Abstract
Computational methods for predicting drug-target interactions have become important in drug research because they can help to reduce the time, cost, and failure rates for developing new drugs. Recently, with the accumulation of drug-related data sets related to drug side effects and pharmacological data, it has became possible to predict potential drug-target interactions. In this study, we focus on drug-drug interactions (DDI), their adverse effects () and pharmacological information (), and investigate the relationship among chemical structures, side effects, and DDIs from several data sources. In this study, data from the STITCH database, from drugs.com, and drug-target pairs from ChEMBL and SIDER were first collected. Then, by applying two machine learning approaches, a support vector machine (SVM) and a kernel-based L1-norm regularized logistic regression (KL1LR), we showed that DDI is a promising feature in predicting drug-target interactions. Next, the accuracies of predicting drug-target interactions using DDI were compared to those obtained using the chemical structure and side effects based on the SVM and KL1LR approaches, showing that DDI was the data source contributing the most for predicting drug-target interactions.
Highlights
Computational approaches are promising tools in drug research since they can help reduce the time, costs, and failure rates for developing new drugs
Since the study by Yamanishi et al [18] confirmed that pharmacological spaces are useful in predicting drug-target interactions, we further investigated this concept with respect to drug-drug interactions (DDIs); i.e, how the positive or negative association of two drugs can be used to infer the drug’s target proteins
DDIPharm was extracted from STITCH; in STITCH, interactions between chemicals were collected from various resources including similar activity profiles in the anticancer drug screen data of 60 human tumor cell lines (NCI60), pharmacological actions obtained from Medical Subject Headings (MeSH), literature by using natural language processing, and pathway and experimental databases [4]
Summary
Computational approaches are promising tools in drug research since they can help reduce the time, costs, and failure rates for developing new drugs. We compared the contribution of DDI to both the chemical structure and side effect similarities based on the SVM and KL1LR approaches, showing that DDI was the data source contributing the most for predicting drug-target interactions. We integrated the chemical structure, side effect, and DDI data sets to predict drug-target interactions. DDIPharm was extracted from STITCH; in STITCH, interactions between chemicals were collected from various resources including similar activity profiles in the anticancer drug screen data of 60 human tumor cell lines (NCI60), pharmacological actions obtained from Medical Subject Headings (MeSH), literature by using natural language processing, and pathway and experimental databases [4]. The two superscripts in the last column represent the following: 1 is # of drugs with matched identifiers from ChEMBL drugs with target interactions and SIDER side effects, and 2 is # of drugs having DDI in 1. doi:10.1371/journal.pone.0080129.t001 were used to estimate the prediction accuracy of the proposed methods and contributions of drug-related data sources for inferring drug-target interactions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
