DeepCPI:A Deep Learning-based Framework for Large-scale in silico Drug Screening

Accurate identification of compound–protein interactions(CPIs)in silico may deepen our understanding of the underlying mechanisms of drug action and thus remarkably facilitate drug discovery and development.Conventional similarity-or docking-based computational methods for predicting CPIs rarely exploit latent features from currently available large-scale unlabeled compound and protein data and often limit their usage to relatively small-scale datasets.In the present study,we propose Deep CPI,a novel general and scalable computational framework that combines effective feature embedding(a technique of representation learning)with powerful deep learning methods to accurately predict CPIs at a large scale.Deep CPI automatically learns the implicit yet expressive low-dimensional features of compounds and proteins from a massive amount of unlabeled data.Evaluations of the measured CPIs in large-scale databases,such as Ch EMBL and Binding DB,as well as of the known drug–target interactions from Drug Bank,demonstrated the superior predictive performance of Deep CPI.Furthermore,several interactions among smallmolecule compounds and three G protein-coupled receptor targets(glucagon-like peptide-1 receptor,glucagon receptor,and vasoactive intestinal peptide receptor)predicted using Deep CPI were experimentally validated.The present study suggests that Deep CPI is a useful and powerful tool for drug discovery and repositioning.The source code of Deep CPI can be downloaded from https://github.com/Fangping Wan/Deep CPI.

Mechanism of actions of Oncocin, a proline- rich antimicrobial peptide, in early elongation revealed by single-molecule FRET

Dear Editor Proline-rich antimicrobial peptides （PrAMPs） are a class of antimicrobial peptides containing a high content of proline residues. PrAMPs selectively target Gram-negative bacteria through special transporters such as SmbA to enter cyto- plasm （Mattiuzzo et al., 2007）. On the other hand, PrAMPs present a low toxicity to mammalian cells, because they cannot effectively penetrate the mammalian cellular mem- brane （Hansen et al., 2012） or they are internalized through an endocytotic process to minimize interaction with cytosolic ribosomes （Tomasinsig et al., 2006）. Therefore, PrAMPs are promising candidates to treat infections and to deliver drugs （Schmidt et al., 2016）.

Simulating the ion permeation and ion selection for a eukaryotic voltage-gated sodium channel NavPaS

Dear Editor, Voltage-gated sodium （Nav） channels are membrane pro- teins that are responsible for the propagation of action potentials in mammals by mediating Na~ influx in excitable cells such as nerve and muscle. In human, Nay channels are therapeutic targets as their mutations con- tribute to many diseases. Structures of prokaryotic Nay channels, e.g., NavAb （Payandeh et al., 2011）, NavRh （Zhang et al., 2012） and NavMs （Mccusker et al., 2012）, were successively determined in the past years. Recently, the cryo-EM structures of two eukaryotic Nay channels were reported （Shen et al., 2017; Yan et al., 2017）. Nay channels contain 24 transmembrane helices.