Structure Prediction
Today, we announce our partnership with Chai Discovery to provide Chai-1r for unrestricted commercial use. Chai-1 matches or beats AlphaFold3 in many different benchmarks. Most notably, Chai-1 shows tremendous success in protein complexes, protein-ligand complexes, covalent modifications, and nucleic acids. Not mention antibodies and immune proteins.
Webserver: https://app.tamarind.bio/chai
API: https://app.tamarind.bio/api-docs
Chai-1r excels in antibody-antigen interaction prediction with mean DockQ % of
- Chai-1r (+4 epitope residues): 43.7
- Chai-1: 35.6
- Boltz (an AlphaFold3 reproduction from MIT & Genesis): 26.4
- AlphaFold2: 20.6
On an architecture note, Chai-1 can produce high quality structure prediction without needing multiple sequence alignments. Notably, it matches AF2-Multimer performance for protein-protein complexes without needing MSAs.
Chai-1 Residue Distance Restrictions & Epitope Specification
Chai-1's capabilities extend beyond its base sequence modeling. Users can specify epitopes by identifying maximum distances between two residues in separate chains, for example those retrieved from experimental methods. The authors find that this can improve docking prediction by double digit percentages. Most notably, they find that this epitope limitation doubles antibody-antigen structure prediction accuracy.
Get In Touch
Tamarind provides a simple, high through graphical interface, and programmatic API. Alongside these, we support chaining Chai-1 with dozens of others protein design tools. Get in touch to hear more on how we can support your AlphaFold3 usage in a scalable, confidential cloud with enterprise-grade security.