Terminal
Terminal/Skill
Finds proteins with similar 3D shapes by searching a structure file (.pdb, .cif) against databases such as PDB and AlphaFold through Foldseek.
By Google
Works with
npx skills add google-deepmind/science-skills --skill foldseek-structural-searchuv: Read the uv skill and follow its Setup instructions to ensure
uv is installed and on PATH.Submit a user-provided 3D protein structure file (.cif, .mmcif, or .pdb)
to the Foldseek web server API to find structurally similar proteins. Report the
top structural hits, interpret key alignment metrics, summarize the inferred
protein functions, save the Markdown-formatted table to a .md file, and save
the full detailed results to a local JSON file.
.pdb, .cif, or .mmcif file
path..md file for
your immediate summary. The JSON is saved purely for subsequent, specialized
tool use..cif, .mmcif, or .pdb file in their workspace.
afdb50, afdb-swissprot, pdb100, BFVD,
mgnify_esm30, cath50, gmgcl_id, bfmd, afdb-proteome.proteinA_foldseek_results.json and proteinA_foldseek_results.md)..md file:
uv run scripts/search.py <path-to-file> -o <generated-filename.json> > <generated-filename.md>uv run scripts/search.py <path-to-file> -o <generated-filename.json> --databases <db1,db2,db3> > <generated-filename.md>.md file..md file carefully
to view the Markdown table.Target ID column for the reported matches.
.json and .md)
and their locations so they can be seamlessly used in subsequent analysis
steps.and ask them to verify the file path.