AI-driven drug & target discovery
Using machine learning to pick targets, design molecules and antibodies, and predict which ADC will work.
AlphaFold-enabled structure prediction, generative small-molecule design (Insilico, Recursion/Exscientia, Isomorphic), de novo antibody design (Absci, Generate, Nabla), and multi-omic target identification (DualityBio's DB-1329 CDCP1 ADC was AI-nominated). First AI-designed oncology molecules are in phase 2; none approved yet.
How it works
Deep learning over sequence, structure, and omics; active learning with wet-lab loops.
- Speed of design cycles
- Novel target hypotheses
- Clinical validation lag
- Biology, not chemistry, is the usual failure point
Latest papers
topQuery for this technology: (TITLE:"AI drug discovery" OR ABSTRACT:"AI drug discovery" OR TITLE:"generative model" OR ABSTRACT:"generative model" OR TITLE:"de novo design" OR ABSTRACT:"de novo design") 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 AI-driven drug & target discovery, not a curated reading list.