Conventional drug development remains a protracted, costly, and high-risk endeavor, typically spanning 10–15 years from target identification to post-marketing surveillance. This multistage process encompasses target discovery and validation, hit identification and optimization, preclinical testing, clinical trials, regulatory approval, and ongoing safety monitoring. In this way, only 10–12% of candidates entering clinical trials reach regulatory approval. Despite being well established, this linear model of drug development is increasingly recognized as unsustainable. Each approved drug is estimated to cost over USD 2.5 billion, nearly 90% of candidates fail during clinical development, and meaningful breakthroughs, particularly for orphan diseases and targeted therapies, remain limited [1]. These shortcomings have catalyzed growing interest in computational approaches as transformative tools capable of accelerating discovery, reducing costs, and improving success rates in the search for viable drug candidates [2].
In traditional methods, once lead compounds are identified through high-throughput screening, structural optimization aims to enhance binding affinity, selectivity, bioavailability, and safety. This process is typically guided by structure–activity relationships (SAR) analysis [3]. Preclinical evaluation then assesses toxicity and efficacy in animal models [4], with only the most promising compounds advancing to human trials. Collectively, these stages underscore the inefficiencies of the conventional approach and highlight the urgent need for innovation to streamline drug development timelines [5]. Computational methods have emerged as a powerful catalyst in modern drug discovery, offering novel strategies to accelerate pharmaceutical innovation [6]. Traditional compound optimization methods are often labor-intensive and experimentally driven. In contrast, computational methods enable researchers to navigate vast chemical spaces efficiently, generating novel molecules with high affinity for specific biological targets in a fraction of the time [7].
AI-driven target identification and validation leverage large-scale biological datasets—including genomics, proteomics, and transcriptomics—to uncover disease-associated pathways, particularly in complex, polygenic disorders such as cancer and neurodegenerative diseases [8]. Deep learning models can predict biological activity and validate targets computationally, reducing reliance on costly and time-consuming laboratory assays [9]. One of the most transformative applications of computational methods lies in de novo compound generation. Deep learning architectures can design novel drug-like molecules that extend beyond existing chemical libraries while adhering to principles of chemical stability, drug-likeness, and bioactivity [10]. This capability significantly compresses early discovery timelines.
Computational methods also enhance drug optimization by predicting pharmacokinetic and pharmacodynamic properties, thereby improving candidate selection and reducing late-stage failures. By analyzing large datasets, Computational models can identify off-target effects and toxicity risks, enabling safer and more effective compound refinement [3]. Moreover, machine learning techniques such as random forests, support vector machines, and neural networks help prioritize the most promising candidates for downstream testing [11].
Beyond discovery, computational models are increasingly applied to preclinical and clinical development. Predictive models can assess toxicity and side effects without extensive animal or human exposure, while AI-assisted trial design improves patient recruitment, monitoring, and overall trial efficiency [12,13]. Generative AI is also a cornerstone of precision medicine, enabling therapies tailored to individual genetic and molecular profiles. By predicting patient-specific drug responses, AI supports personalized treatment strategies—particularly in oncology, where tumor heterogeneity demands highly individualized interventions [14,15,16]. Additionally, computer-driven virtual screening and drug repurposing allow rapid identification of new therapeutic uses for existing compounds. By mining large clinical and preclinical datasets, computer-assisted drug design can uncover previously unrecognized drug–target relationships, accelerating the availability of treatments for unmet medical needs [17,18,19].
In this context, this Special Issue consolidates a broad array of computational strategies—from structure-based methods like docking, molecular dynamics (MD) and free-energy profiling, to ligand-based techniques like pharmacophore modeling, similarity analysis, and QSAR (quantitative structure–activity relationships). This content curation sends a clear message: computational chemistry and bioinformatics are no longer niche—they are a central, mainstream pillar of modern drug discovery. As in earlier editions, the ambition is to blur the boundary between “in silico only” and “wet-lab + in silico” workflows, encouraging hybrid studies that combine computational predictions with experimental validation. The papers collected in this issue illustrate how computational tools are applied across a wide spectrum of real-world drug-discovery problems.
Conflicts of Interest
The authors declare no conflict of interest.
