PoseBusters
Physics-aware eval of docking/co-folding poses — 19 checks catching chemically impossible outputs.
Composite score: 97.0
Rubric (1–5 per criterion)
rigor
5/5
coverage
4/5
maintenance
5/5
adoption
5/5
quality
5/5
accessibility
5/5
industry_relevance
5/5
Metadata
Stages
Hit ID
Modalities
small-moleculeprotein-general
Task types
pose-validation
License
BSD-3-Clause
First release
2023-08
Last updated
2025-02
Flags
none
Size & scope
- complexes: 428
- checks_per_pose: 19
Primary paper
Title
PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences
Authors
Buttenschoen M, Morris GM, Deane CM
Year
2024
DOI / arXiv
Citations
360
Links
- Official site: https://posebusters.readthedocs.io/
- GitHub: https://github.com/maabuu/posebusters
- Leaderboard: https://github.com/maabuu/posebusters
Hosted by (initiatives)
Experts (primary authors / maintainers)
Groups (host labs / companies / consortia)
Related benchmarks
Notes (honest caveats)
Exposed major failure modes in AlphaFold-Multimer/DiffDock/RFAA. Default pharma filter.