A weighted bilinear neural collaborative filtering approach for drug repositioning

Abstract

Drug repositioning is an efficient and promising strategy for traditional drug discovery and development. Many research efforts are focused on utilizing deep-learning approaches based on a heterogeneous network for modeling complex drug–disease associations. Similar to traditional latent factor models, which directly factorize drug–disease associations, they assume the neighbors are independent of each other in the network and thus tend to be ineffective to capture localized information. In this study, we propose a novel neighborhood and neighborhood interaction-based neural collaborative filtering approach (called DRWBNCF) to infer novel potential drugs for diseases. Specifically, we first construct three networks, including the known drug–disease association network, the drug–drug similarity and disease–disease similarity networks (using the nearest neighbors). To take the advantage of localized information in the three networks, we then design an integration component by proposing a new weighted bilinear graph convolution operation to integrate the information of the known drug–disease association, the drug’s and disease’s neighborhood and neighborhood interactions into a unified representation. Lastly, we introduce a prediction component, which utilizes the multi-layer perceptron optimized by the α-balanced focal loss function and graph regularization to model the complex drug–disease associations. Benchmarking comparisons on three datasets verified the effectiveness of DRWBNCF for drug repositioning. Importantly, the unknown drug–disease associations predicted by DRWBNCF were validated against clinical trials and three authoritative databases and we listed several new DRWBNCF-predicted potential drugs for breast cancer (e.g. valrubicin and teniposide) and small cell lung cancer (e.g. valrubicin and cytarabine).

Identification of Novel Immune Ferropotosis-Related Genes Associated With Clinical and Prognostic Features in Gastric Cancer

“…Our results have a satisfactory correlation with clinical results, which indicates that IFRSig is a good predictor of risk factors. It is of note that this model might be further improved by more advanced machine learning algorithms as illustrated in other similar medical studies ( 26 – 28 ).…”

A Machine Learning Method to Trace Cancer Primary Lesion Using Microarray-Based Gene Expression Data

“…For instance, further research should consider integrating multiple types of biomarkers to improve inference accuracies, such as circulating tumor DNA ( 43 ) and H&E images ( 44 ). It is also favorable to adopt more advanced machine learning algorithms for prediction or to use algorithms that integrate learning more efficiently ( 45 ). In a recent breakthrough, Liu et al.…”

Prediction of Tumor Mutation Load in Colorectal Cancer Histopathological Images Based on Deep Learning

“…In recent years, machine learning methods have been widely used in biomedical research like drug repositioning ( 37 , 38 ) and single-cell analysis ( 39 ). Among all of these fields, deep learning showed advantages over many previous related technologies ( 40 , 41 ). For example, in lung cancer research, deep learning methods can be used to identify biomarker genes on pathological images ( 42 , 43 ).…”