Deep learning accelerates discovery of novel modulators targeting cardiac calcium transport

Abstract

Sarcoplasmic reticulum calcium ATPase (SERCA) is a transmembrane pump critical for calcium transport from the cytosol to the lumen of the sarcoplasmic reticulum in cardiac cells. Deregulation and deactivation of the SERCA pump is a hallmark of heart failure; thus, the development of SERCA activating drugs has emerged as a promising approach for the treatment for this condition. We used a virtual screening strategy developed by our group that incorporates machine learning classifiers and deep learning generators for data augmentation to design SERCA modulators that stimulate intracellular Ca2+ transport in cardiac cells.