Objective To find out the difference between fetal malnutrition (FM) and small for gestational age (SGA) and its clinical significance. Methods Clinical nutritional status was assessed in 548 singleton term babies. Nine superficial, rapidly detected signs of malnutrition were taken for the clinical assessment nutritional status score (CANSCORE). FM was diagnosed if the total score was less than or equal to 24. Results Among 40 SGA, 21(52.5%) were FM, the other 19 (47.5%) were not FM with scores more than 24, whereas 13(2.8%) out of 508 AGA (appropriate for gestational age) were FM. Conclusion SGA and FM are not synonymous and FM can be rapidly determined by the CANSCORE. Biochemical and ultrasonic studies should be done in high risk preg nancy during second trimester to discover FM and intervene by nutritional treatment to prevent the infants with FM.

The therapy of acute promyelocytic leukemia (APL) with all-trans retinoic acid and arsenic trioxide was first discovered in China, which made a great contribution worldwide to APL treatment. However, foreign guidelines did not include the Chinese chemotherapy regimens, and our regimens were inconsistent with foreign guidelines. Therefore, it is necessary to interpret the home and international guidelines and to explore standard treatment of APL by analyzing APL guidelines of the China, Europe and the United States. Owing to several discrepancies between domestic and foreign APL guidelines, unifying the APL's diagnosis and treatment standard is desperately needed at present according to the evidence-based medicine. It is hoped that Chinese chemotherapy regimens will be more acceptable to other countries of the world, and would benefit the diagnosis and treatment of human APL.

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.