We are at the forefront of utilizing advanced computational biology techniques to unravel intricate biological data, with a particular emphasis on transcriptomics and imaging data from cancer patients, especially those with prostate cancer (PCa).

Our research is structured around three pivotal themes:

• Biological Knowledge Integration: We incorporate prior biological knowledge into machine learning algorithms that analyze transcriptomics data, aiming to construct both robust and interpretable classifiers.

• Microenvironment Analysis: Leveraging single-cell RNA sequencing (scRNA-seq) and spatial omics profiling, we strive to elucidate the tumor microenvironment. Our objective is to pinpoint the molecular and spatial factors that influence PCa progression and metastasis.

• Deep Learning in Histopathology: We design and implement deep learning models on H&E-stained whole slide images, forecasting specific clinical and molecular phenotypes based on the tissue morphology derived from PCa patients.

Our overarching goal, guided by these themes, is to identify the primary mediators of disease progression in prostate cancer patients. By harnessing state-of-the-art computational tools, we aim to shed light on the intricate interplay of tumor and metastatic microenvironments specific to prostate cancer.