About the Journal

ISSN: pending registration. Founding Editorial Board: appointments in progress.

The Journal of AI-Driven Drug Discovery (JAIDD) is a peer-reviewed open-access journal on the application of artificial intelligence across the drug-discovery pipeline.

Machine learning is now used at most stages of drug discovery, from target identification and structure prediction to molecular design and the prediction of ADMET properties. JAIDD publishes methodological and applied work in this area, with an emphasis on validation and reproducibility.

JAIDD serves computational chemists, structural biologists, pharmacologists, AI researchers, and drug discovery scientists in academia, biotechnology, and the pharmaceutical industry. Published by Vallensis Publishing, Switzerland. Follows the COPE Core Practices.

Aims & Scope

JAIDD publishes original research, reviews, methodological papers, and technical notes on AI-driven drug discovery, molecular design, and computational pharmacology. Topics of interest include:

• Structure-based drug design using AI
• Generative models for molecular design (VAEs, GANs, diffusion models, transformers)
• Protein structure prediction and validation (AlphaFold2/3 and successors)
• De novo protein design and engineering
• Molecular docking and free energy perturbation
• AI-driven ADMET prediction and optimisation
• AI for target identification and validation
• Drug repurposing and repositioning using AI
• Protein-protein interaction prediction and modulation
• Computational antibody and biologics design
• AI-assisted synthesis planning and retrosynthesis
• Machine learning force fields and molecular dynamics
• Benchmarking studies and reproducibility in AI-driven drug discovery

Out of scope: purely synthetic chemistry without an AI/computational component, clinical pharmacology, and animal studies without computational methodology.