About
I'm a Ph.D. candidate and graduate research assistant in Computer Science at Purdue University and Purdue Institute for Cancer Research. I'm advised by Prof. Ananth Grama and Dr. Nadia Atallah Lanman.
Before joining Purdue, I earned my B.S. (First Class Honours) in Computer Science from the City University of Hong Kong, where I did my final year project and worked as a research assistant advised by Prof. Shuai Cheng Li.
My research interests sit at the intersection of Computational Biology and Machine Learning. I am particularly focused on developing multi-modal deep learning and causal learning frameworks to solve complex problems in omics data and drug discovery.
Selected Projects
We developed the first end-to-end framework to translate single-cell transcriptomics into high-resolution histopathology images. The model utilizes a rectified flow backbone and a dual-attention encoder to capture complex gene-morphology relationships.
Proposed a novel gradient-based causal discovery method. By reformulating d-separation via first-order logic and relaxing it into continuous space, we enabled differentiable optimization for constraint-based causal inference, improving robustness in low-sample regimes.
Developed a novel hierarchical clustering algorithm for single-cell RNA sequencing that utilizes topological entropy to identify complex cell type relationships and developmental hierarchies, outperforming state-of-the-art tools in clustering accuracy.
Experience
-
Data Science Intern (Computational Biology)
Johnson & Johnson (Janssen Pharmaceuticals), 2024.