COMPUTATIONAL DRUG DESIGN-IN SILICO REVOLUTION REVIEWD THE EVOLUTION,INNOVATION,AND INFLUENCE ON MODERN DRUG DISCOVERY

In-silico drug design evolved from a supportive technique into a core component of pharmaceutical research. This review provided a comprehensive overview of the computational drug discovery landscape, emphasizing innovations in methodologies, AI integration, and software capabilities. Breakthroughs such as AlphaFold 3, 3DMolFormer, and DiffDock significantly advanced protein structure prediction, docking accuracy, and generative molecule design. Artificial intelligence and machine learning enabled large-scale virtual screening, denovo compound generation, and predictive ADMET modelling with improved precision and efficiency. Widely adopted tools—both commercial (e.g., Schrödinger, MOE, Optibrium) and open-source (e.g., AutoDock, PyRx, DataWarrior)—integrated molecular docking, pharmacophore modelling, QSAR, molecular dynamics, and explainable AI for simulating drug–target interactions prior to synthesis. This review contrasted computational and experimental methods, highlighting benefits such as scalability, cost reduction, and early toxicity prediction, while also acknowledging limitations like biological oversimplification and the necessity for experimental validation. Case studies illustrated real-world applications in drug repurposing and hit identification. Emerging directions included quantum simulations, personalized virtual trials, and federated AI platforms—further reinforcing the transformative role of in silico tools in drug discovery.

KEYWORDS: In-silico drug design, Computer-aided drug discovery (CADD), Virtual screening, Molecular docking, ADMET prediction, AlphaFold, AI in pharmacology, Computational pharmacology, QSAR modelling.