Role of Artificial Intelligence in Modern Drug Discovery: A Literature Overview

Bringing a new drug to today’s market is extremely costly and time-consuming. To accelerate this process, the pharmaceutical industry has turned to Artificial Intelligence (AI). In addition to AI, machine learning (ML), deep learning (DL), and big data analytics have emerged as transformative tools that have improved the efficacy and accuracy. AI helps in the analysis of molecular structures and in the evaluation of in vivo and in vitro characteristics without putting human or animal lives at risk. AI applications in drug development include peptide synthesis, ligand-based virtual screening, toxicity prediction, drug repositioning, pharmacophore modeling, quantitative structure–activity relationships, polypharmacology, and drug release monitoring. Although AI involvement and application in drug discovery are still in their early stages, it has the potential to revolutionize this field entirely. In recent years, AI has enabled researchers to solve complex problems such as designing drugs with low toxicity, identifying targets for difficult diseases, and developing drugs with improved efficacy.However, AI implementation in drug discovery still faces notable gaps and limitations, including data quality issues, poor interpretability of AI-generated models, ethical considerations, and the need to validate AI-generated predictions through experimental studies. The findings reveal that AI, Machine learning, and Deep learning have advanced multiple stages of drug discovery by improving target identification, toxicity prediction, and molecular design, and have the potential to increase the success rate of drug discovery. In this paper, we discuss conventional methods of drug development and then examine how artificial intelligence and deep learning are changing the process of drug discovery.