Abstract
Predicting drug-target interactions is important for the development of novel drugs and the repositioning of drugs. To predict such interactions, there are a number of methods based on drug and target protein similarity. Although these methods, such as the bipartite local model (BLM), show promise, they often categorize unknown interactions as negative interaction. Therefore, these methods are not ideal for finding potential drug-target interactions that have not yet been validated as positive interactions. Thus, here we propose a method that integrates machine learning techniques, such as self-training support vector machine (SVM) and BLM, to develop a self-training bipartite local model (SELF-BLM) that facilitates the identification of potential interactions. The method first categorizes unlabeled interactions and negative interactions among unknown interactions using a clustering method. Then, using the BLM method and self-training SVM, the unlabeled interactions are self-trained and final local classification models are constructed. When applied to four classes of proteins that include enzymes, G-protein coupled receptors (GPCRs), ion channels, and nuclear receptors, SELF-BLM showed the best performance for predicting not only known interactions but also potential interactions in three protein classes compare to other related studies. The implemented software and supporting data are available at https://github.com/GIST-CSBL/SELF-BLM.
Highlights
In recent years, interest in identifying drug-target interactions has dramatically increased for drug development and for understanding the mechanisms of action of various drugs
Our model showed good performance based on the area under the ROC curve (AUC) and the area under the precision-recall curve (AUPR) values of the updated dataset
We proposed a modified bipartite local model (BLM), termed SELF-BLM, to accurately predict potential drug-target interactions
Summary
Interest in identifying drug-target interactions has dramatically increased for drug development and for understanding the mechanisms of action of various drugs. Various in silico screening methods have been developed to predict drug-target interactions Among these methods, machine learning-based approaches such as bipartite local model (BLM) and MI-DRAGON which utilize support vector machine (SVM), random forest and artificial neural network (ANN) as part of their prediction model are widely used because of their sufficient performance and the ability to use large-scale drug-target data [4,5,6,7,8,9]. To train the model, we used a previous dataset for humans involving enzymes, G-protein coupled receptors (GPCRs), ion channels, and nuclear receptors from previous studies [23] We constructed another drug-target interaction data set that contained recently updated interaction information for performance validation. Our proposed method found the highest number of potential drug-target interactions compared to other related methods in most cases
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have