Unleashing AI for preclinical drug development
6 affiliations
- 1McWilliams School of Biomedical Informatics
- 2University of Texas Health Science Center at Houston
- 3School of Computing and Artificial Intelligence
- 4Southwest Jiaotong University
- 5College of Artificial Intelligence Medicine
- 6Chongqing Medical University
Abstract
Artificial intelligence (AI) is reshaping preclinical drug development across target discovery, therapeutic design, synthesis, functional characterization and safety assessment. In this review, we present an integrated view of AI across the preclinical pipeline, beginning with target identification, modality selection and representation learning for molecular, protein, structural, cellular and multimodal data. We then examine major generative modeling paradigms including autoregressive, latent-variable, diffusion, flow-based and guided approaches and their applications across small molecules, peptides, enzymes, antibodies, Tcell receptors and mRNA therapeutics. We discuss how these methods support de novo design, structure- and pocket-conditioned generation, sequence–structure co-design, affinity and activity optimization, developability engineering and synthesis-aware discovery. We further review AI-enabled retrosynthesis, reaction prediction and closed-loop experimental optimization, emphasizing the distinction between computational synthesizability and experimentally executable chemistry. Beyond molecular generation, we organize functional prediction from binding and kinetics through target engagement, pharmacological activity, mechanism of action, pathway response and phenotypic outcome. We also examine singlecell perturbation modeling, organoid-based drug-response prediction, toxicity and off-target assessment, and prospective validation across therapeutic modalities. Across these areas, we highlight the importance of uncertainty estimation, out-of-distribution generalization, reproducibility and experimentally grounded benchmarking. Finally, we discuss how integrating generative AI, mechanistic biology and iterative design–make–test–analyze cycles could transform AI from isolated predictive tools into decision-support systems for preclinical drug development.
Related
- Development of a Translational Assay for Identification and Quantitation of Orthologous Proteins to Aid Drug Development in Preclinical Models.
- Drug–Drug Conjugates as Intelligent Preclinical Platforms for Targeted Cancer Therapy
- Chalcone-pyridine/pyrimidine hybrids: promising candidates for anticancer drug development
- Development of an innovative method to enhance doxorubicin loading into erythrocyte-derived nanovesicles for breast cancer drug delivery
- Exploiting the synergy between computational and experimental biophysics for efficient cancer drug development
BibTeX
@misc{kumar2026unleashing,
title = {{Unleashing AI for preclinical drug development}},
author = {Himansu Kumar and Yankai Yu and Zhengxiao Yang and Bowen Wang and Xi Hu and Haixia Xu and Xiaohui Zhan and Hao Zhou and Jianguo Wen and Xiaobo Zhou},
howpublished = {ChemRxiv},
year = {2026},
month = oct,
doi = {10.26434/chemrxiv.15010246/v1},
url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010246/v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Unleashing AI for preclinical drug development
AU - Himansu Kumar
AU - Yankai Yu
AU - Zhengxiao Yang
AU - Bowen Wang
AU - Xi Hu
AU - Haixia Xu
AU - Xiaohui Zhan
AU - Hao Zhou
AU - Jianguo Wen
AU - Xiaobo Zhou
PY - 2026
DA - 2026/10/11
PB - ChemRxiv
DO - 10.26434/chemrxiv.15010246/v1
UR - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010246/v1
AB - Artificial intelligence (AI) is reshaping preclinical drug development across target discovery, therapeutic design, synthesis, functional characterization and safety assessment. In this review, we present an integrated view of AI across the preclinical pipeline, beginning with target identification, modality selection and representation learning for molecular, protein, structural, cellular and multimodal data. We then examine major generative modeling paradigms including autoregressive, latent-variable, diffusion, flow-based and guided approaches and their applications across small molecules, peptides, enzymes, antibodies, Tcell receptors and mRNA therapeutics. We discuss how these methods support de novo design, structure- and pocket-conditioned generation, sequence–structure co-design, affinity and activity optimization, developability engineering and synthesis-aware discovery. We further review AI-enabled retrosynthesis, reaction prediction and closed-loop experimental optimization, emphasizing the distinction between computational synthesizability and experimentally executable chemistry. Beyond molecular generation, we organize functional prediction from binding and kinetics through target engagement, pharmacological activity, mechanism of action, pathway response and phenotypic outcome. We also examine singlecell perturbation modeling, organoid-based drug-response prediction, toxicity and off-target assessment, and prospective validation across therapeutic modalities. Across these areas, we highlight the importance of uncertainty estimation, out-of-distribution generalization, reproducibility and experimentally grounded benchmarking. Finally, we discuss how integrating generative AI, mechanistic biology and iterative design–make–test–analyze cycles could transform AI from isolated predictive tools into decision-support systems for preclinical drug development.
ER -