protein-sequence-similarity-search
Agent skill fromgoogle-deepmind/science-skills
Searches for homologous protein sequences using MMseqs2 (fast, default) or BLAST (comprehensive, fallback). Trigger this whenever the user provides a protein sequence or FASTA file and asks to find homologues, sequence matches, or wants to infer protein function based on sequence similarity, but not when the user wants to infer protein function based on structural similarity.
How to install protein-sequence-similarity-search
install protein-sequence-similarity-search
# install the science-skills pack with the skills CLI
npx skills add google-deepmind/science-skills# or add only this skill to Claude Code: copy the folder
skills/protein_sequence_similarity_search/
# into
~/.claude/skills/protein_sequence_similarity_search/ (all projects)
.claude/skills/protein_sequence_similarity_search/ (one project)
1## Prerequisites231. **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure4 `uv` is installed and on PATH.52. **User Notification**: If6 .licenses/protein_sequence_similarity_search_LICENSE.txt does not already7 exist in the workspace root directory then (1) prominently notify the user8 to check the terms at https://www.ebi.ac.uk/jdispatcher/sss/ncbiblast and9 https://colabfold.com, then (2) create the file recording the notification10 text and timestamp.113. **`.env` file**: Make sure the `.env` file exists in your home directory.12 Create one if it does not exist.134. **`USER_EMAIL`** (optional but recommended): Recommended by the EBI for14 BLAST job tracking, but the skill works without it. You **MUST** use the15 safe credentials protocol in the `credentials` skill to check for and16 request this credential if this skill looks relevant to the user's request.1718## Goal1920Take a user-provided amino acid sequence (or a path to a `.fasta` file), search21for sequence homologues using the fastest available method, generate a22Markdown-formatted table of the top hits, interpret key alignment metrics,23summarize the inferred protein functions, and save results locally for future24programmatic analysis.2526## Core Rules2728- **Strict Validation**: For BLAST, only use database codes listed in the29 table below.30- **No Hallucinations**: If a script throws an error or returns no hits,31…
Excerpt shown under the repository's Apache-2.0 license.
