Objective To analyze the injury mechanism and distribution of the motor vehicle engine shake shaft caused injuries (MVESSCI) in North Henan province. Methods A follow up was done on 520 patients with the motor vehicle engine shaft injuries treated in our hospital from January 1998 to May 2002. The epidemiological features were analyzed concerning gender, age, injury time and injury sites. Results There were 300 males and 220 females (age range of 9-53 years, mean 31 years) with ratio 1.36 ∶1 of male to female. The MVESSCI were dominated by Colles fractures and distal fractures of ulna and radius, accounting for 73.8% (384/520). The traffic accidents occurred most in May, June, September and October, which accounted for 85.0% (442/520). Conclusions (1) The vehicle engine shake shaft causes the injuries mainly at the distal part of the right forearm, mainly the Colles fracture and the distal fractures of ulna and radius. (2) The injury is mainly due to improper operation in busy farming seasons. (3) The countermeasures to reduce wounds and injuries are to pay much more attention to prevention, strengthen the safety awareness of individuals, improve the structures of motor vehicles and avoid improper manipulation of the vehicles by children.

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 com-pound and protein data and often limit their usage to relatively small-scale datasets. In the present study, we propose DeepCPI, 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. DeepCPI automatically learns the implicit yet expressive low-dimensional features of compounds and proteins from a massive amount of unla-beled data. Evaluations of the measured CPIs in large-scale databases, such as ChEMBL and Bind-ingDB, as well as of the known drug-target interactions from DrugBank, demonstrated the superior predictive performance of DeepCPI. Furthermore, several interactions among small-molecule compounds and three G protein-coupled receptor targets (glucagon-like peptide-1 recep-tor, glucagon receptor, and vasoactive intestinal peptide receptor) predicted using DeepCPI were experimentally validated. The present study suggests that DeepCPI is a useful and powerful tool for drug discovery and repositioning. The source code of DeepCPI can be downloaded from https://github.com/FangpingWan/DeepCPI.