Year: 2026 | Month: June | Volume: 13 | Issue: 6 | Pages: 93-106
DOI: https://doi.org/10.52403/ijrr.20260610
Artificial Intelligence and Large Language Models in Drug Discovery and Pharmacogenomics: A Comprehensive Pharmacological Review of AlphaFold, Generative AI for De Novo Design, Clinical Decision Support, and the Translational Pipeline
Adiba Begum1, R. L. Manisha2, Muvvala Sudhakar3
1Student, Department of Pharmacology, Malla Reddy College of Pharmacy, Maisammaguda, Dhulapally, Secunderabad–500100, Telangana, India.
2Head of Department, Department of Pharmacology, Malla Reddy College of Pharmacy, Maisammaguda, Dhulapally, Secunderabad–500100, Telangana, India.
3Principal, Malla Reddy College of Pharmacy, Maisammaguda, Dhulapally, Secunderabad–500100, Telangana, India.
Corresponding Author: Dr. R. L. Manisha
ABSTRACT
Artificial intelligence (AI) — particularly deep learning, generative models, and large language models (LLMs) — has emerged as a transformative force across pharmacology, drug discovery, clinical pharmacy, and pharmacogenomics. The 2020 release of AlphaFold by DeepMind, recognized with the 2024 Nobel Prize in Chemistry (jointly to Demis Hassabis, John Jumper, and David Baker), produced near-experimental-accuracy three-dimensional structures for nearly all known proteins, fundamentally transforming structural biology and structure-based drug design. The 2022–2025 wave of generative AI and large language models (GPT-4, Claude, Gemini, Llama) has demonstrated capabilities relevant to medical decision support, clinical documentation, drug information, pharmacovigilance, and patient education. AI-native biotechnology companies including Insilico Medicine, Recursion Pharmaceuticals, BenevolentAI, Atomwise, Exscientia, Isomorphic Labs, and Iambic Therapeutics have advanced AI-discovered drug candidates into clinical trials, with INS018_055 (Insilico, idiopathic pulmonary fibrosis) progressing to Phase 2 as a notable early example. The pharmacogenomics field is increasingly leveraging machine learning for genome-wide variant interpretation, polygenic risk scoring, drug-gene interaction prediction, and dose individualization. This review provides a comprehensive analysis of AI applications across the pharmaceutical value chain, including the technical foundations, target identification and validation, hit identification and lead optimization, ADMET prediction, AI-driven clinical trial design and patient stratification, post-market pharmacovigilance, LLM-based clinical decision support, the evolving regulatory landscape (FDA, EMA, and CDSCO frameworks), pharmacogenomic applications, the Indian AI and biotechnology context, and future directions for pharmacology education and translational research.
Keywords: Artificial intelligence; Large language models; AlphaFold; Drug discovery; Pharmacogenomics; Generative AI; Deep learning; Transformer; Clinical decision support; Foundation models; Precision medicine.
[PDF Full Text]