No abstract

No abstract

No abstract

Motivation Deep neural network (DNN) algorithms were utilized in predicting various biomedical phenotypes recently, and demonstrated very good prediction performances without selecting features. This study proposed a hypothesis that the DNN models may be further improved by feature selection algorithms. Results A comprehensive comparative study was carried out by evaluating 11 feature selection algorithms on three conventional DNN algorithms, i.e. convolution neural network (CNN), deep belief network (DBN) and recurrent neural network (RNN), and three recent DNNs, i.e. MobilenetV2, ShufflenetV2 and Squeezenet. Five binary classification methylomic datasets were chosen to calculate the prediction performances of CNN/DBN/RNN models using feature selected by the 11 feature selection algorithms. Seventeen binary classification transcriptome and two multi-class transcriptome datasets were also utilized to evaluate how the hypothesis may generalize to different data types. The experimental data supported our hypothesis that feature selection algorithms may improve DNN models, and the DBN models using features selected by SVM-RFE usually achieved the best prediction accuracies on the five methylomic datasets. Availability and implementation All the algorithms were implemented and tested under the programming environment Python version 3.6.6. Supplementary information Supplementary data are available at Bioinformatics online.

Development of cost-effective and high-efficiency electrocatalysts for the hydrogen evolution reaction (HER) is still of great significance for industrial clean hydrogen fuel production. Herein, a novel heterostructured VN/Mo2C nanoparticle is synthesized by a facile and one-step pyrolysis protocol. When applied for the HER, the optimized VN/Mo2C catalyst exhibited quite low overpotentials (alkaline medium: 45 mV, acid medium: 140 mV, and neutral medium: 180 mV) for driving the current density of 10 mA cm–2, obviously superior to the isolated vanadium nitride (VN) and Mo2C counterparts, and remarkable catalytic durability for at least 100 h. Such an outstanding electrocatalytic HER performance is primarily ascribed to the increased catalytically active sites, enhanced electronic interaction effects, as well as the improved electrical conductivity over the heterostructured VN/Mo2C nanoparticles. This study provides a new method for the design of HER electrocatalysts with high efficiency and stability.