Jul 2026· Expert Opinion on Drug Discovery· Vol 21, pp. 965 - 981· 0 citations· 54 references
Medicine
TL;DR
A critical review is needed to distinguish the stages in which AI can improve search, prioritization, and decision-making from those that remain limited by experimental validation, safety assessment, and clinical evidence generation.
Abstract
ABSTRACT Introduction Artificial intelligence (AI) is increasingly proposed as a means of shortening drug-discovery timelines, although its practical impact varies across the discovery and development process. A critical review is needed to distinguish the stages in which AI can improve search, prioritization, and decision-making from those that remain limited by experimental validation, safety assessment, and clinical evidence generation. Areas covered This review discusses the use of AI in target and pathway prioritization, variant and protein-structure interpretation, drug repurposing, virtual screening, molecular design, ADMET prediction, biomarker discovery, and patient stratification. The review was informed by iterative searches of PubMed and Google Scholar, supplemented by ResearchGate, covering literature from database inception to 15 July 2026, together with reference lists, clinical-trial registries, regulatory disclosures, company reports, and publicly available pipeline updates. Expert opinion AI is most likely to shorten drug discovery when it improves the quality and sequence of decisions, reduces the number of unnecessary experiments, and identifies failure earlier. Its greatest value will arise when it is integrated with high-quality data, disease-relevant experimental models, expert supervision, and prospective clinical validation.
Oncologic drug development is lengthy (~14 years) and expensive (~1.2 billion USD) with low clinical trial success rates (4.1%). Big data and artificial intelligence (AI) are widely proposed as tools to address these challenges. In this review, we examine the current performance and future potential of big data and AI applied to preclinical discovery and development, clinical trials, and the regulatory approval process. We first examine the data foundation required for effective AI, including data harmonization, data commons, and analytical tools. We then assess preclinical applications spanning target identification, compound-library curation, virtual ligand screening, generative chemical design, and high-throughput and high-content screening. In clinical development, we consider the use of big data and AI for outcome prediction, trial design, external and synthetic control arms, adaptive monitoring, and in silico trials. Finally, we discuss how post-approval electronic health records can generate real-world data and real-world evidence to support drug repurposing and improve future oncology drug discovery. Big data is conventionally characterized by a series of “Vs.” In this review, we have used seven “Vs” spanning descriptive and constraining properties of big data and a singular outcome. We have proposed an eighth, Vernacular, a constraint defined as the combined alignment of data semantics and terminology, data representation, data exchange, and data governance across heterogeneous, independently generated datasets to promote interoperability and combined analysis. Although cancer data exhibit substantial Volume, Velocity, and Variety, they remain distributed across fragmented repositories that often cannot be readily integrated. We conclude with a discussion of tabulated resources currently available for the application of big data and AI to oncologic therapeutics.
Fakhar U. Singhera, J. Overhulse, Terrence M. Lee et al.· Cancers· 0 citations
Artificial intelligence (AI) now supports target identification, molecular representation, virtual screening, structure prediction, de novo design, synthesis planning, drug repurposing, and prediction of absorption, distribution, metabolism, excretion, and toxicity (ADMET). These capabilities can expand the chemical and biological hypotheses evaluated before costly experiments, but computational novelty is not equivalent to a safe or effective medicine. This structured critical narrative review examines AI as part of an iterative discovery system linking data, algorithms, medicinal chemistry, experimental biology, pharmacology, manufacturing, and clinical development. The synthesis emphasizes evidence quality, applicability domain, prospective validation, reproducibility, and regulatory credibility. A detailed case analysis of halicin shows both the legitimate achievement and the boundary of AI-prioritized discovery: a graph neural network selected a structurally unusual antibacterial candidate, followed by laboratory and animal validation, yet the finding did not establish clinical efficacy or approval. Additional analysis covers AlphaFold-enabled structural hypothesis generation, AI-designed molecules, multi-objective optimization, ADMET modeling, automated laboratories, clinical-development support, and AI-enabled target discovery. The article proposes five author-defined evidence levels and an author-synthesized stage-gated governance framework. Major limitations include biased or noisy data, distribution shift, shortcut learning, inadequate uncertainty estimation, proprietary opacity, environmental cost, intellectual-property ambiguity, and unequal access to data and computation. AI can accelerate learning and improve prioritization, but therapeutic value requires progressively stronger experimental, translational, clinical, and, where applicable, regulatory evidence.
Paola Carolina Rainer da Silva· Nexus Science Review· 0 citations
This review explores recent AI innovations—such as AlphaFold for protein structure prediction, generative models for de novo drug design, and graph neural networks for drug repurposing—alongside real-world case studies from companies like Exscientia, Insilico Medicine, and BenevolentAI, which have produced clinical candidates like DSP-1181 and rentosertib.
P. Jadhav, R. Pingale, Kanchan Gajanan Gawai et al.· International journal for ad...· 0 citations
A 4-layer framework can give MCOs earlier visibility into a therapy's likely clinical profile, cost-effectiveness distribution, and formulary placement probability before a manufacturer's dossier arrives, and allows budget forecasting and contracting strategy to keep pace with growing AI-accelerated pipelines.
Rishi Sharma· Journal of Managed Care & Sp...· 0 citations
The traditional drug discovery and development process is historically characterized by high attrition rates, escalating financial costs, and decade-long timelines. The emergence of artificial intelligence (AI) and machine learning (ML) has transformed this paradigm by enabling efficient navigation through vast chemical spaces and the integration of complex multi-omic datasets. This evidence-based literature review critically examines the evolution and application of computational technologies across the pharmaceutical pipeline, ranging from early expert systems like DENDRAL, computer-aided drug design (CADD), and quantitative structure-activity relationship (QSAR) modeling to AlphaFold 3 biomolecular complex predictions, computer-assisted synthesis planning (CASP), natural product bioprospecting, and autonomous multi-agent systems. Key advancements in antimicrobial screening, precision oncology, phytochemical characterization, and clinical-stage AI-generated molecules are highlighted. Finally, the translational gap is addressed, emphasizing that AI functions as an advanced decision-support framework requiring rigorous in vitro and in vivo experimental validation, wherein qualified human mediation remains indispensable for therapeutic success.
Leonardo Mairene Muniz· Brazilian Journal of Health...· 0 citations
Traditional drug development suffers from high costs, low success rates, and patient response variability. Precision drug discovery seeks to overcome these limitations by targeting specific genetic and molecular mechanisms but faces challenges in integrating cross-scale, multimodal biomedical data. Recent advances in artificial intelligence (AI), especially deep learning, provide powerful tools to navigate these complexities. This review surveys representative AI methods across four core stages of precision drug discovery: (a) target identification and validation using omics-, drug-, and structure-based approaches; (b) structure- and sequence-guided virtual screening of active compounds; (c) individualized drug response prediction integrating cell-line, single-cell, and multimodal data; and (d) AI-enabled toxicology and safety modeling to anticipate adverse liabilities and improve translational success. We further highlight a paradigm shift toward autonomous scientific agents capable of causal reasoning and end-to-end experimental guidance. Finally, we discuss persistent challenges, including data bias, limited interpretability, and in silico-to-wet lab translation.
