{ "_id": "6ad4a8c07774b2311ffead4d", "Package": "splitGraph", "Title": "Dataset Dependency Graphs for Leakage-Aware Evaluation", "Version": "0.4.0", "Authors@R": "c(\nperson(\"Selcuk\", \"Korkmaz\", role = c(\"aut\",\"cre\"), email = \"selcukorkmaz@gmail.com\",\ncomment = c(ORCID = \"0000-0003-4632-6850\"))\n)", "Description": "Represent biomedical dataset structure as typed dependency\ngraphs so that sample provenance, repeated-measure structure,\nstudy design, batch effects, and temporal relationships are\nexplicit and inspectable. Validates dataset structure, detects\nsample-level overlap, derives deterministic split constraints,\nand produces a tool-agnostic split specification for\nleakage-aware evaluation workflows.", "License": "MIT + file LICENSE", "URL": "https://github.com/selcukorkmaz/splitGraph", "BugReports": "https://github.com/selcukorkmaz/splitGraph/issues", "Encoding": "UTF-8", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/Needs/website": "selcukorkmaz/leakdown", "NeedsCompilation": "no", "RoxygenNote": "7.3.3", "Config/pak/sysreqs": "libglpk-dev libxml2-dev", "Repository": "https://selcukorkmaz.r-universe.dev", "Date/Publication": "2026-09-18 07:23:42 UTC", "RemoteUrl": "https://github.com/selcukorkmaz/splitgraph", "RemoteRef": "HEAD", "RemoteSha": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "Packaged": { "Date": "2026-10-18 11:04:36 UTC", "User": "root" }, "Author": "Selcuk Korkmaz [aut, cre] (ORCID:\n)", "Maintainer": "Selcuk Korkmaz ", "_user": "selcukorkmaz", "_type": "src", "_file": "splitGraph_0.4.0.tar.gz", "_fileid": "https://r2.ropensci.org/7abb5eb5f596fac5ccf123e6dfff4b99a980c95578afebe725801f480513c588", "_filesize": 1127647, "_sha256": "7abb5eb5f596fac5ccf123e6dfff4b99a980c95578afebe725801f480513c588", "_expires": "2027-01-26T11:08:46.000Z", "_created": "2026-10-18T11:04:36.000Z", "_published": "2026-10-18T11:08:48.682Z", "_buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356", "_status": "success", "_host": "GitHub-Actions", "_jobs": [ { "job": 117658714944, "time": 163, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "ERROR", "artifact": "12135080607" }, { "job": 117658714887, "time": 208, "config": "linux-release-x86_64", "r": "4.6.1", "check": "ERROR", "artifact": "12134731071" }, { "job": 117658714826, "time": 139, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "ERROR", "artifact": "12134781713" }, { "job": 117658714763, "time": 119, "config": "macos-release-arm64", "r": "4.6.1", "check": "ERROR", "artifact": "12134189566" }, { "job": 117657993798, "time": 217, "config": "source", "r": "4.6.1", "check": "OK", "artifact": "12134720740" }, { "job": 117658714781, "time": 107, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "12134866306" }, { "job": 117658714864, "time": 113, "config": "windows-devel-x86_64", "r": "4.7.0", "check": "ERROR", "artifact": "12134641844" }, { "job": 117658714754, "time": 112, "config": "windows-oldrel-x86_64", "r": "4.5.3", "check": "ERROR", "artifact": "12134916090" }, { "job": 117658714794, "time": 114, "config": "windows-release-x86_64", "r": "4.6.1", "check": "ERROR", "artifact": "12134088031" } ], "_upstream": "https://github.com/selcukorkmaz/splitgraph", "_commit": { "id": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "author": "Selcuk Korkmaz ", "committer": "GitHub ", "message": "Merge pull request #2 from selcukorkmaz/release/0.4.0\n\nRelease/0.4.0", "time": 1789716222 }, "_maintainer": { "name": "Selcuk Korkmaz", "email": "selcukorkmaz@gmail.com", "login": "selcukorkmaz", "twitter": "@selcukorkmaz", "description": "I am an associate professor in the Department of Biostatistics. ", "uuid": 6230704, "orcid": "0000-0003-4632-6850" }, "_distro": "resolute", "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 4.1.0", "role": "Depends" }, { "package": "graphics", "role": "Imports" }, { "package": "igraph", "role": "Imports" }, { "package": "stats", "role": "Imports" }, { "package": "utils", "role": "Imports" }, { "package": "bioLeak", "role": "Suggests" }, { "package": "jsonlite", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "pkgload", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "rsample", "role": "Suggests" }, { "package": "SummarizedExperiment", "role": "Suggests" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" } ], "_owner": "selcukorkmaz", "_selfowned": true, "_usedby": 