Classification and its applications for drug-target interaction identification

TL;DR

This paper reviews classification methods and explores their application in drug-target interaction prediction, a key challenge in drug discovery, highlighting the importance of supervised learning in biomedical research.

Contribution

It provides a comprehensive review of classification techniques and their specific application to drug-target interaction prediction, addressing a critical problem in drug discovery.

Findings

Classification methods are effective in predicting drug-target interactions.

Application of supervised learning improves accuracy in drug discovery tasks.

The paper highlights challenges and future directions in drug-target prediction.

Abstract

Classification is one of the most popular and widely used supervised learning tasks, which categorizes objects into predefined classes based on known knowledge. Classification has been an important research topic in machine learning and data mining. Different classification methods have been proposed and applied to deal with various real-world problems. Unlike unsupervised learning such as clustering, a classifier is typically trained with labeled data before being used to make prediction, and usually achieves higher accuracy than unsupervised one. In this paper, we first define classification and then review several representative methods. After that, we study in details the application of classification to a critical problem in drug discovery, i.e., drug-target prediction, due to the challenges in predicting possible interactions between drugs and targets.