Model-informed drug development has become central to modern drug development and regulatory decision-making, with the FDA, EMA and PMDA all formally endorsing its use. The integration of artificial intelligence and machine learning with classical pharmacometric approaches is rapidly reshaping the field, and that integration now extends well beyond the clinic. AI and machine-learning tools, both open-source and proprietary, are being applied at every stage of the pipeline, from target identification and ADMET prediction in discovery, through preclinical and clinical modelling, to regulatory review and post-market surveillance. Generative models, large language models and protein-structure prediction are entering routine practice alongside established PK/PD, PBPK and quantitative systems pharmacology methods, while questions of reproducibility, validation, explainability and regulatory credibility cut across all of them. Yet a consolidated forum that bridges traditional modelling with these emerging data-driven methods across the full development continuum remains lacking. This Special Issue addresses that gap and is highly relevant across academia, industry and regulatory agencies.

Scope
The Special Issue will welcome original research, reviews and perspectives covering:

- AI/ML-enhanced population PK/PD modelling
- Machine learning approaches in PBPK and IVIVE
- Quantitative systems pharmacology (QSP) and digital twins
- Model-informed precision dosing
- AI in special populations (paediatrics, geriatrics, organ impairment)
- AI and machine learning across the drug development continuum, from discovery and preclinical through clinical, regulatory and post-market surveillance
- Open-source versus proprietary ("closed") AI systems, and their trade-offs for academia, industry and regulators
- Machine learning for ADMET, DMPK and physicochemical property prediction
- AI-driven molecular and protein-structure prediction (for example AlphaFold) in support of PK/PD and target characterization
- Generative AI, large language models and foundation models in pharmaceutical science
- AI-assisted allometric scaling and first-in-human pharmacokinetic prediction
- Free and accessible AI tools and the democratization of pharmacometric modelling and pharmaceutical education
- Regulatory perspectives on AI/ML in MIDD submissions, including the FDA credibility assessment framework
- Reproducibility, validation and explainability of ML models in pharmacometrics and across AI-enabled pipelines

Please note that the manuscript submission deadline is flexible, if you require an extension or have any other question, do not hesitate to contact us at the Publishing Office.

Authors

Journal of Pharmacy & Pharmaceutical Sciences