Loading
Open-source structure models that match AlphaFold 3, with Boltz-2 also predicting how strongly a drug binds.
Boltz is an open-source family of diffusion-based structure models from MIT that reproduces AlphaFold 3-level accuracy for proteins, nucleic acids and small molecules. Boltz-1 (2024) was released under the permissive MIT licence, giving academic and commercial groups a freely usable alternative to closed models. Boltz-2 (2025), developed with Recursion, added an affinity head that predicts how strongly a small molecule binds, approaching the accuracy of physics-based free energy perturbation (FEP) at a fraction of the compute cost, which matters for ranking candidate cancer drugs. Affinity accuracy varies by target class, so predictions still need experimental confirmation for a new protein family. For a newcomer: Boltz is the free model that matches AlphaFold 3 and can also estimate how tightly a drug will bind.
Diffusion structure model with affinity head.
Query for this technology: (TITLE:"Boltz-1 / Boltz-2" OR ABSTRACT:"Boltz-1 / Boltz-2" OR TITLE:"MIT, open" OR ABSTRACT:"MIT, open") AND (cancer OR tumor OR tumour OR oncology OR carcinoma OR lymphoma OR leukemia OR leukaemia OR myeloma OR sarcoma OR melanoma OR glioma). Results are unfiltered search hits about Boltz-1 / Boltz-2 (MIT, open), not a curated reading list.
Shares Recursion Pharmaceuticals, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tags foundation-model, structure.
Shares Recursion Pharmaceuticals, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI-driven drug & target discovery.
Shares the tags foundation-model, structure.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag foundation-model.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow, AI-driven drug & target discovery and the tag foundation-model.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag foundation-model.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell, Drug discovery roadmap: screening in mice → maps of dependency → designing in silico, AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag foundation-model.
Open-source projects that implement or serve this technology, from OnCo's own catalogue: licence and last activity as the repository reported them on the day of the fetch. Listing is not endorsement; check the licence before reuse and the validation before clinical use.
An open biomolecular structure and affinity prediction model from MIT and Recursion, released under MIT with weights.