References
- Dowden, H.; Munro, J. Trends in clinical success rates and therapeutic focus. Nat. Rev. Drug Discov. 2019, 18, 495–496. [Google Scholar] [CrossRef]
- Ru, J.; Li, P.; Wang, J.; Zhou, W.; Li, B.; Huang, C.; Li, P.; Guo, Z.; Tao, W.; Yang, Y.; et al. TCMSP: A database of systems pharmacology for drug discovery. J. Cheminform. 2014, 6, 13. [Google Scholar] [CrossRef] [PubMed]
- Jorgensen, W.L. Efficient drug lead discovery and optimization. Acc. Chem. Res. 2009, 42, 724–733. [Google Scholar] [CrossRef]
- Teicher, B.A.; Andrews, P.A. Anticancer drug development guide. Cancer Chemother. Pharmacol. 2004, 54, S1–S8. [Google Scholar]
- Johnson, J.R.; Williams, G.; Smith, R. Accelerating drug discovery using computational approaches. Drug Discov. Today 2001, 6, 239–246. [Google Scholar]
- Roomi, M.S.; Culletta, G.; Longo, L.; Filgueira de Azevedo, W., Jr.; Perricone, U.; Tutone, M. Docking in the Dark: Insights into Protein–Protein and Protein–Ligand Blind Docking. Pharmaceuticals 2025, 18, 1777. [Google Scholar] [CrossRef]
- Sellwood, M.A.; Ahmed, M.; Segler, M.H.S.; Brown, N. Artificial intelligence in drug discovery. Future Med. Chem. 2018, 10, 2025–2028. [Google Scholar] [CrossRef]
- Kadurin, A.; Aliper, A.; Kazennov, A.; Mamoshina, P.; Vanhaelen, Q.; Khrabrov, K.; Zhavoronkov, A. The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology. Oncotarget 2017, 8, 10883–10890. [Google Scholar] [CrossRef] [PubMed]
- Murphy, K.P. Machine Learning: A Probabilistic Perspective; MIT Press: Cambridge, MA, USA, 2011. [Google Scholar]
- Bleicher, K.H.; Böhm, H.J.; Müller, K.; Alanine, A.I. Hit and lead generation: Beyond high-throughput screening. Nat. Rev. Drug Discov. 2003, 2, 369–378. [Google Scholar] [CrossRef]
- Isarankura-Na-Ayudhya, C.; Na-Bangchang, K.; Prachayasittikul, V. Machine learning techniques for drug discovery. EXCLI J. 2009, 8, 74–88. [Google Scholar]
- Harrer, S.; Shah, P.; Antony, B.; Hu, J. Artificial Intelligence for Clinical Trial Design. Trends Pharmacol. Sci. 2019, 40, 577–591. [Google Scholar] [CrossRef]
- Banik, S. Artificial intelligence in clinical trials: Opportunities and challenges. Perspect. Clin. Res. 2015, 6, 215–217. [Google Scholar]
- Lentini, L.; Perriera, R.; Corrao, F.; Melfi, R.; Tutone, M.; Carollo, P.S.; Fiduccia, I.; Pace, A.; Ricci, D.; Genovese, F.; et al. A precision medicine approach to primary immunodeficiency disease: Ataluren strikes nonsense mutations once again. Mol. Ther. 2025, 33, 3231–3241. [Google Scholar] [CrossRef] [PubMed]
- Ashley, E.A. Towards precision medicine. Nat. Rev. Genet. 2016, 17, 507–522. [Google Scholar] [CrossRef] [PubMed]
- Ginsburg, G.S.; McCarthy, J.J. Personalized medicine: Revolutionizing drug discovery and patient care. Trends Biotechnol. 2001, 19, 491–496. [Google Scholar] [CrossRef] [PubMed]
- Culletta, G.; Almerico, A.M.; Tutone, M. Comparing molecular dynamics-derived pharmacophore models with docking: A study on CDK-2 inhibitors. Chem. Data Collect. 2020, 28, 100485. [Google Scholar] [CrossRef]
- Brindha, G.; Vinodhini, R.; Sathya, R. Drug repurposing: A review. J. Pharm. Sci. Res. 2016, 8, 1293–1297. [Google Scholar]
- Ma, D.L.; Chan, D.S.; Leung, C.H. Molecular docking for virtual screening of natural product databases. Chem. Sci. 2013, 4, 3366–3383. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.