Menü
Gene ID conversion and annotation. Invoke when you need to map between any gene identifier formats.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | mygene |
| description | Gene ID conversion and annotation. Invoke when you need to map between any gene identifier formats. |
Python client for the MyGene.info API — fast gene ID mapping and annotation.
import mygene
mg = mygene.MyGeneInfo()
# Single gene query
result = mg.getgene('ENSG00000141510', fields='symbol,name')
# → {'symbol': 'TP53', 'name': 'tumor protein p53', ...}
# Batch query (most common use case)
gene_ids = ['ENSG00000141510', 'ENSG00000012048', 'ENSG00000146648']
results = mg.querymany(gene_ids, scopes='ensembl.gene', fields='symbol,entrezgene', species='human')
import mygene
import pandas as pd
mg = mygene.MyGeneInfo()
# Your gene list (e.g., from DE results index)
ensembl_ids = df.index.tolist()
# Query
results = mg.querymany(
ensembl_ids,
scopes='ensembl.gene',
fields='symbol',
species='human', # or 'mouse', 'rat', etc.
as_dataframe=True
)
# Build mapping dict
id_map = results['symbol'].dropna().to_dict()
# Apply to your data
df['gene_symbol'] = df.index.map(id_map)
results = mg.querymany(
gene_symbols,
scopes='symbol',
fields='entrezgene',
species='human',
as_dataframe=True
)
results = mg.querymany(
refseq_ids, # e.g., ['NM_000546', 'NM_007294']
scopes='refseq',
fields='symbol',
species='human',
as_dataframe=True
)
results = mg.querymany(
entrez_ids,
scopes='entrezgene',
fields='symbol',
species='human',
as_dataframe=True
)
| Parameter | Values | Purpose |
|---|---|---|
scopes | 'ensembl.gene', 'symbol', 'entrezgene', 'refseq' | Input ID type |
fields | 'symbol', 'entrezgene', 'name', 'go', 'pathway.kegg' | What to return |
species | 'human', 'mouse', 'rat', or taxonomy ID (9606, 10090) | Organism filter |
as_dataframe | True / False | Return DataFrame vs list of dicts |
# Ensembl gene IDs
'ENSG00000141510' # Human (ENSG)
'ENSMUSG00000059552' # Mouse (ENSMUSG)
# Entrez IDs — plain integers
'7157' # TP53
# Gene symbols — short uppercase names
'TP53', 'BRCA1', 'EGFR'
# RefSeq
'NM_000546' # mRNA
'NP_000537' # Protein
results = mg.querymany(ids, scopes='ensembl.gene', fields='symbol', species='human', as_dataframe=True)
# Check for unmapped
unmapped = results[results['notfound'] == True] if 'notfound' in results.columns else pd.DataFrame()
print(f"Mapped: {len(results) - len(unmapped)}, Unmapped: {len(unmapped)}")
# Use only mapped genes
mapped = results[results['symbol'].notna()]
# Some IDs map to multiple genes — keep first match
results = results[~results.index.duplicated(keep='first')]
Mouse genes use different capitalization (e.g., Tp53 not TP53):
results = mg.querymany(
mouse_ensembl_ids,
scopes='ensembl.gene',
fields='symbol',
species='mouse', # Important: specify mouse
as_dataframe=True
)
Wrong species: Always specify species. Ensembl IDs are species-specific (ENSG = human, ENSMUSG = mouse) but specifying the species avoids ambiguous matches.
Version suffixes: Ensembl IDs sometimes have versions (ENSG00000141510.12). Strip them:
clean_ids = [x.split('.')[0] for x in ensembl_ids]
Network required: mygene queries an online API. It will fail without network access.
Large batches: For >1000 genes, querymany handles batching automatically. No need to split manually.
Mixed ID types: If your data has mixed ID formats, detect the type first:
if ids[0].startswith('ENS'):
scopes = 'ensembl.gene'
elif ids[0].isdigit():
scopes = 'entrezgene'
else:
scopes = 'symbol'
import mygene
import gseapy as gp
mg = mygene.MyGeneInfo()
# 1. DE results have Ensembl IDs as index
de_results = pd.read_csv('deseq2_results.csv', index_col=0)
# 2. Map to symbols
clean_ids = [x.split('.')[0] for x in de_results.index]
mapped = mg.querymany(clean_ids, scopes='ensembl.gene', fields='symbol', species='human', as_dataframe=True)
id_map = mapped['symbol'].dropna().to_dict()
# 3. Get significant gene symbols
sig_genes = de_results[de_results['padj'] < 0.05].index
sig_symbols = [id_map[g.split('.')[0]] for g in sig_genes if g.split('.')[0] in id_map]
# 4. Run enrichment
enr = gp.enrichr(gene_list=sig_symbols, gene_sets='GO_Biological_Process_2021', organism='human')
Invoke after experiment-runner completes an investigation's query bundle. Evaluates all claims in current_investigation.json and produces an investigation-level adjudication. Writes claim_scores.json.
Invoke after investigation-decomposition. Runs all queries in an investigation bundle using shared data preparation. Writes code and results.
Invoke after main agent writes L2 assessment. Reads epistemic state (L1/L2), patterns, and investigations to recommend next action. Writes strategy_recommendation.json.
Gene set enrichment analysis (GSEA, Enrichr, over-representation). Invoke when query mentions enrichment, pathway analysis, GO analysis, GSEA, or gene set.
Invoke before running experiments for an investigation. Reads current_investigation.json and task_packet.json, writes current_investigation_requirements.json with shared data preparation and per-query requirements.
Phylogenetic analysis: multiple sequence alignment (MAFFT), tree building (IQ-TREE, FastTree), tree metrics (treeness, branch lengths, patristic distances). Invoke when query involves phylogenetic trees, evolutionary analysis, sequence alignment, treeness, or tree statistics.