Why bioLeak | Guided workflow | Example data | Create leakage-aware splits with make_split_plan() | Validating splits with check_split_overlap() | Scalability | Strict leakage mode | Guarded preprocessing and imputation | Fit and resample with fit_resample() | Tidymodels interoperability | Nested tuning with tune_resample() | Advanced: Using Gradient Boosting with Parsnip | Advanced: Custom learners | Visual diagnostics | Audit leakage with audit_leakage() | Time-series leakage checks | Cross-validation uncertainty with cv_ci() | Delta Leakage Sensitivity Index: Quantifying Performance Inflation | Motivation | Mathematical framework | Notation | Stage 1: Within-repeat aggregation | Stage 2: Per-repeat inflation score | Point estimates | Setting up a two-pipeline comparison | Running delta_lsi() | Designing for a target inference tier | Statistical inference | Sign-flip randomization test | Huber M-estimator and robustness properties | BCa bootstrap confidence interval | Pairing condition and the inference tier system | Paired vs. unpaired designs | Metric direction with higher_is_better | Accessing the LeakDeltaLSI object | Connection to audit_leakage() | Parallel Processing | Simulation suite | Objects and summaries

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

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

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

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?

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

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

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

Introduction | Installation and Setup | Why Access the PDB from R? | rPDBapi Capabilities | Package Feature Map | Core Concepts in the RCSB PDB API | Workflow 1: Simple Search for Kinase Structures | Workflow 2: Refine the Search with Structured Operators | Workflow 3: Retrieve Entry-Level Metadata | Workflow 4: Inspect the Raw API Payload and Convert It to Tidy Data | Workflow 4b: Batch Retrieval, Provenance, and Cache-Aware Access | Workflow 5: Retrieve Assembly-Level Data | Workflow 5b: Identifier-Aware Retrieval Patterns | Workflow 6: Retrieve Taxonomy and Chain-Level Biological Context | Workflow 7: Retrieve Detailed Entry Annotations | Workflow 8: Download Coordinates and Inspect Atomic Data | Workflow 8b: Working with the Rich Object Model | Workflow 9: Downstream Analysis in R | Workflow 10: Optional Visualization with r3dmol | Advanced Search Modalities | Sequence Search | Sequence Motif Search | Structure Similarity Search | Chemical Search | Complete Search Operator Reference | Query Search Variants and Scan Parameters | Complete Metadata Retrieval Surface | Building Property Lists Incrementally | Non-polymer and Chemical Component Data | Instance-Level Retrieval | Low-Level API Access and Parsing Helpers | Return Contracts and Error Handling | Appendix A: Export-by-Export Reference | Appendix B: Minimal Example Pattern for Every Export | Appendix C: Supported Identifier Levels and Typical Formats | Appendix D: Return Classes and Their Meaning | Appendix E: Error and Failure-Mode Guidance | Reproducible Research with rPDBapi | Summary | Session Information

1) Similar compounds from a seed structure | 2) Fetch assay activity in long format | 3) Build activity matrix (compound x assay) | 4) Add chemical features and prepare model matrix | 5) Export model-ready artifact

1) Typed result contract | 2) Runtime policy and transport controls | 3) Unified request layer and typed wrappers | 4) Caching and offline replay | 5) Async listkey workflows (pc_submit -> pc_poll -> pc_collect) | 6) Checkpointed batching and resume | 7) Benchmarking and threshold gates | 8) Analysis-layer helpers for assay modeling | 8.1 Similarity retrieval and long assay activity table | 8.2 Activity matrix (dense or sparse) | 8.3 Feature table, matrix conversion, and export | 9) Optional ecosystem bridges | 10) Targeted PUG View helper for bio test sections | 11) Lifecycle policy (legacy vs nextgen) | 12) Recommended production pattern

Step 1: Name to CID | Step 2: CID to AID | Step 3: Assay summary retrieval

1) Resolve CIDs from names | 2) Retrieve a compact property panel | 3) Prepare a modeling-ready table | 4) Convert to model matrix form | 5) Benchmark harness for scale and CI gates

Configure defaults | Clear cache for a clean run | Cached property retrieval | Chunked batch execution