Virtual screening beyond the DMTA cycle: using massively-multitask regression models (MMRMs) to predict off-target activity, Mechanisms-of-action, polypharmacology and drug repurposing
26 Sep 2024
Target Identification
By transfer learning between 10,000s of assays, millions of data points, and 10 millions of experimental measurements, massively multitask modeling makes predictions comparable to 4-concentration experimental biochemical and cellular EC50s.
Predictions for millions of compounds on up to 10,000 assays provides unique information.
Predictions for millions of compounds on up to 10,000 assays provides unique information.
- What are the strengths and weaknesses of various MMRM algorithms?
- What are successful applications in drug discovery with examples?
- Are there other approaches, experimental or computational, besides MMRMs?
Industry Expert
