molclaw-protein-sequence-retrieve

Retrieve protein sequences and metadata from gene names or UniProt identifiers.

28|2|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/InternScience/MolClaw --skill molclaw-protein-sequence-retrieve
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: molclaw-protein-sequence-retrieve
Source: https://github.com/InternScience/MolClaw/tree/main/skills/L1_tools/molclaw-protein-sequence-retrieve
Command: npx skills add https://github.com/InternScience/MolClaw --skill molclaw-protein-sequence-retrieve

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Resolve ambiguous gene names or identifiers and quickly obtain authoritative protein sequence data and metadata for downstream analysis and agent workflows.

Core Features & Use Cases

  • Identifier resolution: Accepts a gene name or UniProt ID and optional organism to locate the correct protein entry.
  • Structured metadata output: Returns uniprot_id, gene_name, protein_name, organism, amino acid sequence, length, and status/message fields for robust integration.
  • Integration-ready: Designed to be called by agents or pipelines that need programmatic access to protein sequences for evaluation, screening, or optimization tasks.
  • Use case: Given the input "PDE5A" for Homo sapiens, obtain the UniProt accession, full amino acid sequence, and length for use in docking or sequence-based feature extraction.

Quick Start

Request the sequence and metadata for gene name TP53 in Homo sapiens.

Frequently Asked Questions about molclaw-protein-sequence-retrieve

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

FAQPage Schema
How do I retrieve a protein sequence using a gene name?

To retrieve a protein sequence using a gene name, provide the gene name and an optional organism to resolve the correct UniProt entry. The Skill returns structured metadata including the uniprot_id, full amino acid sequence, protein_name, and length.

What metadata is returned when fetching a protein sequence from UniProt?

Fetching a protein sequence from UniProt returns structured metadata fields including uniprot_id, gene_name, protein_name, organism, amino acid sequence, length, and status/message fields for error handling.

Can I get protein sequences across different species with a UniProt ID?

Yes, you can retrieve protein sequences across different species by providing a UniProt identifier or gene name with an optional organism parameter. This resolves the correct protein entry for lookups across species.

How do I resolve ambiguous gene names to find the correct protein entry?

To resolve ambiguous gene names and find the correct protein entry, supply the gene name along with an optional organism parameter. This locates the authoritative protein sequence data and resolves the UniProt accession for downstream analysis.

Can I integrate protein sequence retrieval into a bioinformatics pipeline?

Yes, you can integrate protein sequence retrieval into a bioinformatics pipeline or agent workflows. It provides programmatic access to structured sequence metadata, including status and message fields, for robust automated evaluation tasks.

What should I do if my protein sequence lookup returns an error?

If your protein sequence lookup returns an error, check the status and message fields in the structured metadata output. These fields provide error handling details to help diagnose issues with the gene name or UniProt identifier resolution.