cosmic-database

Download COSMIC cancer mutation datasets via Python scripts and CLI tools.

16|7|Updated Nov 20, 2025
One-click install
npx skills add https://github.com/jackspace/ClaudeSkillz --skill cosmic-database-jackspace
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cosmic-database
Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-db-cosmic-database
Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill cosmic-database-jackspace

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pandas, pysam, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates access to COSMIC cancer mutation datasets, including mutations, Cancer Gene Census, mutational signatures, gene fusions, and copy number data, enabling authenticated retrieval and integration into cancer genomics workflows.

Core Features & Use Cases

  • Query core COSMIC data types (mutations, cancer_gene_census, signatures, structural_variants, copy_number, gene_expression, fusion_genes)
  • Handle authentication and data downloads for academic and commercial use
  • Download and load data into Python/pandas workflows for downstream analyses
  • Integrate COSMIC data with variant annotation, signature analysis, and cancer genomics pipelines

Quick Start

Use the Python script to download COSMIC data files (e.g., CosmicMutantExport.tsv.gz) and read them with pandas for downstream analyses.

Frequently Asked Questions about cosmic-database

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download COSMIC cancer mutation data programmatically?

Download COSMIC cancer mutation data programmatically using Python scripts that handle authentication and retrieve datasets like CosmicMutantExport.tsv.gz. The Skill provides functions to specify genome assembly (GRCh38/GRCh37), dataset type, and file format (TSV, CSV, VCF), then load results directly into pandas for analysis.

What COSMIC datasets can I access through this integration?

Access core COSMIC datasets including mutations, Cancer Gene Census, mutational signatures, structural variants, fusions, copy number, gene expression, and resistance mutations. All datasets support multiple genome assemblies and file formats for integration into cancer genomics workflows.

Can I use COSMIC data with VCF files in my bioinformatics pipeline?

Yes, this Skill supports VCF file format alongside TSV and CSV for COSMIC data downloads. You can retrieve mutation data in VCF format and integrate it with pysam for variant annotation and downstream bioinformatics analyses.

How do I handle authentication when accessing COSMIC datasets?

The Skill enforces authentication handling for both academic and commercial COSMIC access. Authentication credentials are managed through the Python functions, enabling secure, reproducible data downloads across research and clinical contexts.

Do I need pandas and requests libraries to use COSMIC data access?

Yes, the Skill requires pandas for data manipulation, requests for authenticated downloads, and pysam for VCF file handling. These dependencies enable loading COSMIC datasets into Python workflows for downstream analysis and integration.

What's the best way to integrate COSMIC mutations into a precision oncology pipeline?

Use the Skill's CLI and Python functions to download relevant COSMIC datasets, specify genome assembly and file format, then load data into pandas DataFrames. Combine with variant annotation and signature analysis tools to build reproducible precision oncology workflows.