Beyond the drug-centric view: Advancing AI virtual cell platforms for environmental perturbation modelling

Environmental exposures contribute substantially to global morbidity and mortality, with their biological effects shaped by factors such as dose, exposure duration, life-stage timing, and cumulative or sequential exposure patterns. With rapid advances in AI based virtual cell (VC) technologies, current frameworks emphasize genet-ic and pharmacological perturbations, leaving environmental perturbations insufficiently modelled. This imbal-ance is due to fundamental structural limitations in data availability, chemical space coverage, and representa-tional design, as well as lacking standardized annotation of dose, timing and mixtures, which are core deter-minants of environmental perturbations. This review argues that incorporating environmental perturbations as a foundational component of virtual cell development is necessary to extend these models toward environ-mental and public health applications. We review the evolution of these perturbation predictive models from mathematical models to deep learning and foundation model architectures, evaluate the status of virtual cell efforts across genomic, transcriptomic, proteomic, metabolomic and phenomic modalities, and show the sys-tematic gaps that currently limit their applicability to environmental health. We outline key challenges, includ-ing data scarcity and bias, inadequate representation of environmental perturbations, limited multimodal inte-gration, and weak benchmarking practices. To address these issues, we propose the development of stand-ardized environmental perturbation datasets, integrated and standalone multimodal architectures, uncertainty-aware evaluation metrics, and regulatory-aligned benchmarking frameworks which are all geared toward ad-vancing in silico perturbation and non-animal testing, promoting the 3Rs paradigm.