{"entity":{"id":"ai-drug-design","kind":"technology","name":"AI-driven drug & target discovery","aka":[],"tldr":"Using machine learning to pick targets, design molecules and antibodies, and predict which ADC will work.","summary":"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.","status":"phase-2","asOf":"2026-09-04","wikipedia":"https://en.wikipedia.org/wiki/Drug_design","links":[{"label":"Wikipedia","url":"https://en.wikipedia.org/wiki/Drug_design"}],"tags":["frontier"],"related":[],"cancers":[],"sections":["ai-computation","drug-discovery"],"technologies":[],"targets":[],"drugs":[],"companies":["genesis-molecular-ai","iambic-therapeutics","algen-biotechnologies","aqemia","bighat-biosciences","blank-bio","certis-oncology-solutions","cytoreason","evaxion","harmonic-discovery","iktos","immunai","lila-sciences","nested-therapeutics","nimbus-therapeutics","relay-therapeutics","resistancebio","reverie-labs","serinus-biosciences","turbine","valo-health"],"institutions":[],"pathways":[],"terms":[],"trials":[],"people":[],"bottlenecks":[],"keyPapers":[],"journals":[],"dependsOn":[],"notes":[],"principle":"Deep learning over sequence, structure, and omics; active learning with wet-lab loops.","strengths":["Speed of design cycles","Novel target hypotheses"],"limitations":["Clinical validation lag","Biology, not chemistry, is the usual failure point"]},"route":"/technologies/ai-drug-design/","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/"}],"company":[{"id":"algen-biotechnologies","kind":"company","name":"Algen Biotechnologies","route":"/companies/algen-biotechnologies/"},{"id":"aqemia","kind":"company","name":"Aqemia","route":"/companies/aqemia/"},{"id":"arpeggio-bio","kind":"company","name":"Arpeggio Bio","route":"/companies/arpeggio-bio/"},{"id":"bighat-biosciences","kind":"company","name":"BigHat Biosciences","route":"/companies/bighat-biosciences/"},{"id":"blank-bio","kind":"company","name":"Blank Bio","route":"/companies/blank-bio/"},{"id":"certis-oncology-solutions","kind":"company","name":"Certis Oncology Solutions","route":"/companies/certis-oncology-solutions/"},{"id":"compugen","kind":"company","name":"Compugen","route":"/companies/compugen/"},{"id":"cradle-bio","kind":"company","name":"Cradle","route":"/companies/cradle-bio/"},{"id":"cytoreason","kind":"company","name":"CytoReason","route":"/companies/cytoreason/"},{"id":"evaxion","kind":"company","name":"Evaxion","route":"/companies/evaxion/"},{"id":"exscientia","kind":"company","name":"Exscientia","route":"/companies/exscientia/"},{"id":"generate-biomedicines","kind":"company","name":"Generate:Biomedicines","route":"/companies/generate-biomedicines/"},{"id":"genesis-molecular-ai","kind":"company","name":"Genesis Molecular AI (formerly Genesis Therapeutics)","route":"/companies/genesis-molecular-ai/"},{"id":"google-health","kind":"company","name":"Google (Health, DeepMind, Verily)","route":"/companies/google-health/"},{"id":"harmonic-discovery","kind":"company","name":"Harmonic Discovery","route":"/companies/harmonic-discovery/"},{"id":"iambic-therapeutics","kind":"company","name":"Iambic Therapeutics","route":"/companies/iambic-therapeutics/"},{"id":"iktos","kind":"company","name":"Iktos","route":"/companies/iktos/"},{"id":"immunai","kind":"company","name":"Immunai","route":"/companies/immunai/"},{"id":"insilico-medicine","kind":"company","name":"Insilico Medicine","route":"/companies/insilico-medicine/"},{"id":"isomorphic-labs","kind":"company","name":"Isomorphic Labs","route":"/companies/isomorphic-labs/"},{"id":"latent-labs","kind":"company","name":"Latent Labs","route":"/companies/latent-labs/"},{"id":"lila-sciences","kind":"company","name":"Lila Sciences","route":"/companies/lila-sciences/"},{"id":"nested-therapeutics","kind":"company","name":"Nested Therapeutics","route":"/companies/nested-therapeutics/"},{"id":"nimbus-therapeutics","kind":"company","name":"Nimbus Therapeutics","route":"/companies/nimbus-therapeutics/"},{"id":"noetik","kind":"company","name":"Noetik","route":"/companies/noetik/"},{"id":"pathos-ai","kind":"company","name":"Pathos