0, "_updates": [ { "week": "2026-12", "n": 2 }, { "week": "2026-16", "n": 1 }, { "week": "2026-18", "n": 3 }, { "week": "2026-24", "n": 1 }, { "week": "2026-27", "n": 6 }, { "week": "2026-28", "n": 3 }, { "week": "2026-38", "n": 1 } ], "_tags": [], "_stars": 1, "_contributors": [ { "user": "selcukorkmaz", "count": 39, "uuid": 6230704 } ], "_userbio": { "uuid": 6230704, "type": "user", "name": "Selçuk Korkmaz", "followers": 59, "description": "I am an associate professor in the Department of Biostatistics. " }, "_downloads": { "count": 541, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/splitGraph" }, "_devurl": "https://github.com/selcukorkmaz/splitgraph", "_searchresults": 13, "_rbuild": "4.6.1", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/manual.pdf", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "extra/splitGraph.html", "LICENSE" ], "_homeurl": "https://github.com/selcukorkmaz/splitgraph", "_realowner": "selcukorkmaz", "_cranurl": true, "_releases": [ { "version": "0.1.0", "date": "2026-04-21" }, { "version": "0.2.0", "date": "2026-04-29" }, { "version": "0.3.0", "date": "2026-07-03" }, { "version": "0.4.0", "date": "2026-09-17" } ], "_exports": [ "add_edges", "as_igraph", "as_split_spec", "build_dependency_graph", "combine_graphs", "create_edges", "create_nodes", "dependency_graph", "depgraph_validation_report", "derive_split_constraints", "detect_dependency_components", "detect_shared_dependencies", "export_graph", "graph_edge_set", "graph_from_metadata", "graph_node_set", "graph_query_result", "grouping_vector", "ingest_metadata", "leakage_risk_summary", "migrate_dependency_graph_json", "migrate_split_spec_json", "query_edge_type", "query_neighbors", "query_node_type", "query_paths", "query_shortest_paths", "read_dependency_graph", "read_split_spec", "relatedness_edges_from_kinship", "spatial_edges_from_coords", "split_constraint", "split_spec", "split_spec_validation", "subset_graph", "summarize_leakage_risks", "validate_graph", "validate_graph_json", "validate_split_spec", "validate_split_spec_json", "write_dependency_graph", "write_split_spec" ], "_help": [ { "page": "as_split_spec", "title": "Translate splitGraph Constraints into Stable Split Specifications", "topics": [ "as_split_spec", "summarize_leakage_risks", "validate_split_spec" ] }, { "page": "build_dependency_graph", "title": "Assemble and Validate Dependency Graphs", "topics": [ "as_igraph", "build_dependency_graph", "validate_graph" ] }, { "page": "create_nodes", "title": "Create Canonical Node and Edge Tables", "topics": [ "create_edges", "create_nodes" ] }, { "page": "depgraph_validation_report", "title": "Validation Report Object for splitGraph Graphs", "topics": [ "depgraph_validation_report", "leakage_risk_summary", "split_spec", "split_spec_validation" ] }, { "page": "derive_split_constraints", "title": "Derive Split Constraints from Dependency Graphs", "topics": [ "derive_split_constraints", "grouping_vector" ] }, { "page": "export_graph", "title": "Export a Dependency Graph for Other Tools", "topics": [ "export_graph" ] }, { "page": "graph_edit", "title": "Edit Dependency Graphs", "topics": [ "add_edges", "combine_graphs", "graph_edit", "subset_graph" ] }, { "page": "graph_from_metadata", "title": "Build a Dependency Graph Directly from a Metadata Table", "topics": [ "graph_from_metadata", "graph_from_metadata.data.frame", "graph_from_metadata.default", "graph_from_metadata.SummarizedExperiment" ] }, { "page": "graph_node_set", "title": "Construct Core splitGraph S3 Objects", "topics": [ "dependency_graph", "graph_edge_set", "graph_node_set", "graph_query_result", "split_constraint" ] }, { "page": "ingest_metadata", "title": "Standardize Sample Metadata", "topics": [ "ingest_metadata" ] }, { "page": "migrate_json", "title": "Upgrade Serialized splitGraph JSON to the Current Schema Version", "topics": [ "migrate_dependency_graph_json", "migrate_json", "migrate_split_spec_json" ] }, { "page": "pairwise_edges", "title": "Build Pairwise Leakage Edges from Continuous Similarity", "topics": [ "pairwise_edges", "relatedness_edges_from_kinship", "spatial_edges_from_coords" ] }, { "page": "plot.dependency_graph", "title": "Plot a Dependency Graph", "topics": [ "plot.dependency_graph" ] }, { "page": "query_node_type", "title": "Query Dependency Graph Structure", "topics": [ "detect_dependency_components", "detect_shared_dependencies", "query_edge_type", "query_neighbors", "query_node_type", "query_paths", "query_shortest_paths" ] }, { "page": "splitgraph_conditions", "title": "Classed Conditions Signalled by splitGraph", "topics": [ "splitgraph_conditions" ] }, { "page": "validate_json", "title": "Validate Serialized splitGraph JSON Against the Shipped Schema", "topics": [ "validate_graph_json", "validate_json", "validate_split_spec_json" ] }, { "page": "write_dependency_graph", "title": "Serialize a Dependency Graph to JSON", "topics": [ "read_dependency_graph", "write_dependency_graph" ] }, { "page": "write_split_spec", "title": "Serialize a Split Specification to JSON", "topics": [ "read_split_spec", "write_split_spec" ] } ], "_readme": "https://github.com/selcukorkmaz/splitgraph/raw/HEAD/README.md", "_rundeps": [ "cli", "cpp11", "glue", "igraph", "lattice", "lifecycle", "magrittr", "Matrix", "pkgconfig", "rlang", "vctrs" ], "_vignettes": [ { "source": "adapter-cookbook.Rmd", "filename": "adapter-cookbook.html", "title": "Adapter cookbook: from split_spec to native resamples", "author": "Selçuk Korkmaz", "engine": "knitr::rmarkdown", "headings": [ "What this vignette is for", "Build a split_spec to work with", "Adapter 1 — base R: leave-one-group-out folds", "Honoring block variables", "Honoring the stratum annotation", "Adapter 2 — rsample::group_vfold_cv()", "Adapter 3 — rsample::rolling_origin()", "Two things to check before trusting an ordered adapter", "Going across language boundaries via JSON", "Letting the spec pick the adapter", "When you need a custom adapter" ], "created": "2026-04-29 12:58:47", "modified": "2026-09-18 07:23:42", "commits": 3 }, { "source": "case-study-gse60424.Rmd", "filename": "case-study-gse60424.html", "title": "Case study: a real multi-donor, multi-cell-type cohort (GEO GSE60424)", "engine": "knitr::rmarkdown", "headings": [ "The data", "Build the graph", "What validation says", "How much would a naive split leak?", "Derive constraints", "Composite grouping and over-merging", "The split_spec", "Working with a subset", "Handing off" ], "created": "2026-09-18 07:23:42", "modified": "2026-09-18 07:23:42", "commits": 1 }, { "source": "cross-language-handoff.Rmd", "filename": "cross-language-handoff.html", "title": "Cross-language handoff: R to JSON to Python to scikit-learn", "author": "Selçuk Korkmaz", "engine": "knitr::rmarkdown", "headings": [ "Derive and serialize in R", "What is actually on disk", "Read in Python", "Versions are part of the contract", "Verify the round-trip", "Drive scikit-learn", "Why this matters" ], "created": "2026-07-02 19:03:02", "modified": "2026-09-18 07:23:42", "commits": 3 }, { "source": "faq-design-notes.Rmd", "filename": "faq-design-notes.html", "title": "FAQ and design notes", "engine": "knitr::rmarkdown", "headings": [ "Why not just call make_split_plan(group = , batch = ) directly?", "When does composite-strict over-merge?", "How do thresholds interact with transitive closure?", "What does the stratum column mean, and does splitGraph stratify?", "Schema versioning policy, in one place", "Can I build a graph straight from a SummarizedExperiment?", "Which errors can I catch programmatically?", "How large a cohort can splitGraph handle?" ], "created": "2026-09-18 07:23:42", "modified": "2026-09-18 07:23:42", "commits": 1 }, { "source": "modeling-structure.Rmd", "filename": "modeling-structure.html", "title": "Modeling site, platform, relatedness, and spatial structure", "author": "Selçuk Korkmaz", "engine": "knitr::rmarkdown", "headings": [ "Cluster-style relations: site, region, platform, assay", "Watch for a composite that collapses", "Pairwise relation: genetic relatedness", "Pairwise relation: spatial proximity", "Deriving on a subset is leakage-safe", "Combining a pairwise relation with a direct one", "Thresholds are inputs, not modeling" ], "created": "2026-07-02 19:35:11", "modified": "2026-09-18 07:23:42", "commits": 3 }, { "source": "quick-start.Rmd", "filename": "quick-start.html", "title": "Quick start: from a metadata table to a split_spec in ten minutes", "engine": "knitr::rmarkdown", "headings": [ "1. A metadata table", "2. Build and validate", "3. Choose a constraint mode", "4. Emit the split_spec", "5. See which leakage paths the choice closes", "6. Hand off", "Where to go next" ], "created": "2026-09-18 07:23:42", "modified": "2026-09-18 07:23:42", "commits": 1 }, { "source": "leakage-aware-workflow.Rmd", "filename": "leakage-aware-workflow.html", "title": "splitGraph: From Metadata to Leakage-Aware Split Design", "author": "Selçuk Korkmaz", "engine": "knitr::rmarkdown", "headings": [ "Why splitGraph exists", "A realistic toy dataset", "Fast path: graph_from_metadata()", "Ingest metadata and build typed nodes and edges", "Assemble the dependency graph", "Visualize the typed structure", "Reshaping a graph you already have", "Exporting for other tools", "Validate before you split", "When you really do need to relax a check", "Query the graph to inspect hidden structure", "Derive split constraints from the graph", "Batch constraints", "Time constraints", "Composite constraints", "Cluster-style relations: site, region, platform, assay", "Site", "Region", "Platform and assay", "Pairwise relations: relatedness and spatial proximity", "Time ordering can come from precedence edges alone", "Translate the constraint into a split specification", "Summarize the leakage picture in one object", "Downstream handoff", "Persisting the handoff", "Case studies", "Case study 1: repeated subjects in a longitudinal cohort", "Case study 2: a subject reused across studies", "Case study 3: partially observed technical metadata", "Case study 4: choosing a defensible split strategy", "When splitGraph is useful", "What splitGraph is not for", "Takeaway" ], "created": "2026-03-16 22:13:20", "modified": "2026-09-18 07:23:42", "commits": 7 } ], "_score": 5.5031094366713695, "_indexed": true, "_nocasepkg": "splitgraph", "_universes": [ "selcukorkmaz" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.4.0", "date": "2026-10-18T11:06:54.000Z", "distro": "resolute", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/045d27a813dab92eef96501d3572c3bb2b6501ce0c4741741c3d3e5372ed1479", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.6.1", "os": "linux", "version": "0.4.0", "date": "2026-10-18T11:07:32.000Z", "distro": "resolute", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/6d4687b8a3768e17e6475a85a79b11f171035b25d3b00c3cf460d6fa8d0dc934", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.5.3", "os": "mac", "version": "0.4.0", "date": "2026-10-18T11:06:37.000Z", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/e3021a4b9db1e3b14b106c1fcb674d5427efa868e196821ff56a036c4e290485", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.6.1", "os": "mac", "version": "0.4.0", "date": "2026-10-18T11:06:24.000Z", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/7598c56630c0de8fd8476324596b8ad3362ffac84d50e1185585ef3744f00f2c", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.6.0", "os": "wasm", "version": "0.4.0", "date": "2026-10-18T11:06:40.000Z", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/b8ec94489a1e7c5519e2e9f5d40a508fecbcb6896379174352e80f5db719ef2d", "status": "success", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.7.0", "os": "win", "version": "0.4.0", "date": "2026-10-18T11:05:47.000Z", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/757ae99c4dd92cd653270641197c99beca5627dfe2a729c5741d9d17f7bd450a", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.5.3", "os": "win", "version": "0.4.0", "date": "2026-10-18T11:06:03.000Z", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/4d858aad672f04cfb15235e014267561d9ffb1574f7a8ec7ce347edbffaa2e2c", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" }, { "r": "4.6.1", "os": "win", "version": "0.4.0", "date": "2026-10-18T11:05:58.000Z", "commit": "c12682e3ee9ea3e1c8f070bedcc588286649c530", "fileid": "https://r2.ropensci.org/9781ca028e57494d05c275433c32b7e27d8c9525138c6e6ccbaa1222a17ff941", "status": "failure", "check": "ERROR", "buildurl": "https://github.com/r-universe/selcukorkmaz/actions/runs/39121531356" } ] }