Ensembl Database

Ensembl Database: ID Mapping and Genomic Features

Prerequisites

1. uv: Read the uv skill and follow its Setup instructions to ensure uv is installed and on PATH.
2. User Notification: If .licenses/ensembl_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://useast.ensembl.org/index.html and https://github.com/Ensembl/ensembl-rest/wiki, then (2) create the file recording the notification text and timestamp.

Overview

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:

• ENSG (Gene): Stable identifier for a human gene. Other species will have different three-letter species codes.
• ENST (Transcript): Stable identifier for a transcript (splicing isoform).
• ENSP (Protein): Stable identifier for a translated protein.
• MANE Select: The consensus primary transcript agreed upon by Ensembl and NCBI.
• Canonical: Ensembl's representative transcript (used if MANE is not available or non-human).

Core Rules

• Use the Wrapper: ALWAYS execute the provided helper scripts to query the database rather than accessing the database directly. The scripts automatically enforce the required rate limit gracefully.
• Default Species: If the species is absent or ambiguous in the prompt, default to "human". You MUST explicitly flag this default to the user to ensure they are aware.
• Primary Transcripts: When listing transcripts for a gene, only return the MANE Select transcript (for human) or the Canonical transcript (for others) unless the user explicitly asks for all alternative isoforms. You MUST flag to the user when multiple transcripts are available and you are defaulting to the primary one.
• Assembly Handling: The default assembly is GRCh38. For GRCh37 requests, you MUST use the --assembly GRCh37 flag. You MUST explicitly flag to the user when a non-default assembly is being used.
• Output Location: The script writes full JSON/FASTA output to temporary files in /tmp by default, or to a user-specified file using the --output flag. It also prints a concise summary to stdout.
• Notification: If this skill is used, ensure this is mentioned in the output.

Available Commands

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 transcripts command, canonical-tss accepts both symbols (e.g., TP53) and Ensembl IDs, and automatically resolves them. It also does the math for strand orientation (TSS is Start for + strand and End for - strand), outputting the single integer coordinate directly.