A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing

Thai-Hoang Pham, Yue Qiu, Jucheng Zeng, Lei Xie, Ping Zhang

Abstract: In drug discovery and repurposing, systematic analysis of genome-wide gene expression of chemical perturbations on human cell lines is a useful approach, but is limited due to a relatively low experimental throughput. Computational, deep learning methods can help. In this work a graph neural network called Deep Chemical Expression is developed that can predict chemical-induced gene expression profiles. It is applied to identify drug repurposing candidates for COVID-19 treatments.