Harnessing Molecular Biophysics and AI for Cellular Disease Mechanisms and Drug Discovery

Recent developments in molecular biophysics and AI provide a path to connect biomolecular structure and dynamics with cellular phenotypes, revealing mechanistic drivers of disease and actionable therapeutic opportunities. Cells are governed by physical principles: forces, conformational dynamics, diffusion, and energy landscapes shape how molecular networks sense, compute, and fail. Molecular biophysics deciphers these rules at atomic to mesoscale resolution, while AI now enables powerful modeling, representation learning, and design across vast biological datasets. Recent advances include AI-augmented structure prediction and design, experimental investigation of biomolecular structures in near-native contexts, high-content and single-cell phenomics, and multimodal omics integration. By uniting these capabilities, researchers can map how molecular states propagate to cellular dysfunction and identify precise intervention points for drug discovery.Despite rapid progress, fundamental challenges limit translation from mechanism to medicine. Disease mechanisms often arise from context-dependent, nonequilibrium states, and transient events—such as rare conformers, allosteric couplings, biomolecular condensates, and mesoscale assemblies—that elude static structure investigation and bulk assays. Bridging genotype to phenotype remains difficult due to heterogeneous data, limited interpretability of black-box AI, and sparse ground truth at intermediate biophysical scales. In drug discovery, teams must navigate rugged design landscapes balancing potency, selectivity, kinetics, ADMET, resistance pathways, and delivery constraints for diverse modalities. Furthermore, robust integration of biophysical measurements with AI—spanning time and length scales—requires improved standards, high-quality datasets, uncertainty quantification, and reproducible, physics-informed methods.This Research Topic aims to catalyze solutions by integrating molecular biophysics with interpretable, data-efficient AI to decode cellular disease mechanisms and accelerate therapeutic discovery. By coupling quantitative measurements with advanced computation—ranging from physics-based simulations to causal and generative modeling—this Topic seeks to uncover mechanism-to-phenotype maps, identify robust intervention nodes, and compress design–make–test cycles. Contributions that connect atomistic events to cellular outcomes and translate insights into small molecules, biologics, and emerging modalities are especially encouraged.To gather further insights in this expansive field, this Topic welcomes articles addressing, but not limited to, the following themes:- Molecular structure, dynamics, and energetics across scales- Biophysics of intrinsically disordered proteins, condensates, and mesoscale assemblies- AI-enhanced modeling: physics-informed learning, foundation models, and generative design- Integrating simulations (e.g., MD, enhanced sampling) with single-molecule and ensemble biophysics- Quantitative models of dysregulated signaling, mechanotransduction, and membrane trafficking in disease- Multimodal data fusion: cryo-EM/ET, NMR, XL-MS, FRET, imaging, phenomics, and omics- Interpretable and causal ML; uncertainty quantification and robustness in biomedical AI- Predictive models of binding kinetics, allostery, selectivity, and resistance evolution- Design of small molecules, peptides, antibodies, PROTACs, molecular glues, and RNA-targeting agents- High-throughput and single-cell biophysics, live-cell biosensors, CRISPR and chemical-genetic screens- Microphysiological systems and in situ biophysics for translational de-risking- Data standards, FAIR resources, benchmarks, and reproducibility; ethical and privacy-preserving AIContributions that address emerging modalities, scalable experimental platforms, and strategies for translational robustness are encouraged. Manuscripts may be submitted under the accepted article types. We particularly welcome multidisciplinary approaches that integrate experimental and theoretical insights to advance mechanistic understanding and accelerate drug discovery at the interface of molecular biophysics and AI. Topic editors: Jack Adam Tuszynski, Md Ashrafuzzaman Source: https://www.frontiersin.org/research-topics/77151/harnessing-molecular-biophysics-and-ai-for-cellular-disease-mechanisms-and-drug-discovery