade4", "class", "cli", "cluster", "clusterSim", "cpp11", "dplyr", "e1071", "farver", "generics", "ggplot2", "glue", "gridExtra", "gtable", "isoband", "labeling", "lattice", "lifecycle", "magrittr", "MASS", "pillar", "pixmap", "pkgconfig", "proxy", "purrr", "R6", "RColorBrewer", "Rcpp", "RcppArmadillo", "rlang", "S7", "scales", "sp", "stringi", "stringr", "tibble", "tidyr", "tidyselect", "utf8", "vctrs", "viridisLite", "withr" ], "_vignettes": [ { "source": "explore-classifications.Rmd", "filename": "explore-classifications.html", "title": "Alternative classifications with ulrb", "engine": "knitr::rmarkdown", "headings": [ "Explore alternative classifications", "Index", "Classical example", "Prepare data", "Default is k = 3", "Apply 2 classifications: Rare vs Abundant", "Apply more complicated classification, k>3", "Why k = 1 is non-sense", "What is the maximum value of k and why?", "Approaches to evaluate k", "Fine grained analysis", "Automatic k selection", "Everything automatic", "How each index behaves across all possible values of k?", "References" ], "created": "2023-06-06 09:48:40", "modified": "2025-05-14 17:46:58", "commits": 10 }, { "source": "Glossary.Rmd", "filename": "Glossary.html", "title": "Glossary", "engine": "knitr::rmarkdown", "headings": [ "Why we made this tutorial", "Phylogenetic units", "Phylogenetic units translated to machine learning", "Variables and features", "Abundance classification", "Summary" ], "created": "2023-09-15 13:49:24", "modified": "2023-11-01 15:02:53", "commits": 2 }, { "source": "eco-analysis.Rmd", "filename": "eco-analysis.html", "title": "Integration of ulrb in a simple microbial ecology workflow", "engine": "knitr::rmarkdown", "headings": [ "Ecological analysis of microbial rare biosphere defined by ulrb", "Quick overview of N-ICE dataset", "(a) Load and clean OTU table", "(b) Rarefy samples", "(b) Classify OTUs into rare, undetermined or abundant (with define_rb() function);", "(c) Merge OTU table with metadata information", "(e) Calculate and plot diversity metrics against environmental variables.", "Alpha diversity plots", "Beta diversity", "Final considerations", "References" ], "created": "2023-04-12 10:10:40", "modified": "2025-07-07 07:10:30", "commits": 11 }, { "source": "ulrb-vignet.Rmd", "filename": "ulrb-vignet.html", "title": "Tutorial to define rare biosphere with ulrb", "engine": "knitr::rmarkdown", "headings": [ "Unsupervised Learning Based Definition Of Microbial Rare Biosphere", "Brief note on nomenclature", "Pre-processing of data prior to clustering algorithm", "Load and clean abundance table", "Transform abundance table into tidy/long format", "Apply definition of rare biosphere with unsupervised learning", "Fully automated version", "Verify results", "(1) Rank Abunddance Curve (RAC) to verify clustering", "(2) Silhouette plots", "Sanity check summary", "References" ], "created": "2023-01-10 11:02:54", "modified": "2025-05-14 17:46:58", "commits": 21 } ], "_score": 5.5263392773898445, "_indexed": true, "_nocasepkg": "ulrb", "_universes": [ "pascoalf" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.8", "date": "2026-06-02T07:21:16.000Z", "distro": "noble", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "8bf15327fa9d85b51cf825455e1bee9f4b5950a0c94ac0715581975ee37bb5ce", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.6.0", "os": "linux", "version": "0.1.8", "date": "2026-06-02T07:21:20.000Z", "distro": "noble", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "23b90dc2b848ef3573d787192a64c04e0a1458d2ffbb07714853b208403c1c8c", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.5.3", "os": "mac", "version": "0.1.8", "date": "2026-06-02T07:21:09.000Z", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "582dd551f7ba779150bd1917f02ace7263fe1236cf1c47b300dbf8e4212ab075", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.6.0", "os": "mac", "version": "0.1.8", "date": "2026-06-02T07:20:47.000Z", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "090e6f89ca853a241e452bc4ebedf0006c6135deaa634607eac3df7c2fcaceb0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.8", "date": "2026-06-02T07:21:11.000Z", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "3e56c947140c7f385a67d148aa5f1430ae315abb4a8dad3e915d992e570b7e6c", "status": "success", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.7.0", "os": "win", "version": "0.1.8", "date": "2026-06-02T07:20:15.000Z", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "be6a1e52ab12ea7908a30a0830c71d2685c4561fbb6bf0c0a57afbf64f0d11bc", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.5.3", "os": "win", "version": "0.1.8", "date": "2026-06-02T07:20:37.000Z", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "e415ac384f089872e7b30c3fcdd56c3ef0c777381a3afa5e36f2320cdfbc43c5", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" }, { "r": "4.6.0", "os": "win", "version": "0.1.8", "date": "2026-06-02T07:20:20.000Z", "commit": "e8271ff0b9dd1240b98268323bca3ab4ccc79d7d", "fileid": "246bc6e4da44b99fd1084c3ad3029fcd84bce538100c3e1f3079a0020e282538", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/pascoalf/actions/runs/26804516086" } ] }