AI","route":"/companies/pathos-ai/"},{"id":"profluent-bio","kind":"company","name":"Profluent","route":"/companies/profluent-bio/"},{"id":"recursion","kind":"company","name":"Recursion Pharmaceuticals","route":"/companies/recursion/"},{"id":"relay-therapeutics","kind":"company","name":"Relay Therapeutics","route":"/companies/relay-therapeutics/"},{"id":"resistancebio","kind":"company","name":"ResistanceBio (Viosera Therapeutics)","route":"/companies/resistancebio/"},{"id":"reverie-labs","kind":"company","name":"Reverie Labs","route":"/companies/reverie-labs/"},{"id":"serinus-biosciences","kind":"company","name":"Serinus Biosciences","route":"/companies/serinus-biosciences/"},{"id":"syngene","kind":"company","name":"Syngene International","route":"/companies/syngene/"},{"id":"treeline-biosciences","kind":"company","name":"Treeline Biosciences","route":"/companies/treeline-biosciences/"},{"id":"turbine","kind":"company","name":"Turbine","route":"/companies/turbine/"},{"id":"valo-health","kind":"company","name":"Valo Health","route":"/companies/valo-health/"}],"roadmap":[{"id":"adc-generations","kind":"roadmap","name":"ADC roadmap: from Mylotarg to bispecific and dual-payload ADCs","route":"/roadmaps/adc-generations/"},{"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/"}],"collection":[{"id":"open-targets","kind":"collection","name":"Open Targets Platform","route":"/collections/open-targets/"}],"technology":[{"id":"adc-payload-neutralizer","kind":"technology","name":"ADC payload neutralisers","route":"/technologies/adc-payload-neutralizer/"},{"id":"ai-compute-platforms","kind":"technology","name":"AI compute and model platforms for oncology","route":"/technologies/ai-compute-platforms/"},{"id":"alphafold3","kind":"technology","name":"AlphaFold 3","route":"/technologies/alphafold3/"},{"id":"boltz","kind":"technology","name":"Boltz-1 / Boltz-2 (MIT, open)","route":"/technologies/boltz/"},{"id":"chai-1","kind":"technology","name":"Chai-1 / Chai-2","route":"/technologies/chai-1/"},{"id":"chemistry42","kind":"technology","name":"Chemistry42 and Pharma.AI (Insilico)","route":"/technologies/chemistry42/"},{"id":"de-novo-protein-design","kind":"technology","name":"De novo designed protein binders","route":"/technologies/de-novo-protein-design/"},{"id":"esm3","kind":"technology","name":"ESM3 (EvolutionaryScale)","route":"/technologies/esm3/"},{"id":"high-throughput-screening-libraries","kind":"technology","name":"High-throughput screening and DNA-encoded libraries","route":"/technologies/high-throughput-screening-libraries/"},{"id":"molecular-glue-platforms","kind":"technology","name":"Molecular glue discovery platforms","route":"/technologies/molecular-glue-platforms/"},{"id":"phenom-2","kind":"technology","name":"Phenom-2 and Recursion OS","route":"/technologies/phenom-2/"},{"id":"rfdiffusion","kind":"technology","name":"RFdiffusion / RFdiffusion2 and ProteinMPNN (Baker Lab)","route":"/technologies/rfdiffusion/"},{"id":"structural-biology-infrastructure","kind":"technology","name":"Structural biology infrastructure (cryo-EM, synchrotrons, AlphaFold)","route":"/technologies/structural-biology-infrastructure/"},{"id":"drug-repurposing","kind":"technology","name":"Systematic drug repurposing","route":"/technologies/drug-repurposing/"}],"person":[{"id":"giulio-draetta","kind":"person","name":"Giulio Draetta","route":"/people/giulio-draetta/"},{"id":"paul-workman","kind":"person","name":"Paul Workman","route":"/people/paul-workman/"},{"id":"regina-barzilay","kind":"person","name":"Regina Barzilay","route":"/people/regina-barzilay/"}],"bottleneck":[{"id":"b-ai-validation","kind":"bottleneck","name":"AI that is built but not validated or deployed","route":"/bottlenecks/b-ai-validation/"},{"id":"b-generic-repurposing","kind":"bottleneck","name":"No incentive to repurpose cheap drugs","route":"/bottlenecks/b-generic-repurposing/"},{"id":"b-undruggable-targets","kind":"bottleneck","name":"The undruggable drivers","route":"/bottlenecks/b-undruggable-targets/"},{"id":"b-translational-valley","kind":"bottleneck","name":"The valley of death between lab and