RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction

Histopathology whole-slide images (WSIs) are routinely acquired in clinical practice and contain rich tissue morphology but lack direct molecular architecture and functional programs defining pathological states, whereas RNA sequencing (RNA-seq) provides genome-wide transcriptional profiles at substantial cost, thereby motivating WSI-based genome-wide transcriptomic prediction. Existing approaches for predicting gene expression from WSIs predominantly rely on deterministic regression with one-to-one mapping, limiting their ability to capture biological heterogeneity and predictive uncertainty. We propose RNA-FM, a flow-matching generative framework for genome-wide bulk RNA-seq prediction from histopathology images. RNA-FM formulates transcriptomic prediction as a continuous-time conditional transport problem, learning a velocity field that maps a simple prior to the target gene expression distribution conditioned on morphological features. By incorporating pathway-level structure, RNA-FM enables scalable, biologically interpretable, and genome-wide gene expression imputation. Extensive experiments across multiple anatomical regions, pathway-level analysis, and external validation cohorts demonstrate that RNA-FM consistently outperforms state-of-the-art approaches while effectively capturing both inter-patient and intra-tumoral heterogeneity.