Overfit deep neural network for predicting drug-target interactions.

Drug-target interactions (DTIs) prediction is an important step in drug discovery. As traditional biological experiments or high-throughput screening are high cost and time-consuming, many deep learning models have been developed. Overfitting must be avoided when training deep learning models. We propose a simple framework, called OverfitDTI, for DTI prediction. In OverfitDTI, a deep neural network (DNN) model is overfit to sufficiently learn the features of the chemical space of drugs and the biological space of targets. The weights of trained DNN model form an implicit representation of the nonlinear relationship between drugs and targets. Performance of OverfitDTI on three public datasets showed that the overfit DNN models fit the nonlinear relationship with high accuracy. We identified fifteen compounds that interacted with TEK, a receptor tyrosine kinase contributing to vascular homeostasis, and the predicted AT9283 and dorsomorphin were experimentally demonstrated as inhibitors of TEK in human umbilical vein endothelial cells (HUVECs).

SERCA2a: a key protein in the Ca2+ cycle of the heart failure.

Calcium ion (Ca2+) cycle plays a crucial role in the contraction and relaxation of cardiomyocytes. The sarcoplasmic reticulum (SR) acts as an organelle for storing Ca2+, which mediated the release and re-uptake of Ca2+ during contraction and relaxation. Disorders of SR function lead to the dysfunction of Ca2+ cycle and myocardial cell function. The sarcoplasmic/endoplasmic reticulum Ca2+ ATPase 2a (SERCA2a) acts as a subtype of SERCA expressed in the heart, which mediates the contraction of cardiomyocytes and Ca2+ in the cytoplasm to re-enter into the SR. The rate of uptake of Ca2+ by the SR determines the rate of myocardial relaxation. The regulation of SERCA2a activity controls the contractility and relaxation of the heart, affecting cardiac function. The expression and activity of SERCA2a are reduced in failing hearts. Gene therapy by increasing the expression of SERCA2a in the heart has been proven effective. In addition, SERCA2a is regulated by a variety of factors, including transmembrane micropeptides, protein kinases, and post-translational modifications (PTMs). In this review, we discuss the regulatory factors of SERCA2a and provide new insights into future treatments and the direction of heart failure research. In addition, gene therapy for SERCA2a has recently emerged as therapeutic option and hence will be discussed in this review.