CALL FOR PAPERS

Clinical Pharmacology & Therapeutics (CPT) is seeking submissions for an upcoming themed issue on "Who Signs the Model? Evidence, Autonomy, and Accountability in AI-Informed Drug Development.”

This themed issue will explore the shift from AI as a predictive tool to AI as a participant in the evidentiary chain, and will feature methods, benchmarks, case studies, and regulatory perspectives that clarify who is accountable for a model-informed decision, on what evidence that decision rests, and what happens when the model is wrong. Contributions that make an AI method usable by a practicing pharmacologist or a regulatory reviewer will be prioritized over those that demonstrate capability alone.

We welcome submissions on a variety of topics, including but not limited to:

• Perspectives on evidence, autonomy, and accountability when AI participates in pharmacological decision-making, including human oversight, liability, and disclosure norms
• Structure prediction and co-folding (AlphaFold 3 and open successors) → target engagement, off-target liability, transporter and enzyme interaction prediction
• Binding affinity and potency prediction on human dose and exposure-response, and whether in-silico affinity can support a first-in-human dose rationale
• Generative and de novo design of small molecules, peptides, antibodies, protein therapeutics, targeted degraders: the clinical pharmacology profile of what comes out
• ADME, physicochemical, and safety property prediction from structure → DDI and toxicity liability, weighted alongside in vitro and NAM evidence
• Closing the discovery-to-clinic gap: whether AI-designed molecules actually behave differently in first-in-human studies and their translational success
• Use cases and implementation of recent AI-focused regulatory frameworks, including the FDA risk-based credibility assessment framework, the FDA–EMA Guiding Principles of Good AI Practice, and ICH M15
• Agentic AI in drug development: multi-agent systems for protocol design, pharmacometric analysis, literature and label synthesis, and submission-ready documentation, with transparent accounting of error rates and human checkpoints
• Foundation models for pharmacology, including molecular, PK/PD, EHR, and multimodal pretraining, with evidence of where transfer holds and where it fails
• Benchmarks, evaluation standards, and reporting norms for AI in clinical pharmacology, including hallucination, silent failure, and prospective validation
• Uncertainty quantification, calibration, and regulatory-acceptable validation for AI, ML, and hybrid mechanistic/data-driven models, including conformal prediction and acceptance criteria for go/no-go decisions
• AI-enabled MIDD: neural differential equations, ML-augmented quantitative systems pharmacology and population PK, and fit-for-purpose validation when the model is learned rather than written
• Virtual patients, digital twins, and in-silico control arms: construction, validation, borrowing strategies, and the evidentiary threshold for substituting simulated for enrolled patients
• Lifecycle management of deployed models, including dataset shift, drift detection, retraining, post-deployment monitoring, and what constitutes a reportable change
• Federated learning, privacy-preserving methods, and synthetic patient data for integrating diverse sources of pharmacologic and real-world data
• Multimodal AI across EHR, claims databases, patient registries, imaging, digital pathology, multi-omics, and wearable data for real-world evidence (RWE) generation, exposure-response characterization, predictive enrichment, and safety signal detection
• Methods for digital biomarkers and continuous monitoring, including representation learning, measurement error, and missing data
• Transparency artifacts that regulators can use, including model cards, data provenance and lineage, and reproducibility packages for learned models
• AI on the regulator’s side of the table: generative AI in review, inspection targeting, and pharmacovigilance (including signal detection and post-market surveillance), and the interplay of efficiency, error, and due process
• AI where data are structurally scarce, including pediatrics, pregnancy and lactation, organ impairment, and rare disease, and the limits of extrapolation
• Training the next generation of clinical pharmacologists for AI-intensive practice, as well as workforce and organizational readiness for adopting these tools in regulatory and clinical workflows

Submissions of original research are particularly encouraged, but reviews, position/white papers, or perspectives are also welcome. Educational, tutorial-style papers will also be considered. In the cover letter of your submission, please state that you are responding to this Call for Papers.

Please contact cpteditor@ascpt.org for details about manuscript types and format requirements, or review our Author Guidelines here.

To be considered for publication in this high-profile themed issue, manuscripts should be submitted via the online submission and tracking system by November 30, 2026.

If you would like to make a pre-submission inquiry or request a deadline extension, please contact the CPT editorial office at cpteditor@ascpt.org.

Sort by: Newest First Oldest First Most Popular Most unliked