A molecular video-derived foundation model for scientific drug discovery

Accurate molecular representation of compounds is a fundamental challenge for prediction of drug targets and molecular properties. In this study, we present a molecular video-based foundation model, named VideoMol, pretrained on 120 million frames of 2 million unlabeled drug-like and bioactive molecules. VideoMol renders each molecule as a video with 60 frames and designs three self-supervised learning strategies on molecular videos to capture molecular representation. We show high performance of VideoMol in predicting molecular targets and prototyping drug discovery benchmark datasets. VideoMol achieves high accuracy in identifying antiviral molecules against various disease-specific drug targets (i.e., EBV and EPD). Progress is noted toward better binding affinity than existing molecular docking references in understanding the three-dimensional structure of molecules. We further illustrate interpretability of VideoMol using key molecular substructures.