Bio stats ml reporting
Analyze biological results with statistics or machine learning and produce validated reports. Use when aggregating features, testing hypotheses, training models, or reporting performance.From its SKILL.md
npx -y skills add fmschulz/omics-skills --skill bio-stats-ml-reportingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 11 stars11 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
- runs commandsInstructs the agent to run 2 commands, including `scripts/validate_predictions.py` and 1 more.
SKILL.md
5.1 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it
Bio Stats ML Reporting
Aggregate results, train ML models, and produce reports with validated references.
Instructions
- Join outputs in DuckDB v1.1+ and build feature tables. Arrow / DuckLake integration is the recommended bridge into ML pipelines for large datasets.
- Train baseline models and evaluate with cross-validation.
- CPU baseline: scikit-learn v1.5+ for linear/tree/clustering baselines; XGBoost v2.1.4+ for gradient boosting.
- GPU node available (CUDA): set
device="cuda"on XGBoost (native since v2.0) by default. For sklearn-compatible estimators (random forest, k-means, PCA, UMAP), use RAPIDS cuML as a drop-in replacement and record the device in the run log.
- Generate reports and validate references.
- Validate the prediction table with
scripts/validate_predictions.py. Keep group identifiers and confounder labels in the table so the gate can detect sample/group leakage, class imbalance, calibration failure, batch-outcome imbalance, and performance that does not beat the majority-class null.
- Validate the prediction table with
- For exploratory omics projects, aggregate discovery evidence across the literature-derived analysis playbook, annotation, phylogenomics, viromics, and comparative-genomics outputs.
- Comparative-axes rollup — join the per-axis comparison artifacts produced by upstream skills into a single
comparative_axes_summary.tsv. The rollup must have one row per (query genome, axis) and include:genome-property frontier(size, gene count, etc. — link torelative_genome_metrics.tsvandgenome_size_frontier.tsv)marker-gene census(link tomarker_census.tsv)family copy-number expansions/contractions(link tofamily_copy_number_comparison.tsvandfamily_expansion_candidates.tsv)synteny / conserved neighborhoods(link toconserved_neighborhoods.tsv)non-coding RNA census(link toncRNA_census.tsv) Each row records observation, comparison baseline, literature reference, status (notable / conserved / artifact / negative), and a follow-up test.
- Produce an interesting-findings section that ranks candidate discoveries relative to the literature-derived baseline and separates:
- strong candidates with multiple evidence types
- plausible candidates needing validation
- likely artifacts or conserved lineage features
- explicit negative findings where nothing notable was detected
- Include the comparison baseline, literature context, confidence, and next discriminating analyses for each candidate.
Quick Reference
| Task | Action |
|---|---|
| Run workflow | Follow the steps in this skill and capture outputs. |
| Validate inputs | Confirm required inputs and reference data exist. |
| Review outputs | Inspect reports and QC gates before proceeding. |
| Tool docs | See docs/README.md. |
| Validate predictions | uv run --no-project python scripts/validate_predictions.py predictions.tsv --report validation.json --require-beats-null |
Input Requirements
Prerequisites:
- Tools declared in the project's pinned Pixi environment. See
docs/README.mdfor expected tools. - Results tables and metadata are available. Inputs:
- results/.parquet or results/.tsv
- metadata.tsv
Output
- results/bio-stats-ml-reporting/models/
- results/bio-stats-ml-reporting/metrics.tsv
- results/bio-stats-ml-reporting/comparative_axes_summary.tsv
- results/bio-stats-ml-reporting/discovery_summary.tsv
- results/bio-stats-ml-reporting/report.md
- results/bio-stats-ml-reporting/logs/
- results/bio-stats-ml-reporting/prediction_validation.json
Quality Gates
- Model performance sanity checks pass.
- Reference validation passes.
- On failure: retry with alternative parameters; if still failing, record in report and exit non-zero.
- Verify input tables are readable and schema-consistent.
- Discovery summary joins candidate genes/features to annotation evidence, comparison baseline, literature context, and confidence.
-
comparative_axes_summary.tsvcovers all five mandatory axes (genome-property frontier, marker-gene census, family copy-number, synteny/neighborhoods, ncRNA census) for every query genome, with rows for axes that produced negative findings. - Final report states what is interesting, what is conserved/expected, what is likely artifact, and what should be tested next.
- Grouped splits have no sample or group overlap, calibration is reported, confounding and imbalance are quantified, and the model is compared with a declared null baseline.
Examples
Example 1: Expected input layout
results/*.parquet or results/*.tsv
metadata.tsv
Troubleshooting
Issue: Missing inputs or reference databases Solution: Verify paths and permissions before running the workflow.
Issue: Low-quality results or failed QC gates Solution: Review reports, adjust parameters, and re-run the affected step.
What ships with it: 11 files
52.9 KB alongside SKILL.md, 1 of them executable
docs/
- crossrefapi.md12.5 KB
- duckdb.md5.0 KB
- README.md2.9 KB
- scikit-learn.md9.6 KB
- xgboost.md11.2 KB
fixtures/
- predictions.tsv199 B
scripts/
- validate_predictions.pyruns6.8 KB
summaries/
Gives 0 of the 12 instructions most docs writing skills give in ~1.1k tokens
Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06
- Use third-person for skill descriptionsin 54 of 1951, across 35 files
- Start descriptions with Use whenin 43 of 1951, across 29 files
- Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
- Use active voicein 40 of 1951, across 36 files
- Map file responsibilities before defining tasksin 36 of 1951, across 29 files
- Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
- Ask one question at a timein 35 of 1951
- Offer execution options after saving the planin 33 of 1951, across 24 files
- Include complete code in every stepin 33 of 1951, across 27 files
- Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
- Announce the skill usage at the startin 30 of 1951
- Verify agent compliance after adding the skillin 29 of 1951, across 17 files
Said here and by no other author read
- Join outputs using DuckDB to build feature tables
- Train baseline models using scikit-learn or XGBoost
- Use RAPIDS cuML for GPU acceleration when available
- Validate prediction tables using the provided script
- Aggregate discovery evidence across omics outputs
- Create a comparative axes summary file
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.