Huaxiao Yang

This paper introduces a generative AI framework that predicts cardiomyocyte contraction from static images, achieving high accuracy and revealing structure-function relationships.

This study uses micropatterned cardioids to investigate mesoderm-endoderm interactions in heart development, finding that pattern size affects cavity formation and signaling.

This paper develops a deep learning framework to screen for cardiotoxicity using hiPSC-derived cardiomyocytes, identifying compounds with high toxicity scores and inter-donor variability.

The paper demonstrates that micropatterned human pluripotent stem cells can model early human cardiac vascularization in vitro, resembling a 6.5 post-conception week heart and revealing conserved vascular development programs.

This paper uses conditional GANs to colorize brightfield images of cardiac organoids, providing cell type-specific fluorescence information to enhance their characterization.

This study shows PM curvature promotes ER-PM contact formation in cardiomyocytes via junctophilin-EHD interactions.