What problem does it solve?
This Skill solves the problem of manually searching and downloading nucleotide sequence data by accession or metadata from the European Nucleotide Archive, replacing slow, error-prone data retrieval with structured API-driven downloads for downstream genomics analysis.
Core Features & Use Cases
- Accession-based retrieval: Pull nucleotide sequences and related records such as runs (raw reads), assemblies, and annotations using ENA Browser API endpoints.
- Metadata search at scale: Use ENA Portal API advanced queries to find samples, studies, read runs, and assemblies by taxonomy, fields, and date constraints.
- Bulk download workflows: Support efficient acquisition of FASTQ and assemblies via FTP/Aspera patterns and file-report style metadata needed for pipeline execution.
- Cross-reference and taxonomy lookup: Retrieve links to external databases and taxonomic lineage information to enrich analysis and improve reproducibility.
Quick Start
Ask an AI agent to retrieve FASTQ download URLs for run accession ERR123456 from ENA and return them in a pipeline-ready list.