Recent advances in drug discovery and development through machine learning : A rational drug design (2000-2024)
Abstract
The traditional drug discovery process—often hindered by high costs and long timelines—has been profoundly transformed by machine learning (ML). This review highlights major breakthroughs from 2000 to 2024, illustrating how ML has revolutionized rational drug design by enabling highly accurate predictions of pharmacological properties, from target binding to clinical toxicity. Through an analysis of QSAR and computer-aided drug design (CADD) literature, we demonstrate that ML models achieve significantly higher accuracy in predicting biological activity (ΔAUC > 0.25 compared to traditional methods), ADMET profiles, and off-target effects. These advances stem from innovations such as attention-based neural networks and physics-informed generative models. However, several challenges persist in clinical translation: (1) black-box models with limited interpretability hinder regulatory approval, (2) biased training data perpetuate inaccuracies in polypharmacology prediction, and (3) overfitting to synthetic datasets fails to capture real-world biological complexity. Case studies reveal that ML-predicted candidates occasionally underperform in vivo due to simplified assumptions about protein–ligand dynamics. Despite these limitations, the overall trajectory remains highly promising. Emerging methodologies—such as federated learning for multi-institutional data sharing, hybrid quantum ML for molecular dynamics, and mechanistic embeddings—are bridging th gap between in silico…
How strong is the evidence?
Evidence Hub reads this as a review, done in computer models (in silico), not in people. Its evidence level is 5 of 5 (Very low · case / narrative / animal / in vitro / in silico). Case reports, narrative reviews, and animal, cell or computer-model studies give the weakest evidence for human health.
Read the paper
Related studies
- Quantum dots: synthesis, bioapplications, and toxicity
- A Guide to In Silico Drug Design
- Quantum Computing for Healthcare: A Review
- Automated in Silico Design of Homogeneous Catalysts
- Identification of Novel 3-Hydroxy-pyran-4-One Derivatives as Potent HIV-1 Integrase Inhibitors Using in silico Structure-Based Combinatorial Library Design Approach
- In silico structural elucidation of RNA-dependent RNA polymerase towards the identification of potential Crimean-Congo Hemorrhagic Fever Virus inhibitors
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.