Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery (preprint)

Properties of molecules are indicative of their functions and thus are useful in many applications. With the advances of deep learning methods, computational approaches for predicting molecular properties are gaining increasing momentum. However, there lacks customized and advanced methods and comprehensive tools for this task currently. Here we develop a suite of comprehensive machine learning methods and tools spanning different computational models, molecular representations, and loss functions for molecular property prediction and drug discovery. Specifically, we represent molecules as both graphs and sequences. Built on these representations, we develop novel deep models for learning from molecular graphs and sequences. In order to learn effectively from highly imbalanced datasets, we develop advanced loss functions that optimize areas under precision-recall curves. Altogether, our work not only serves as a comprehensive tool, but also contributes towards developing novel and advanced graph and sequence learning methodologies. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that our methods achieve consistent improvements over prior methods. In particular, our methods achieve #1 ranking in terms of both ROC-AUC and PRC-AUC on the AI Cures Open Challenge for drug discovery related to COVID-19. Our software is released as part of the MoleculeX library under AdvProp.

The focus and timing of COVID-19 pandemic control measures under healthcare resource constraints (preprint)

Generalizing COVID-19 control strategies in one community to others is confounded by community's unique demographic and socioeconomic attributes. Here we propose a tailored dynamic model accounting for community-specific transmission controls and medical resource availability. We trained the model using data from Wuhan and applied it to other countries. We show that isolating suspected cases is most effective in reducing transmission rate if the intervention starts early. Having more hospital beds provides leverage that diminishes with delayed intervention onset. The importance of transmission control in turn increases by 65% with a 7-day delay. Furthermore, prolonging outbreak duration by applying an intermediate, rather than strict, transmission control would not prevent hospital overload regardless of bed capacity, and would likely result in a high ratio (21% ~ 84%) of the population being infected but not treated. The model could help different countries design control policies and gauge the severity of suppression failure.