// Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool.
Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.
Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50/Ki values, drug mechanisms, or structure searches.
Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility/inclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.
Use when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls for human genomic variants.
Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).
Query and search the EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (e.g., GO, DOID, HP). Use when the user asks to search for terms, retrieve details, navigate hierarchies (parents, children, ancestors), look up properties and individuals, get autocomplete suggestions, or access ontology metadata and statistics.
| name | ensembl-database |
| description | Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool. |
uv: Read the uv skill and follow its Setup instructions to ensure
uv is installed and on PATH.The Ensembl database is a resource for genome annotation. This skill allows you to interact with the Ensembl REST API to resolve ambiguous symbols, cross-reference IDs (RefSeq, HGNC, UniProt, ENSG), fetch raw sequences, and retrieve detailed transcript structures.
Key Concepts:
"human". You MUST explicitly flag this default to the user to
ensure they are aware.--assembly GRCh37 flag. You MUST explicitly flag to the
user when a non-default assembly is being used./tmp by default, or to a user-specified file using the --output
flag. It also prints a concise summary to stdout.1. Resolve Gene ID — Resolve a symbol, alias, or RefSeq ID to ENSG ID(s). Automatically falls back to resolving synonyms if primary symbol is not found.
uv run scripts/ensembl_api.py resolve-gene TP53 --species human --output tp53.json
uv run scripts/ensembl_api.py resolve-gene PCL2 --output pcl2.json # Falls back to synonym resolution
2. Map ID to External Database — Cross-reference an Ensembl ID to UniProt, HGNC, RefSeq, etc.
uv run scripts/ensembl_api.py map-id ENSG00000141510 --external-db UniProt --output uniprot_map.json
uv run scripts/ensembl_api.py map-id ENST00000269305 --external-db RefSeq_mRNA --output refseq_map.json
3. Get Genomic Sequence — Fetch raw DNA for a coordinate window. Supports
GRCh37 via --assembly GRCh37.
uv run scripts/ensembl_api.py get-sequence 17:7661779-7687550 --species human --output seq.txt
uv run scripts/ensembl_api.py get-sequence chr9:21971100-21971200 --assembly GRCh37 --output seq_grch37.txt
4. Gene Summary — High-level metadata: symbol, biotype, description, chromosomal location.
uv run scripts/ensembl_api.py gene-summary ENSG00000141510 --output gene_summary.json
5. List Transcripts — All transcripts for a gene, with optional
--only-mane or --only-canonical filters. Output includes Transcript Support
Level (TSL).
uv run scripts/ensembl_api.py transcripts ENSG00000141510 --only-mane --output transcripts_mane.json
uv run scripts/ensembl_api.py transcripts ENSG00000141510 --only-canonical --output transcripts_canonical.json
uv run scripts/ensembl_api.py transcripts ENSG00000141510 --output transcripts_all.json
5b. Canonical TSS — Get the single coordinate of the Transcription Start Site (TSS) for the canonical transcript of a gene.
[!NOTE] Unlike the standard
transcriptscommand,canonical-tssaccepts both symbols (e.g.,TP53) and Ensembl IDs, and automatically resolves them. It also does the math for strand orientation (TSS isStartfor+strand andEndfor-strand), outputting the single integer coordinate directly.
uv run scripts/ensembl_api.py canonical-tss TP53 --output tp53_tss.json
uv run scripts/ensembl_api.py canonical-tss ENSG00000141510 --output tss.json
6. Transcript Structure — Exon coordinates, CDS boundaries, and computed 5'/3' UTR regions for a transcript.
uv run scripts/ensembl_api.py transcript-structure ENST00000269305 --output structure.json
7. Protein Info — ENSP ID and sequence length for a transcript.
uv run scripts/ensembl_api.py protein-info ENST00000269305 --output protein_info.json
8. Protein Sequence — Amino acid FASTA for a transcript (ENST) or protein (ENSP) ID.
uv run scripts/ensembl_api.py protein-sequence ENST00000269305 --output protein.fasta
uv run scripts/ensembl_api.py protein-sequence ENSP00000269305 --output protein_ensp.fasta
9. Variant Consequence (VEP) — Predict molecular consequences for a genomic variant. Includes open-licensed plugins: AlphaMissense, Conservation, DosageSensitivity, IntAct, MaveDB, OpenTargets, LoF (Loftee), NMD, UTRAnnotator, mutfunc, LOEUF.
uv run scripts/ensembl_api.py vep 9:21971147:T:C --species human --output vep.json
uv run scripts/ensembl_api.py vep rs699 --species human --output vep_rs699.json
Example VEP stdout output:
[*] Variant: 9:21971147:T>C
[*] Most severe consequence: missense_variant
[*] Found 15 transcript consequences.
[*] VEP Predictions:
- ENST00000304494 (CDKN2A): Consequence = missense_variant
- ENST00000304494 (CDKN2A): Amino Acids = N/S
- ENST00000304494 (CDKN2A): SIFT = deleterious (0.01)
- ENST00000304494 (CDKN2A): AlphaMissense Class = likely_benign
- ENST00000304494 (CDKN2A): AlphaMissense Pathogenicity = 0.2129
- ENST00000304494 (CDKN2A): Conservation = 2.05
- ENST00000304494 (CDKN2A): Dosage Sensitivity (Haplo) = 0.889228328567991
- ENST00000304494 (CDKN2A): Dosage Sensitivity (Triplo) = 0.135514349094646
- ENST00000304494 (CDKN2A): Loss of Function (LOEUF) = 0.791
Presenting VEP Results: After running the VEP command, you MUST present the full VEP Predictions list from stdout to the user. This list contains both standard VEP predictions (Consequence, Amino Acids, SIFT, PolyPhen) and open-license plugin results (AlphaMissense, Conservation, Dosage Sensitivity, LOEUF, Loftee LoF, NMD, UTRAnnotator, Mutfunc). Do NOT just summarize — show the complete list so the user can see all predictions. If the list is very long (many transcripts), show the MANE Select / canonical transcript rows in full and note that the complete data is in the JSON output.
If the user needs detailed, nested structural data (like the precise integer coordinates of Exon 2 of a transcript) that isn't summarized in stdout:
--output or the temporary file
path printed by the script).jq or write a quick, disposable python snippet to
extract the specific data point requested. Do not attempt to read the
entire JSON file into your context if it is very large.If you need to make an API call that the script does not support (e.g., fetching
protein domain annotations, coordinate mapping between assemblies, homology
searches, linkage disequilibrium, or phenotype lookups), read
references/ensembl_rest_api_reference.md for a complete reference of available
endpoints, parameters, and response fields.
CRITICAL: When writing custom scripts or using alternatives to the provided
scripts, you MUST respect the Ensembl REST API rate limits (maximum 15
requests per second) and handle 429 Too Many Requests errors gracefully (e.g.,
with exponential backoff).