Extend cell line space to position payloads and ADCs
Select cancer sub-indications or molecular biomarkers predictive of payload, payload combination or ADC sensitivity
Rank drug-drug combinations to design dual-payload ADCs
Reveal ADC specific biological insights to address mechanism driving resistance
6 ADCs representing 5 antigen targets
100+ small molecules, including 20 payloads
KO alterations across 5000+ genes
Virtual PDX and PDO library of -400 samples
Wet lab perturbation data generation
Wet lab validation of key hypotheses
Why trust us?
Accurately predict drug responses using limited data
Compound responses with known mechanisms can be predicted at high accuracy, across 1,400+ cancer cell lines (0.75 Pearson correlation of unseen cell line responses).
Match novel payloads with responder indications
Turbine correctly predicted the sensitivity order of subtypes for microtubule payloads and produced closely aligned rankings for TOP1 inhibitors, potentially guiding trial strategy and avoiding dead-end subtypes.
Design dual-payload ADCs rationally, not by trial-and-error
Turbine predicts GDSC2 Topo1i – PARPi synergy from training only on monotherapy data.
Identify predictive biomarkers early and link payload response to mechanistic drivers of resistance
Turbine’s in silico pharmacology and biomarker screens suggested viable patient selection hypothesis for Topo1 ADCs in NSCLC (to be validated preclinically).