What metadata formats are supported?

The skill supports metadata retrieval in XML (native), JSON (via Portal API), and tabulated formats like TSV or CSV for easy integration into spreadsheets or dataframes.

Does it support the ENA Portal API rate limits?

Yes, it includes best practices for implementing exponential backoff and request batching to remain within the ENA API limit of 50 requests per second.

Can I search for data by specific organism names?

Yes, the skill utilizes the ENA Taxonomy REST API and Portal API to filter records by taxonomic lineage, rank, or specific Taxon IDs.

Is it possible to retrieve functional annotations?

Yes, the skill provides access to EMBL flat file formats and sequence records which include coding/non-coding regions and functional data.

How does this skill handle large genomic data downloads?

The skill provides implementation patterns for using FTP and Aspera for bulk transfers, which are recommended for files exceeding 100MB to ensure performance and reliability.

ENA Bioinformatics Database

Name: ENA Bioinformatics Database
Author: Microck

byMicrock

•

Data Science & ML

Accesses the European Nucleotide Archive (ENA) to retrieve genomic sequences, raw reads, and metadata for bioinformatics pipelines.

About

The ENA Bioinformatics Database skill enables Claude to interact seamlessly with the European Nucleotide Archive, a premier global repository for nucleotide sequence data. It provides the necessary patterns and API logic to query studies, samples, and assemblies using the ENA Portal and Browser APIs, allowing for automated data discovery and retrieval. Whether you need to download raw FASTQ reads, retrieve genome assemblies, or cross-reference taxonomic data, this skill facilitates efficient integration of biological datasets into research workflows while ensuring compliance with rate limits and data citation standards.

Key Features

Support for multiple data formats including XML, JSON, FASTA, and EMBL flat files.
Automated patterns for bulk data transfer via FTP and high-speed Aspera protocols.
Integration with ENA Taxonomy REST API for precise organism lineage lookups.
Programmatic retrieval of raw sequencing reads (FASTQ) and genome assemblies.
Advanced metadata search across ENA Studies, Samples, and Assemblies via Portal API.
81 GitHub stars

Use Cases

Batch downloading metadata and raw data for large-scale sequencing studies.
Cross-referencing ENA records with external biological databases for data annotation.
Automating the retrieval of specific nucleotide sequences for genomic analysis pipelines.

About

Key Features

Support for multiple data formats including XML, JSON, FASTA, and EMBL flat files.
Automated patterns for bulk data transfer via FTP and high-speed Aspera protocols.
Integration with ENA Taxonomy REST API for precise organism lineage lookups.
Programmatic retrieval of raw sequencing reads (FASTQ) and genome assemblies.
Advanced metadata search across ENA Studies, Samples, and Assemblies via Portal API.
81 GitHub stars

Use Cases

Batch downloading metadata and raw data for large-scale sequencing studies.
Cross-referencing ENA records with external biological databases for data annotation.
Automating the retrieval of specific nucleotide sequences for genomic analysis pipelines.