How does the skill handle ENA API rate limits?

The skill includes best practices for staying within the 50 requests per second limit, such as implementing exponential backoff and using batch requests.

What data formats does the ENA Database skill support?

The skill supports a wide range of bioinformatics formats including FASTQ for raw reads, FASTA for sequences, BAM/CRAM for aligned reads, and XML, JSON, or TSV for metadata.

Can I use this skill to download large datasets?

Yes, while the API is used for metadata and small files, the skill provides guidance for using FTP, Aspera, and the enaBrowserTools for high-speed bulk data transfer.

Can I retrieve taxonomic lineage through this skill?

Yes, the skill provides access patterns for the ENA Taxonomy REST API to query taxonomic rank, lineage, and related organism data.

Does it support searching by metadata instead of just accessions?

Yes, it utilizes the ENA Portal API for advanced searches, allowing you to filter by data type, date range, taxonomy, or specific metadata fields.

ENA Database Integration

Name: ENA Database Integration
Author: Microck

byMicrock

•

Data Science & ML

Accesses and retrieves genomic data, sequences, and metadata from the European Nucleotide Archive via REST APIs and FTP.

The ENA Database skill empowers Claude to interact with the European Nucleotide Archive (ENA), a premier global repository for nucleotide sequence data. It provides specialized guidance for querying DNA/RNA sequences, raw reads, and genome assemblies using the ENA Portal and Browser APIs. Ideal for bioinformaticians and computational biologists, this skill facilitates the integration of genomics data into analysis pipelines, supports complex metadata searches, and provides patterns for high-speed bulk data retrieval via FTP or Aspera.

Key Features

0181 GitHub stars

02Searches studies, samples, and genome assemblies using the ENA Portal API

03Provides implementation patterns for handling rate limits and bulk data transfers

04Supports multiple formats including FASTQ, FASTA, BAM/CRAM, XML, and JSON

05Queries taxonomic information including lineage and rank via the Taxonomy API

06Retrieves DNA/RNA sequences and raw sequencing reads by accession number

Use Cases

01Searching for and downloading all genome assemblies associated with a specific organism

02Automating the retrieval of FASTQ files for specific study accessions in genomics pipelines

03Performing cross-reference searches to link ENA records with external biological databases

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microck/ordinary-claude-skills ena-database

For use in Claude.ai and ChatGPT

Download Skill