A Comprehensive Review on Artificial Intelligence in Drug Discovery and Development
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
With clinical trial failure rates exceeding 90%, drug discovery and development is a complicated, expensive, and time-consuming process that usually takes 12 to 15 years and substantial financial investment to bring a single drug to market [1].Inadequate target identification, poor therapeutic efficacy, and unexpected toxicity during late-stage trials are major reasons for attrition in traditional drug development [1-3].These difficulties have forced the adoption of sophisticated computational and data-driven methods and revealed significant inefficiencies in traditional drug discovery pipelines [2, 3].Pharmaceutical research can be accelerated, prediction accuracy can be increased, and experimental workload can be decreased thanks to artificial intelligence (AI), which combines machine learning (ML) and deep learning (DL) techniques [3–5].Target identification and validation, hit identification via virtual screening, lead optimization, and prediction of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties are examples of AI applications in drug discovery [6–9].De novo molecular design and effective chemical space exploration have been made possible by sophisticated AI models like deep neural networks, convolutional neural networks, recurrent neural networks, generative adversarial networks, and variational autoencoders [6,10–12].Additionally, structure-based drug design and early toxicity assessment have been greatly improved by AI-driven tools like graph-based learning models and protein structure prediction systems [10–13].Beyond the early stages of discovery, AI has shown a significant impact on clinical trials and drug development by improving pharmacovigilance and regulatory compliance, optimizing trial design, and improving patient recruitment through electronic health record analysis [14–17]. Despite these developments, the broad use of AI in pharmaceutical research is still constrained by issues with data quality, model interpretability, ethical issues, regulatory acceptance, and high computational requirements [15–17].All things considered, artificial intelligence is a paradigm shift in drug discovery and development, with the potential to lower costs, expedite development, and promote the development of safer, more efficient, and customized therapeutic interventions [1–17].
Fields of Study & Subjects
Computational Drug Discovery Methods
Machine Learning in Materials Science
Artificial Intelligence in Healthcare and Education
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 28 March 2026
- Language
- EN