Page 35 - AIH-2-2

Artificial Intelligence in Health

PERSPECTIVE ARTICLE
Revolutionizing new drug discovery: Harnessing

AI and machine learning to overcome traditional
challenges and accelerate targeted therapies

Satinder Singh *, Vyas Shingatgeri , and Pratima Srivastava 1
2
1
1 Drug Metabolism and Pharmacokinetics, Aragen Life Sciences Limited, Hyderabad, Telangana, India
2 Dean, School of Biosciences, Apeejay Stya University, Gurugram, Haryana, India

Abstract
Designing highly targeted, selective drugs with desirable absorption, distribution,
metabolism, excretion, and pharmacokinetic (PK) profiles; single-digit nanomolar
efficacy; and a wider therapeutic index are challenging. In the traditional drug
discovery process, researchers screen thousands of chemical compounds during
pre-clinical development, progressing through hit identification, lead optimization,
and candidate selection to shortlist – potential clinical candidates with favorable
PK profiles, high tolerability, and manageable toxicity. The selected candidate must
demonstrate sufficient efficacy in treating the target disease in humans. Despite these
efforts, the success rate of the pre-clinical candidate to sail through Phase I, Phase II,
*Corresponding author: and Phase III in clinical trials remains exceedingly low. Supported by powerful data-
Satinder Singh driven tools, artificial intelligence (AI) has transformed this traditional drug discovery
(satinder.singh@aragen.com) process by enabling the analysis of large quantities of omics, phenotypic, and
Citation: Singh S, Shingatgeri V, expression data to identify the biological mechanisms of pathological conditions
Srivastava P. Revolutionizing new and in turn identify druggable proteins or genes. The generative AI-powered toolbox
drug discovery: Harnessing AI and
machine learning to overcome creates novel compounds from scratch, assists scientists in optimizing druggability
traditional challenges and attributes, and bridges the differences between animal and human physiology and
accelerate targeted therapies. Artif anatomy to predict potential toxicity in humans with high accuracy. This review
Intell Health. 2025;2(2):29-40.
doi: 10.36922/aih.4423 discusses the bottlenecks in the traditional drug discovery approach, the impact of
AI and machine learning (ML) in drug discovery, and potential challenges associated
Received: August 2, 2024
with AI/ML adoption.
1st revised: September 10, 2024
2nd revised: September 23, 2024 Keywords: Novel chemical entity; Absorption, distribution, metabolism, and excretion;
Accepted: October 8, 2024 Pharmacokinetics; Artificial intelligence; Machine learning; Deep learning; Generative AI;
Drug discovery and development
Published online: November 6, 2024
Copyright: © 2024 Author(s).
This is an Open-Access article
distributed under the terms of the
Creative Commons Attribution 1. Introduction
License, permitting distribution,
and reproduction in any medium, Artificial intelligence (AI) has revolutionized drug discovery and development by
provided the original work is identifying novel targets, predicting drug–target interactions with high accuracy,
properly cited. designing compounds from scratch, facilitating in silico pharmacokinetic (PK) and
Publisher’s Note: AccScience pharmacodynamic analyses, and optimizing drug formulations for the intended route
Publishing remains neutral with of administration. AI-assisted prediction of the physiochemical properties, bioactivity,
regard to jurisdictional claims in
published maps and institutional binding affinity, and multitarget effects of new chemical entities (NCEs) is greatly
affiliations. benefiting drug discovery companies, enabling them to anticipate druggability attributes

Volume 2 Issue 2 (2025) 29 doi: 10.36922/aih.4423