adaptyvbio/protein-design-skills/foldseek

Claude Code and agent skill by adaptyvbio/protein-design-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Structure similarity search with Foldseek. Use this skill when: (1) Finding similar structures in PDB/AFDB databases, (2) Structural homology search, (3) Database queries by 3D structure, (4) Finding remote homologs not detected by sequence, (5) Clustering structures by similarity. For sequence similarity, use uniprot BLAST. For structure prediction, use chai or boltz.

Install

npx vskill@latest install adaptyvbio/protein-design-skills/foldseek

SKILL.md

Foldseek Structure Search

Prerequisites

RequirementMinimumRecommended
Python3.8+3.10
RAM8GB16GB
Disk10GB50GB (for local databases)

How to run

Note: Foldseek can run locally or via web server. No GPU required.

Option 1: Web Server (Quick; rate-limited, use sparingly)
bash
# Upload structure to web server
curl -X POST "https://search.foldseek.com/api/ticket" \
-F "q=@query.pdb" \
-F "database[]=afdb50" \
-F "database[]=pdb100"
Option 2: Local installation
bash
# Install Foldseek
conda install -c conda-forge -c bioconda foldseek
# Search PDB
foldseek easy-search query.pdb /path/to/pdb100 results.m8 tmp/
# Search AlphaFold DB
foldseek easy-search query.pdb /path/to/afdb50 results.m8 tmp/
Option 3: Python API
python
import subprocess
import pandas as pd
def foldseek_search(query_pdb, database, output="results.m8"):
"""Run Foldseek search."""
subprocess.run([
"foldseek", "easy-search",
query_pdb, database, output, "tmp/",
"--format-output", "query,target,pident,alnlen,evalue,bits"
])
return pd.read_csv(output, sep="\t",
names=["query", "target", "pident", "alnlen", "evalue", "bits"])

Key parameters

ParameterDefaultDescription
--min-seq-id0.0Minimum sequence identity
-e0.001E-value threshold
--alignment-type20=3Di, 1=TM, 2=3Di+AA
--max-seqs1000Max hits to pass through prefilter; reducing this affects sensitivity

Databases

DatabaseDescriptionSize
pdb100PDB chains~340K structures
afdb50AlphaFold DB clustered at 50% sequence identity~53M structures
swissprotSwissProt structures~540K structures
cath50CATH domains~50K domains

Output format

# results.m8 (tabular)
query target pident alnlen evalue bits
query 1abc_A 85.2 120 1e-45 180.5
query 2def_B 72.1 115 1e-32 145.2

Sample output

Successful run
$ foldseek easy-search query.pdb pdb100 results.m8 tmp/
# results.m8 columns: query target pident alnlen mismatch gapopen qstart qend tstart tend evalue bits
query 1abc_A 85.2 120 ... 1e-45 180.5
query 2def_B 72.1 115 ... 1e-32 145.2

Hit identities and E-values above are placeholders; foldseek does not print the [INFO] lines shown by some other tools.

Decision tree

Should I use Foldseek?
│
├─ What are you searching?
│ ├─ By 3D structure → Foldseek ✓
│ ├─ By sequence → Use BLAST (uniprot skill)
│ └─ Both → Run both, compare results
│
└─ What do you need?
├─ Find structural homologs → Foldseek ✓
├─ Remote homolog detection → Foldseek ✓
├─ Structural clustering → Foldseek ✓
└─ Functional annotation → Cross-reference with UniProt

Common use cases

Find similar designs
bash
# Compare your design to PDB
foldseek easy-search design.pdb pdb100 similar_natural.m8 tmp/
Novelty check
bash
# Ensure design is novel (low similarity to known)
foldseek easy-search design.pdb afdb50 novelty.m8 tmp/
# Novel if: top hit identity < 30%
Scaffold search
bash
# Find scaffolds for motif grafting
foldseek easy-search motif.pdb pdb100 scaffolds.m8 tmp/ \
--min-seq-id 0.0 -e 10

Verify

bash
wc -l results.m8 # Number of hits

Troubleshooting

No hits: Lower e-value threshold, try larger database Too many hits: Increase min-seq-id threshold Slow search: Use smaller database

Error interpretation
ErrorCauseFix
Database not foundWrong pathCheck database location
Invalid PDBMalformed structureValidate PDB format
Out of memoryLarge databaseUse more RAM or web server

Next: Download hits with pdb skill → use for scaffold design.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
117
Repository forks
13
7-day trend score
24

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 24 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/adaptyvbio/protein-design-skills/foldseek/badge)](https://verified-skill.com/skills/adaptyvbio/protein-design-skills/foldseek)

Something wrong with this skill or its page? Tell us.