메뉴
Load when converting gene identifiers between Ensembl, Entrez, and HGNC symbol in a bulk RNA-seq count matrix. Skip if the input is already in the desired identifier system, for organisms outside human/mouse, or for non-bulk-counts inputs.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
LLM-grounded biological interpretation of a verified typed consensus run. Reads the typed run dir + the original adata, runs inline per-cluster DE, looks up markers in a bundled tissue-keyed marker DB, and asks the chair LLM to (γ) name each cluster's likely cell type with mandatory marker citations and (β) recommend top-3 next-step skills with mandatory evidence_refs. Output banner [A+I: Interpreted on verified consensus]. Failure-mode contract per ADR 0012.
Multi-resolution typed consensus over sc-clustering. Fans out leiden / louvain at several resolutions in parallel, scores members by silhouette + cross-method NMI, runs kmode / weighted / LCA consensus on the surviving base clusterings, and emits a verified report carrying the mandatory A-path banner per ADR 0010.
Multi-method consensus over spatial-domains. Fans out 5 methods in parallel, computes a SACCELERATOR-style base-clustering ranking, runs typed consensus (kmode / weighted / LCA), and emits a verified consensus report with the mandatory A-path banner per ADR 0010.
Load when scaffolding a NEW OmicsClaw skill from a natural-language request — generates the skill directory layout (SKILL.md, parameters.yaml, references/, tests/) under the chosen domain. Skip when modifying an existing skill (edit its files directly) or when only routing a query (use `orchestrator`).
Load when routing a natural-language omics query to the correct domain skill across spatial / singlecell / genomics / proteomics / metabolomics / bulkrna domains via keyword / LLM / hybrid matching. Skip when the target skill is already known — invoke that skill directly.
Load when copying this directory to bootstrap a new OmicsClaw v2 skill (rename, fill in, then `git add`). Skip when an existing skill already covers the request.
| name | bulkrna-geneid-mapping |
| description | Load when converting gene identifiers between Ensembl, Entrez, and HGNC symbol in a bulk RNA-seq count matrix. Skip if the input is already in the desired identifier system, for organisms outside human/mouse, or for non-bulk-counts inputs. |
| version | 0.3.0 |
| author | OmicsClaw |
| license | MIT |
| tags | ["bulkrna","gene-id","mapping","Ensembl","Entrez","HGNC","annotation"] |
| requires | ["numpy","pandas"] |
Run between counting and downstream analysis when the gene identifiers
in your count matrix don't match the namespace of your downstream tool
(e.g. STARsolo gives Ensembl IDs but GSEA wants HGNC symbols).
Currently supports Ensembl ↔ Entrez ↔ HGNC symbol for human and mouse
via built-in tables, with optional mygene API enrichment. UniProt is
not supported — feed via --mapping-file if needed.
| Input | Format | Required |
|---|---|---|
| Count matrix | .csv (gene id col + sample count cols) | yes (or --demo) |
| Custom mapping | --mapping-file TSV | optional, overrides built-ins |
| Output | Path | Notes |
|---|---|---|
| Mapped matrix | tables/mapped_counts.csv | same shape, gene column rewritten |
| Mapping table | tables/mapping_table.csv | original_id → target_id audit |
| Unmapped IDs | tables/unmapped_genes.csv | original IDs that couldn't be resolved |
| Report | report.md + result.json | summary keys: n_original_genes, n_mapped, n_unmapped, pct_mapped, n_duplicates_resolved, duplicate_strategy, n_final_genes, from_type, to_type, species |
bulkrna_geneid_mapping.py:78: ENSG00000141510.12 → ENSG00000141510).:88 warns and skips API path if mygene not importable).--on-duplicate (sum / first / drop).tables/mapped_counts.csv, tables/mapping_table.csv, tables/unmapped_genes.csv.bulkrna_geneid_mapping.py:88 falls back silently when mygene is not importable, leaving you with built-in-table coverage only. The summary dict does not record whether the API was used; the only signal is the warning log line and the pct_mapped value (built-in tables cover ~20 well-known cancer-relevant genes — anything substantially higher implies the API ran).--from/--to only accept ensembl, entrez, symbol (bulkrna_geneid_mapping.py:271-274). UniProt and other namespaces are not in the choices list and will fail at argparse. If you need UniProt, supply a custom --mapping-file TSV.--species choices at :275). Other organisms fail with empty mappings if mygene isn't installed; either install mygene or supply --mapping-file.--on-duplicate (default sum). Default sums read counts across genes mapping to the same target symbol — meaningful for paralog families but wrong if you wanted per-isoform tracking. Choose first to take the first hit, or drop to keep only unique mappings. The number resolved is in result.json["n_duplicates_resolved"].:78). If your downstream tool requires the version suffix (rare), this skill silently drops it.python omicsclaw.py run bulkrna-geneid-mapping --demo
python omicsclaw.py run bulkrna-geneid-mapping \
--input counts.csv --output results/ \
--from ensembl --to symbol --species human
python omicsclaw.py run bulkrna-geneid-mapping \
--input counts.csv --output results/ \
--from ensembl --to symbol --on-duplicate first
references/parameters.md — every CLI flag and tuning hintreferences/methodology.md — built-in tables, mygene fallback, version-suffix strippingreferences/output_contract.md — exact output directory layoutbulkrna-qc (run before to inspect raw IDs), bulkrna-de (downstream — DE expects whatever ID system the rest of your pipeline uses), bulkrna-enrichment (downstream — enrichment requires HGNC symbols or Entrez IDs in most cases)