MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning
This tool assists drug developers in designing more efficacious drugs, but it is incremental as it integrates existing deep learning models into an interactive interface.
The authors tackled the problem of designing effective drugs by developing MolDesigner, a human-in-the-loop web interface that uses deep learning models to predict drug efficacy indices, enabling real-time interactive editing with less than a second latency.
The efficacy of a drug depends on its binding affinity to the therapeutic target and pharmacokinetics. Deep learning (DL) has demonstrated remarkable progress in predicting drug efficacy. We develop MolDesigner, a human-in-the-loop web user-interface (UI), to assist drug developers leverage DL predictions to design more effective drugs. A developer can draw a drug molecule in the interface. In the backend, more than 17 state-of-the-art DL models generate predictions on important indices that are crucial for a drug's efficacy. Based on these predictions, drug developers can edit the drug molecule and reiterate until satisfaction. MolDesigner can make predictions in real-time with a latency of less than a second.