PULSAR, a multi-scale foundation model that hierarchically integrates molecular, cellular, and multicellular information from single-cell transcriptomes, achieves state-of-the-art disease classification (0.954 accuracy across disease categories), predicts future clinical events including rheumatoid arthritis onset and vaccine responses, and enables generative simulation of cytokine perturbations across biological scales while maintaining interpretability through attention-based identification of disease-driving cell populations.

Biology emerges from interactions across physical scales, where molecular interactions drive cellular states, which in turn orchestrate multicellular tissue functions that collectively define health and disease. However, current computational models are often constrained to single scales in isolation, failing to integrate the biology that emerges from lower to higher levels. Here we present PULSAR (Patient Understanding Leveraging Single-cell universAl Representation), a multi-scale and multicellular foundation model architecture that explicitly enables information flow from genes to cells to multicellular systems. Applied to the human peripheral immune system, PULSAR extracts a unified donor representation that supports rapid disease classification, biomarker prediction, and forecasting of future clinical events, such as Rheumatoid arthritis onset. As a generative model, PULSAR enables the simulation of cytokine perturbation response across physical resolutions, while its interpretability reveals the key cell types driving disease. Overall, PULSAR opens new avenues for precision medicine by enabling computational reasoning that connects molecular biology to clinical phenotypes.