gabrielmoreira Why This Exists
Researchers often need a quick first-pass view of whether a gene or protein target has evidence across multiple public sources. In practice, this usually means checking several websites manually and informally combining results. This skill makes that process reproducible by retrieving and organising public evidence into one structured output.
This skill is for research triage only. It does not infer causality, rank therapeutic value, or make clinical recommendations.
Core Capabilities
- Accept a gene or protein target and an optional disease term.
- Retrieve canonical target information from UniProt.
- Retrieve disease-target association evidence from Open Targets.
- Retrieve recent literature hits from PubMed.
- Optionally retrieve trial records relevant to the target and disease.
- Produce a machine-readable JSON file and a human-readable Markdown report.
Input Formats
| Argument | Required | Example | Notes |
|---|---|---|---|
--gene |
Yes, unless --demo is used |
IL6R |
Gene or target symbol |
--disease |
No | coronary artery disease |
Optional disease context |
--output |
Yes | demo_out |
Output directory |
--max-papers |
No | 5 |
Number of PubMed hits to include |
--max-trials |
No | 5 |
Number of trial records to include |
--demo |
No | --demo |
Runs the built-in demo query |
Workflow
- Validate CLI inputs.
- Resolve the query from either user input or demo mode.
- Query public data sources.
- Normalise results into a structured evidence object.
- Write JSON and Markdown outputs.
- Write reproducibility bundle:
reproducibility/checksums.sha256— SHA-256 hashes of all output filesreproducibility/environment.yml— pinned Conda/pip environmentro-crate-metadata.json— RO-Crate 1.1 provenance record (run params, outputs, script)
CLI Reference
Demo mode
python skills/omics-target-evidence-mapper/omics_target_evidence_mapper.py --demo --output demo_out