Chai-1
Commercial-friendly AlphaFold3-class folding, MSA optional
Chai-1 is a multi-modal foundation model that predicts proteins, nucleic acids, small molecules, ions and their complexes from sequence inputs. It achieves accuracy comparable to AlphaFold3 while running single-sequence inference without MSAs when desired. Licensed to allow commercial use, making it a workhorse for industrial structure prediction.
Chai-1 is being onboarded — request access and be first in line.
At a glance
- Input
- Sequences and ligands (FASTA, SDF)
- Output
- Predicted complex (PDB)
- Developed by
- Chai Discovery
- Published
- Chai Discovery, 2024 · 2024
#co-folding#commercial-friendly#msa-free
Related tools
More methods in Structure Prediction & Folding
