Computational and Systems Pathology

The Computational and Systems Pathology Lab uses computational approaches and mathematical modeling to study human diseases, especially cancer, leveraging “big‐data” from multiple sources (like digital images and molecular data) to improve patient care by generating clinically actionable knowledge. This is achieved through integrating data, information, and expertise from classical pathology disciplines with quantitative methods grounded in biostatistics, epidemiology, mathematics, and computer science. Ultimately, this research will lead to next-generation biomarkers in the form of predictive models for screening, diagnostics, prognostication, and therapy selection.

Besides translational research geared towards biomarker development, the laboratory also focuses on basic research using computational and statistical modeling coupled to high throughput molecular approaches. The main focus of the lab, here, is deciphering the role of coding and non-coding RNA species in regulating the way genetic information becomes function. Such research contributes to our understanding of the way transcriptional and post-transcriptional mechanisms regulates gene expression in individual cells, tissues, and organisms, and to the way such system-level dynamics translates and instructs physiological and pathological processes.

Active projects

• Hardwiring biological mechanisms into predicting cancer phenotypes by computational learning
• Characterizing transcriptional and post-transcriptional regulation in mammalian cells, with a specific focus on the role played by non-coding RNA transcripts
• Developing image analysis approaches for digital pathology applications
• Integration of multi-modal data with clinical information