Objective
The elucidation of a compound's Mechanism of Action (MoA) is a challenging task in the drug discovery process, but it is important in order to rationalise phenotypic findings and to anticipate potential side-effects. Drugs can be classified based on their biological activity and assigned a MoA label using biological activity, gene expression, and cell viability data. AI can be leveraged to predict molecular mechanism underlying phenotypic screens and follow-on assays.
Outcome
With mechanism of action prediction solution, small molecule phenotypic screens can be processed through various workflows. The solution will generate a detailed reporting dashboard including target/pathway predictions and accelerated hit prioritization.
Business Value
Innovating novel drugs, and accelerated drug discovery process. The mechanism of action prediction solution can also be leveraged in in drug repurposing/ drug repositioning as it can facilitate the discovery of new mechanisms of action for old drugs as well as new classes of medicines. It enables virtual drug screening, toxicity prediction and polypharmacology.
H2O's AI and Data Approaches
Driverless AI AutoML, and H2O.ai Wave. The data science approaches include deep learning - feed forward dense NN.