Google DeepMind built AlphaFold, AlphaMissense, AlphaGenome and Med-Gemini, the reference models for structure, variants, and medical multimodal reasoning.
AlphaFold 2 (2020) and AlphaFold 3 (2024) redefined structure prediction; Isomorphic Labs commercialises drug discovery on top. AlphaMissense (2023) scored every possible human missense variant; AlphaGenome (preview June 2025, Nature January 2026) predicts regulatory effects across 1 Mb of sequence. Google Research's Med-Gemini and C2S-Scale extend into clinical and single-cell domains.
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 and the tag ai.
Shares AI in oncology roadmap: pattern readers → foundation models → agents in the workflow and the tag ai.
Shares Cell2Sentence / C2S-Scale (Yale, Google), Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell and the tag ai.
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 and the tag ai.
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 and the tag ai.
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 and the tag ai.
Shares Virtual cell roadmap: from bulk omics to a predictive model of a cancer cell and the tag ai.
Shares Drug discovery roadmap: screening in mice → maps of dependency → designing in silico and the tag ai.
Open-source projects that this organisation maintains, 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.
DeepMind's protein structure prediction system, code and weights released; the structures fill the AlphaFold Database.
DeepMind's model of proteins with ligands, nucleic acids and modifications; code is released for non-commercial use and weights by request.
DeepMind's model predicting regulatory effects of DNA variants; API access is free for non-commercial use.
DeepMind's model and released predictions of pathogenicity for every possible human missense variant, used to triage variants of uncertain significance.