Machine Learning Methods in Drug Discovery.

Lauv Patel,Shanzhi Wang,Xiuzhen Huang,Tripti Shukla,David W Ussery

doi:10.3390/molecules25225277

Abstract

The advancements of information technology and related processing techniques have created a fertile base for progress in many scientific fields and industries. In the fields of drug discovery and development, machine learning techniques have been used for the development of novel drug candidates. The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs. The generation and incorporation of big data, through technologies such as high-throughput screening and high through-put computational analysis of databases used for both lead and target discovery, has increased the reliability of the machine learning and deep learning incorporated techniques. The use of these virtual screening and encompassing online information has also been highlighted in developing lead synthesis pathways. In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed. The applications that produce promising results and methods will be reviewed.

Highlights

Advancements in computational science have accelerated drug discovery and development.Artificial intelligence (AI) is widely used in both industry and academia
These methods are based on separate applications in target discovery, lead compound discovery, synthesis, protein-ligand interactions, etc
One such example is Machine learning (ML) incorporated into target discovery, based heavily on the refinement and search of existing omics and medical data

Summary

Introduction

Advancements in computational science have accelerated drug discovery and development. Wei et al utilized a combinational technique of NB and support vector machine algorithms to predict possible compounds that could be active against targets of human immunodeficiency virus type-1 and the hepatitis C virus generated from multiple QSAR models [50]. Their model utilized NB as a classifier technique paired alongside two different descriptor systems, one being extended-connectivity fingerprint-6. SVM classification has a subset binary class prediction that could differentiate between active from inactive molecules For drug discovery, it could rank compounds from different databases based on the probability of being active for any computational screening. Drugs were discovered to be dual inhibitors against both angiotensin-converting enzyme I and neutral endopeptidases

Limitations

Findings

Conclusions