product","route":"/bottlenecks/b-translational-valley/"},{"id":"b-combination-space","kind":"bottleneck","name":"Too many combinations to test","route":"/bottlenecks/b-combination-space/"}],"idea":[{"id":"idea-bio1-virtual-cell-perturbation","kind":"idea","name":"A virtual cancer cell that predicts what a drug will do before you test it","route":"/ideas/idea-bio1-virtual-cell-perturbation/"},{"id":"idea-bio1-ai-binders-disordered-regions","kind":"idea","name":"AI-designed proteins that grip the floppy parts of cancer drivers","route":"/ideas/idea-bio1-ai-binders-disordered-regions/"},{"id":"idea-moon-open-degrader-consortium","kind":"idea","name":"An open degrader consortium against every undruggable driver transcription factor","route":"/ideas/idea-moon-open-degrader-consortium/"},{"id":"idea-tr2-synergy-ranking-engine","kind":"idea","name":"An open engine that ranks every drug pair by predicted synergy before anyone runs a trial","route":"/ideas/idea-tr2-synergy-ranking-engine/"},{"id":"idea-data-open-cell-foundation-model","kind":"idea","name":"An open foundation model of the cancer cell trained on perturbation data","route":"/ideas/idea-data-open-cell-foundation-model/"},{"id":"idea-bio1-covalent-ligandability-atlas","kind":"idea","name":"An open map of which cancer proteins any drug can stick to","route":"/ideas/idea-bio1-covalent-ligandability-atlas/"},{"id":"idea-fund-precompetitive-undruggable-consortium","kind":"idea","name":"An open-science consortium on the undruggable drivers, open until a candidate","route":"/ideas/idea-fund-precompetitive-undruggable-consortium/"},{"id":"idea-moon-automated-combination-discovery","kind":"idea","name":"Automated combination discovery: patient-sample screens feeding Bayesian platform trials","route":"/ideas/idea-moon-automated-combination-discovery/"},{"id":"idea-bio2-brain-penetrant-glue-degraders","kind":"idea","name":"Design protein degraders small enough to get into the brain","route":"/ideas/idea-bio2-brain-penetrant-glue-degraders/"},{"id":"idea-bio1-p53-mutant-reactivator-expansion","kind":"idea","name":"Extend p53 reactivation beyond the Y220C mutation","route":"/ideas/idea-bio1-p53-mutant-reactivator-expansion/"},{"id":"idea-bio1-evolution-forecasting","kind":"idea","name":"Forecast the next resistance mutation like the weather","route":"/ideas/idea-bio1-evolution-forecasting/"},{"id":"idea-bio1-in-silico-trials-dose","kind":"idea","name":"In silico trials to choose the dose before the first patient","route":"/ideas/idea-bio1-in-silico-trials-dose/"},{"id":"idea-tr2-qsp-combo-dosing","kind":"idea","name":"Mechanistic computer models to pick combination doses before dosing patients","route":"/ideas/idea-tr2-qsp-combo-dosing/"},{"id":"idea-bio1-myc-max-molecular-glue","kind":"idea","name":"Molecular glues that break the MYC-MAX partnership","route":"/ideas/idea-bio1-myc-max-molecular-glue/"},{"id":"idea-bio1-model-predictivity-benchmark","kind":"idea","name":"Score every model system on how well it predicted real trial results","route":"/ideas/idea-bio1-model-predictivity-benchmark/"},{"id":"idea-moon-self-driving-cancer-labs","kind":"idea","name":"Self-driving laboratories that run the cancer biology hypothesis loop autonomously","route":"/ideas/idea-moon-self-driving-cancer-labs/"}],"paper":[{"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/"}],"institution":[{"id":"cancer-center-at-illinois","kind":"institution","name":"Cancer Center at Illinois","route":"/institutions/cancer-center-at-illinois/"},{"id":"cnio","kind":"institution","name":"Centro Nacional de Investigaciones Oncológicas (CNIO)","route":"/institutions/cnio/"},{"id":"embl-ebi","kind":"institution","name":"EMBL's European Bioinformatics Institute","route":"/institutions/embl-ebi/"},{"id":"frederick-national-lab","kind":"institution","name":"Frederick National Laboratory for Cancer Research","route":"/institutions/frederick-national-lab/"},{"id":"newcastle-cancer-centre","kind":"institution","name":"Newcastle Cancer Centre / Northern Centre for Cancer Care","route":"/institutions/newcastle-cancer-centre/"}]}}