Use of machine learning approaches for novel drug discovery

abstract

Introduction: The use of computational tools in the early stages of drug development has increased in recent decades. Machine learning (ML) approaches have been of special interest, since they can be applied in several steps of the drug discovery methodology, such as prediction of target structure, prediction of biological activity of new ligands through model construction, discovery or optimization of hits, and construction of models that predict the pharmacokinetic and toxicological (ADMET) profile of compounds.

Areas covered: This article presents an overview on some applications of ML techniques in drug design. These techniques can be employed in ligand-based drug design (LBDD) and structure-based drug design (SBDD) studies, such as similarity searches, construction of classification and/or prediction models of biological activity, prediction of secondary structures and binding sites docking and virtual screening.

Expert opinion: Successful cases have been reported in the literature, demonstrating the efficiency of ML techniques combined with traditional approaches to study medicinal chemistry problems. Some ML techniques used in drug design are: support vector machine, random forest, decision trees and artificial neural networks. Currently, an important application of ML techniques is related to the calculation of scoring functions used in docking and virtual screening assays from a consensus, combining traditional and ML techniques in order to improve the prediction of binding sites and docking solutions.

Keywords:

• Machine Learning
• Drug Design
• LBDD
• SBDD

Article highlights

• ML techniques can be important tools in LBDD and SBDD studies.

• The most employed ML techniques in drug design projects are artificial neural networks or ANN (self-organizing maps and multilayer perceptron), SVM, DT, RF, and KNN.

• The main recent advances in ML techniques applied in drug discovery comprise the combination of some algorithms and/or techniques, for example, application of ANN to learn the best way to integrate information from KNN models and consensus approaches.

• One of the main advantages of ML techniques in drug discovery is related to the validation procedures, which could ensure robustness and predictive power of the constructed models.

• Applications of ML techniques in drug design involve similarity search, construction/application of classification and/or prediction of biological activity from multivariate models, prediction of secondary structure and binding site, docking, and VS.

Financial and Competing Interests Disclosure

The authors would like to thank the FAPESP (The São Paulo Research Foundation), the Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) and the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) (Brazilian Research Founding Agencies) for their financial support. The authors have no other relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript apart from those disclosed.