Computational Drug Discovery and Design

Chapter 2

Prediction of Human Drug Targets and Their Interactions

Using Machine Learning Methods: Current and Future

Perspectives

Abhigyan Nath, Priyanka Kumari, and Radha Chaube

Abstract

Identification of drug targets and drug target interactions are important steps in the drug-discovery
pipeline. Successful computational prediction methods can reduce the cost and time demanded by the
experimental methods. Knowledge of putative drug targets and their interactions can be very useful for
drug repurposing. Supervised machine learning methods have been very useful in drug target prediction
and in prediction of drug target interactions. Here, we describe the details for developing prediction models
using supervised learning techniques for human drug target prediction and their interactions.

Key wordsDrug target identification, Drug target interaction, Feature selection, Machine learning

1 Introduction

One of the salient steps in the drug-discovery pipeline is the identi-

fication of drug targets or druggable proteins. Druggable proteins

can be defined as those proteins which can be regulated by interac-

tion with a drug and whose interaction can be exploited to produce

a therapeutic effect. Majority of druggable targets belongs to the

G-protein coupled receptors, ion-channels, and kinases [1]. Tradi-

tionally microarrays [2] including both nucleic acid microarrays [3]

and protein microarrays [4, 5] are used for identification and vali-

dation of drug targets. Also one of the alternative suitable methods

is high throughput NMR-based screening for drug target interac-

tion [6]. Expression profiling, biochemical and cell based assays,

and cell and model organism based genetics which involves pertur-

bation of gene function are the three major methods for drug target

discovery [7]. Novel drug targets can be identified broadly under

three major levels—physiological, mechanistic, and genetic

levels [8].

Mohini Gore and Umesh B. Jagtap (eds.),Computational Drug Discovery and Design, Methods in Molecular Biology, vol. 1762,
https://doi.org/10.1007/978-1-4939-7756-7_2,©Springer Science+Business Media, LLC, part of Springer Nature 2018

21