Gene Info

Source: https://github.com/aipoch/medical-research-skills

When to Use

• Use this skill when the request matches its documented task boundary.
• Use it when the user can provide the required inputs and expects a structured deliverable.
• Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming.

Key Features

• Scope-focused workflow aligned to: "Retrieves comprehensive gene information including PubMed publication counts, NCBI summaries, and Ensembl transcript data. Supports batch processing and file input. Invoke when the user asks for gene details, publication statistics, or needs to analyze a list of genes.".
• Packaged executable path(s): scripts/fetch_gene_info.py plus 1 additional script(s).
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

See ## Prerequisites above for related details.

• Python: 3.10+. Repository baseline for current packaged skills.
• Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.

Example Usage

See ## Usage above for related details.

cd "20260316/scientific-skills/Evidence Insight/gene-info"
python -m py_compile scripts/fetch_gene_info.py
python scripts/fetch_gene_info.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/fetch_gene_info.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: scripts/fetch_gene_info.py with additional helper scripts under scripts/.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Validation Shortcut

Run this minimal command first to verify the supported execution path:

python scripts/validate_skill.py --help

Gene Information Tool

This skill retrieves detailed information for specific genes from authoritative databases (NCBI PubMed, NCBI Gene, Ensembl). It supports single-gene queries, batch processing, and file-based input.

Capabilities

• PubMed Statistics: Retrieves total publication counts and counts for specific keywords.
• Gene Summary: Fetches official gene descriptions and summaries from NCBI.
• Transcript Data: Retrieves transcript counts and maximum amino acid sequence lengths from Ensembl.
• Batch Processing: Efficiently queries multiple genes in parallel.
• File Input: Supports reading gene lists from text files.
• Data Export: Supports saving results to JSON or CSV formats.

Usage

To use this skill, run the provided Python script with gene symbols.

Prerequisites

NCBI recommends providing an email address to contact you in case of excessive usage. You can also optionally provide an API key for higher rate limits.

Set the following environment variables (recommended):

• NCBI_EMAIL: Your email address (Recommended)
• NCBI_API_KEY: Your NCBI API Key (Optional)

Or provide them via command line arguments:

• --email <your_email> (Recommended)
• --api-key <your_api_key> (Optional)

Basic Usage (Single Gene)

python .trae/skills/gene-info/scripts/fetch_gene_info.py BRCA1

With Keyword Search (for PubMed)

python .trae/skills/gene-info/scripts/fetch_gene_info.py BRCA1 --keyword "breast cancer"

Batch Processing (Multiple Genes)

python .trae/skills/gene-info/scripts/fetch_gene_info.py BRCA1 TP53 EGFR --keyword "mutation"

File Input

Create a file containing a list of genes (supports multiple formats), then run:

Supported Formats:

• Plain text list (one per line)
• CSV/TSV files (automatically detects columns named "Gene" or "Symbol")
• Free text (comma, space, or semicolon separated)

Example genes.txt:

BRCA1
TP53
EGFR

Command:

python .trae/skills/gene-info/scripts/fetch_gene_info.py --file genes.txt --keyword "cancer"

Export Results

Save results to a CSV or JSON file:

python .trae/skills/gene-info/scripts/fetch_gene_info.py BRCA1 TP53 --output results.csv

Output Format

The script outputs a JSON array containing objects with the following fields:

• gene: Gene symbol
• totalPublications: Total PubMed publications
• keywordPublications: Publications matching gene + keyword (if keyword provided)
• summary: Gene summary text
• transcriptCount: Number of transcripts
• maxAminoAcids: Maximum amino acid length
• chromosome: Chromosome location
• organism: Organism name
• sequence: Genomic sequence (if --include-sequence used)
• orthologs: List of orthologs (if --include-homology used)

Advanced Features

Include Genomic Sequence

Add --include-sequence to fetch the genomic sequence from Ensembl.

python .trae/skills/gene-info/scripts/fetch_gene_info.py BRCA1 --include-sequence

Include Homology Data

Add --include-homology to fetch orthologs (e.g., mouse, rat homologs).

python .trae/skills/gene-info/scripts/fetch_gene_info.py BRCA1 --include-homology