RepoAI
Browse MCPs

Protein Sequence Similarity Search

88TrustedShips scripts

Homologue identification using high-speed sequence alignment tools and databases.

What it does

Protein Sequence Similarity Search allows your assistant to identify protein homologues by querying specialized biological databases. Instead of manual lookups, the assistant executes automated searches to find sequences that share evolutionary origins with your provided amino acid string or FASTA file.

The skill processes your data using either rapid, default algorithmic searches or more extensive BLAST queries based on your needs. It generates structured summaries that highlight alignment metrics and potential functions, creating local files that persist for future investigation.

When it earns its place

Reach for it when…

This tool is appropriate when you need to identify related proteins for a given sequence to determine conservation, evolutionary relationships, or potential functional annotations. It is intended for initial screening and automated data collection where speed and database cross-referencing are required for primary sequence analysis.

Look elsewhere when…

Avoid this skill if you need to perform structural comparisons, as it relies strictly on primary amino acid sequence data rather than 3D protein conformation. It is not suitable for de novo protein folding predictions or when your analysis requires deep integration with structural bioinformatics pipelines.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • find similar proteins to this sequence
  • run a BLAST search on this FASTA file
  • find evolutionary homologues for my protein
  • can you identify the function of this sequence via alignment

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/protein_sequence_similarity_search ~/.claude/skills/protein-sequence-similarity-search

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/protein_sequence_similarity_search .claude/skills/protein-sequence-similarity-search

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

Protein Sequence Similarity Search changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →