Regulatory genomics
Regulatory genomics skill. Enhancer/promoter annotation, transcription factor binding, regulatory variant analysis, and chromatin state classification.
Use This Skill When
- Enhancer/promoter annotation.
- Transcription factor binding.
- Regulatory variant analysis.
- Chromatin state classification.
Required Inputs
- Research objective, decision target, or hypothesis.
- Available data, source constraints, and domain assumptions.
- Required outputs, success metrics, and deadline or reproducibility constraints.
Workflow
- Confirm scope, assumptions, and the exact artifact set to save.
- Apply the narrowest domain method that answers the request with defensible evidence.
- Save code, tables, figures, and intermediate outputs to files instead of chat-only output.
- State limitations, uncertainty, and any validation or sensitivity checks performed.
- Append skill selection, handoff I/O, and file writes to
logs/process-log.jsonl.
Deliverables
report.md: concise method, results, interpretation, and file inventory in the user's language.results/: structured outputs, metrics, model artifacts, or extracted findings.figures/: English-only charts, diagrams, or panels when visual output is needed.data/: processed or derived datasets when transformation occurs.
Available Tools (MCP)
External tools available via ToolUniverse MCP server.
Falls back to Python requests + public REST APIs when MCP is unavailable.
| Source |
Tool |
Description |
| ENCODE |
ENCODE_search |
ENCODE API |
| ENCODE |
ENCODE_get_experiment |
ENCODE API |
| Ensembl |
Ensembl_regulatory_features |
Ensembl API |
Quality Gates
If any gate fails: identify the specific failing check, fix the issue, and re-validate before proceeding.
Gotchas
- Reference genome version (hg19 vs hg38) must be confirmed before analysis. Mixing versions produces invalid coordinates
- FASTQ quality scores can use different encoding (Phred+33 vs Phred+64). Verify encoding before alignment
- Batch effects between sequencing runs must be assessed. Combine technical replicates only after batch correction
Validation Loop
- Execute analysis and generate outputs
- Check:
- Method selection matches the research question and stated assumptions
- All outputs are saved to files (no chat-only results)
- Limitations and uncertainty are explicitly stated
logs/process-log.jsonl is updated with execution trace
- If any check fails:
- Identify the failing gate
- Fix the specific issue
- Re-run validation
- Proceed only after all gates pass
1---2name: co-scientist-regulatory-genomics3description: Regulatory genomics skill. Enhancer/promoter annotation, transcription factor binding, regulatory variant analysis, and chromatin state classification. Use when working with enhancer/promoter annotation, transcription factor binding, regulatory variant analysis.4---56# Regulatory genomics78Regulatory genomics skill. Enhancer/promoter annotation, transcription factor binding, regulatory variant analysis, and chromatin state classification.910## Use This Skill When1112- Enhancer/promoter annotation.13- Transcription factor binding.14- Regulatory variant analysis.15- Chromatin state classification.1617## Required Inputs1819- Research objective, decision target, or hypothesis.20- Available data, source constraints, and domain assumptions.21- Required outputs, success metrics, and deadline or reproducibility constraints.2223## Workflow24251. Confirm scope, assumptions, and the exact artifact set to save.262. Apply the narrowest domain method that answers the request with defensible evidence.273. Save code, tables, figures, and intermediate outputs to files instead of chat-only output.284. State limitations, uncertainty, and any validation or sensitivity checks performed.295. Append skill selection, handoff I/O, and file writes to `logs/process-log.jsonl`.3031## Deliverables3233- `report.md`: concise method, results, interpretation, and file inventory in the user's language.34- `results/`: structured outputs, metrics, model artifacts, or extracted findings.35- `figures/`: English-only charts, diagrams, or panels when visual output is needed.36- `data/`: processed or derived datasets when transformation occurs.3738## Available Tools (MCP)3940> External tools available via [ToolUniverse](https://github.com/mims-harvard/ToolUniverse) MCP server.41> Falls back to Python `requests` + public REST APIs when MCP is unavailable.4243| Source | Tool | Description |44|--------|------|-------------|45| ENCODE | `ENCODE_search` | ENCODE API |46| ENCODE | `ENCODE_get_experiment` | ENCODE API |47| Ensembl | `Ensembl_regulatory_features` | Ensembl API |4849## Quality Gates5051- [ ] The selected method matches the scientific question and stated assumptions.52- [ ] Outputs are reproducible, saved to files, and traceable from inputs to conclusions.53- [ ] Missing data, uncertainty, bias, and hard limits are made explicit.54- [ ] `report.md` and `logs/process-log.jsonl` reference the generated artifacts.55- [ ] No essential result remains chat-only.5657If any gate fails: identify the specific failing check, fix the issue, and re-validate before proceeding.5859## Gotchas6061- Reference genome version (hg19 vs hg38) must be confirmed before analysis. Mixing versions produces invalid coordinates62- FASTQ quality scores can use different encoding (Phred+33 vs Phred+64). Verify encoding before alignment63- Batch effects between sequencing runs must be assessed. Combine technical replicates only after batch correction6465## Validation Loop66671. Execute analysis and generate outputs682. Check:69 - Method selection matches the research question and stated assumptions70 - All outputs are saved to files (no chat-only results)71 - Limitations and uncertainty are explicitly stated72 - `logs/process-log.jsonl` is updated with execution trace733. If any check fails:74 - Identify the failing gate75 - Fix the specific issue76 - Re-run validation774. Proceed only after all gates pass
nahisaho