Abstract
Heterogeneity in cancer gene expression is typically linked to genetic and epigenetic alterations, yet the extent of contribution from posttranscriptional regulation remains unclear. Here, we systematically measured messenger RNA (mRNA) dynamics across diverse breast cancer models, revealing that mRNA stability substantially shapes gene expression variability. To decipher these dynamics, we developed GreyHound, an interpretable multimodal deep-learning framework integrating RNA sequence features and RNA binding protein (RBP) expression. GreyHound identified an extensive network of RBPs and their regulons underlying variations in mRNA stability, including a regulatory axis centered on RBP RBMS3 and redox regulator TXNIP. RBMS3 depletion resulted in targeted transcript destabilization-associated with poor clinical outcomes and enhanced metastatic potential in xenograft models. In vivo epistasis studies confirmed that RBMS3-mediated regulation of TXNIP mRNA stability drives this metastasis-suppressive program. These findings identify a key posttranscriptional mechanism in breast cancer and illustrate how interpretable models of RNA dynamics can uncover regulatory programs in disease.