Artificial Intelligence in Drug Discovery and Development: From Target Identification to Clinical Trials

Abstract

ABSTRACT Background: Drug discovery and development are complex, costly, and failure-prone processes that require the integration of biological, chemical, pharmacological, toxicological, and clinical evidence. Artificial intelligence (AI), including machine learning (ML), deep learning, natural language processing, generative models, and foundation models, is increasingly being applied across this pipeline. Objective : This review examines the role of AI from target identification and validation through hit discovery, lead optimization, preclinical evaluation, clinical trial design and conduct, and regulatory oversight. Methods : A narrative review was prepared using peer-reviewed research, major reviews, clinical trial reports, and regulatory guidance identified through biomedical literature resources and targeted searches of journal and official agency websites. Emphasis was placed on evidence published through 30 October 2026. No formal systematic screening or meta-analysis was performed. Results: AI can integrate multi-omics and literature data for target prioritization; support structure prediction, virtual screening, molecular generation, and multi-parameter optimization; and assist toxicity prediction, trial recruitment, protocol feasibility, monitoring, and data analysis. AlphaFold 3 has expanded structural prediction to biomolecular interactions. A notable clinical example is rentosertib (formerly ISM001-055), a generative-AI-discovered TNIK inhibitor evaluated in a randomized phase 2a trial for idiopathic pulmonary fibrosis. The trial provides an important proof-of-concept but does not establish that AI alone caused clinical success or that the candidate is an approved medicine. Conclusion: AI is becoming an enabling technology throughout pharmaceutical research and development, but it does not eliminate the need for biological reasoning, medicinal chemistry, experimental testing, rigorous clinical trials, or regulatory evaluation. Its value depends on high-quality data, prospective validation, transparent context of use, and multidisciplinary human oversight.

Keywords

Authors & affiliations

Cite this article

Krina Sunil Patel. Artificial Intelligence in Drug Discovery and Development: From Target Identification to Clinical Trials. ClinSphere Journals. 2026;undefined(undefined). https://doi.org/10.5281/zenodo.23802240

1. Scannell JW, Blanckley A, Boldon H, Warrington B. Diagnosing the decline in pharmaceutical R&D efficiency. Nat Rev Drug Discov. 2012;11(3):191-200. doi:10.1038/nrd3681.
2. Zhang K, Yang X, Wang Y, Yu Y, Huang N, Li G, et al. Artificial intelligence in drug development. Nat Med. 2025;31:45-59. doi:10.1038/s41591-024-03434-4.
3. Hasselgren C, Oprea TI. Artificial intelligence for drug discovery: are we there yet? Annu Rev Pharmacol Toxicol. 2024;64:527-550. doi:10.1146/annurev-pharmtox-040323-040828.
4. Gangwal A, Ansari A, Ahmad S, Azad AK, Kumarasamy S, Subramaniyan V, et al. Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities. Front Pharmacol. 2024;15:1331062. doi:10.3389/fphar.2024.1331062.
5. Pun FW, Podolskiy D, Izumchenko E, Mortlock A, Oprea TI, Scheibye-Knudsen M, et al. Target identification and assessment in the era of AI. Nat Rev Drug Discov. 2026;25:534-552. doi:10.1038/s41573-026-01412-8.