{"entity":{"id":"alphafold3","kind":"technology","name":"AlphaFold 3","aka":[],"tldr":"Predicts the 3D shape of proteins together with DNA, RNA, small molecules and antibodies, the starting point for much modern drug design.","summary":"AlphaFold 3, from Google DeepMind and Isomorphic Labs, predicts the three-dimensional structure of proteins together with DNA, RNA, small molecules, ions and antibodies by combining a Pairformer trunk with a diffusion module that generates all atom positions jointly. Described in Nature 2024, it extends AlphaFold 2 from single proteins to complexes and ligands, which is why it has become the starting point for much modern structure-based drug design, including work on cancer targets. The weights were released for academic use late in 2024, while Isomorphic uses successor models commercially. Its predictions are static structures, and accuracy for antibody-antigen complexes is still limited, so experimental validation remains essential for binder design. For a newcomer: AlphaFold 3 draws a picture of how a drug or antibody might fit onto its target before anyone makes it.","status":"established","asOf":"2026-09-08","links":[{"label":"Nature 2024","url":"https://doi.org/10.1038/s41586-024-07487-w"}],"tags":["foundation-model","structure"],"related":[],"cancers":[],"sections":["drug-discovery","ai-computation"],"technologies":["ai-drug-design"],"targets":[],"drugs":[],"companies":["google-deepmind","isomorphic-labs"],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":["paper-abramson-nature"],"journals":[],"dependsOn":[],"notes":[],"principle":"AlphaFold 3 combines a Pairformer with a diffusion module over all biomolecular types.","strengths":["Complexes and ligands"],"limitations":["Static structures; antibody-antigen accuracy still limited"],"since":2024},"route":"/technologies/alphafold3/","neighbours":{"section":[{"id":"ai-computation","kind":"section","name":"AI & Computation","route":"/fronts/ai-computation/"},{"id":"drug-discovery","kind":"section","name":"Drug Discovery Platforms","route":"/fronts/drug-discovery/"}],"technology":[{"id":"ai-drug-design","kind":"technology","name":"AI-driven drug & target discovery","route":"/technologies/ai-drug-design/"}],"company":[{"id":"google-deepmind","kind":"company","name":"Google DeepMind (and Google Research)","route":"/companies/google-deepmind/"},{"id":"isomorphic-labs","kind":"company","name":"Isomorphic Labs","route":"/companies/isomorphic-labs/"}],"paper":[{"id":"paper-abramson-nature","kind":"paper","name":"Accurate structure prediction of biomolecular interactions with AlphaFold 3","route":"/key-papers/paper-abramson-nature/"},{"id":"paper-alphafold2-jumper-nature-2021","kind":"paper","name":"AlphaFold 2: predicting protein structures to near-experimental accuracy","route":"/key-papers/paper-alphafold2-jumper-nature-2021/"}],"roadmap":[{"id":"ai-oncology-roadmap","kind":"roadmap","name":"AI in oncology roadmap: pattern readers → foundation models → agents in the workflow","route":"/roadmaps/ai-oncology-roadmap/"},{"id":"drug-discovery-roadmap","kind":"roadmap","name":"Drug discovery roadmap: screening in mice → maps of dependency → designing in silico","route":"/roadmaps/drug-discovery-roadmap/"}]}}