Drug Target Group Prediction with Multiple Drug Networks

Abstract

Background: Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments. Methods: In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model. Results and Conclusion: Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

Identifying Cell-Type Specific Genes and Expression Rules Based on Single-Cell Transcriptomic Atlas Data

“…Step five was adopted to construct a series of feature subsets. On each feature subset, one RF classifier was trained and evaluated on the samples consisting of the features from this feature subset by using 10-fold cross-validation (Kohavi, 1995;Che et al, 2019;Cui and Chen, 2019;Zhou et al, 2019). The performance corresponding to the different numbers of features is given in Supplementary Table S3.…”

Identifying Methylation Pattern and Genes Associated with Breast Cancer Subtypes

“…In this study, we used multi-class classifier to discriminate samples from four breast cancer subtypes. We evaluated the trained multi-class classifiers by using a 10-fold cross-validation [39,40,116,117,118]. For the predicted results yielded by 10-fold cross-validation, the sensitivity and specificity for each class were calculated.…”

Identifying the Immunological Gene Signatures of Immune Cell Subtypes

“…Classifiers on samples with each feature subset were learned, which were further tested with 10-fold cross-validation [32][33][34][35][36][37]. Then, the feature interval containing the feature subset with the highest performance was determined and denoted as [min, max].…”