AI in Drug Designing, Repurposing, and Pharmacometrics

Artificial intelligence (AI) including machine learning and deep learning is accelerating the pace of drug design and development while making it more cost-effective than traditional methods. AI tools like AlphaFold 3 help scientists accurately predict how proteins and other molecules interact, speeding up the generation of new drugs from scratch and large-scale virtual screening. In drug repurposing, AI analyzes huge amounts of data such as patient records, genetic information, and real-world evidence to find new uses for existing drugs. Thus, AI-based drug repurposing helps save time and money, especially for rare diseases and cancers. In pharmacometrics, AI improves modeling of how drugs work in the body, helps design better clinical trials, predicts patient responses, and personalizes treatments. With evolving regulations including the FDA's recent draft guidance on using AI in drug development decisions, this Special Issue on 'AI in Drug Designing, Repurposing, and Pharmacometrics' brings together the latest research to explore innovative applications, real-world successes, and ongoing challenges in this exciting area. The special issue will also be a platform for generating novel ideas relevant to both teaching and research through commentary, perspectives, and review papers on broader aspects of AI-based drug design and development.

The goal of this Special Issue on 'AI in Drug Designing, Repurposing and Pharmacometrics' is to address the ongoing challenges in pharmaceutical research and development such as high costs (over $2 billion per drug), long timelines (10–15 years), and high failure rates (around 90%). Despite exciting progress like AlphaFold 3 improving molecule predictions and virtual screening, these advancements face hurdles like poor data quality, biased models, lack of clear explanations ('black box' issues), ethical problems, and unclear regulations.

To tackle these and unlock AI's full potential, this Special Issue brings together the latest research on more understandable and fair AI models, strategies to reduce bias, real-world examples in repurposing drugs for rare diseases and cancer, and better pharmacometrics tools like AI-powered PK/PD modelling. In line with the FDA's January 2025 draft guidance on risk-based AI use in drug decisions, it promotes trustworthy and transparent approaches to help turn innovations into real clinical successes, leading to quicker, safer, and cheaper ways to develop new medicines.

This Special Issue on 'AI in Drug Designing, Repurposing and Pharmacometrics' welcomes original research articles, brief communications, reviews, mini reviews, methodological advances, case studies, commentaries, and perspectives that explore the application of artificial intelligence (AI), machine learning (ML), and deep learning in transforming pharmaceutical research and development.

The scope encompasses, but is not limited to:
- Drug Design: De novo molecule generation, structure-based and ligand-based virtual screening, generative models (e.g., GANs, VAEs, diffusion models), prediction of ADMET properties, protein-ligand interactions and advancements building on tools like AlphaFold 3 for biomolecular structure prediction.
- Drug Repurposing: Network-based approaches, knowledge graphs, multimodal data integration (e.g., omics, electronic health records, real-world evidence), identification of novel indications for existing drugs and applications in oncology, rare diseases, and infectious diseases.
- Pharmacometrics: AI-enhanced population pharmacokinetics/pharmacodynamics (PK/PD) modelling, model-informed drug development (MIDD), quantitative systems pharmacology (QSP), personalized dosing, physiologically-based PK (PBPK) and integration with clinical trial simulation.

Cross-cutting themes include interpretable and explainable AI, bias mitigation, data quality and multimodal integration, ethical considerations, real-world validation, and alignment with evolving regulatory frameworks (e.g., FDA's January 2025 draft guidance on AI for regulatory decision-making).

We invite submissions from researchers, clinicians, data scientists, and industry experts. Manuscripts should present novel insights, robust methodologies, and evidence-based discussions that advance trustworthy AI applications in drug development. Authors are encouraged to highlight practical implications for accelerating safer, more efficient drug pipelines, while addressing challenges like model transparency and regulatory compliance. For submission instructions, please visit the journal's website or contact the Guest Editors.

Article types and fees

This Issue accepts the following article types, unless otherwise specified in the Issue description:

• Brief Communication
• Commentary
• Mini Review
• Original Research
• Review

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Issue accepts the following article types, unless otherwise specified in the Issue description:

• Brief Communication
• Commentary
• Mini Review
• Original Research
• Review

Keywords: Artificial Intelligence, Drug Discovery, Drug Designing, Drug Repurposing, Pharmacokinetics, Pharmacodynamics