Mingze Dong
![cover.png](/assets/img/cover.png?ec2e583126354e43ac741efff5899fa8)
Generated by DALL·E.
I am a CBB (Computational Biology & Bioinformatics) PhD student at Yale University. I am very fortunate to be co-advised by Prof. Yuval Kluger and Prof. Rong Fan. Before my PhD, I earned BS degree in Integrated Science from Peking University, focusing on applied math and biology. During my undergraduate, I did research in Lin lab at Peking University and worked as a research intern in van Dijk lab at Yale University.
I have a broad research interest in causal representation learning, generative models, and interpretable machine learning. My work aims to develop novel machine learning approaches to reveal novel biological insights in single-cell data and spatial omics data. In my recent works, I developed causal frameworks to investigate perturbation responses in scRNA-seq data (CINEMA-OT) and identify causal communicating genes in spatial omics data (GEASS). More recently, I developed novel variational inference frameworks that systematically reveals cell intrinsic variation and intercellular communications for spatial omics data (SIMVI), and enables zero-shot query of biological states in scRNA-seq data via identifiable modeling (scShift). Besides these, I also enjoy collaborating with experimentalists to analyze new biological data, or working on fundamental machine learning problems.
Feel free to contact me if you are interested in a potential collaboration or just a chat!
selected publications
- Nature MethodsCausal identification of single-cell experimental perturbation effects with CINEMA-OTNature Methods, 2023
- Ongoing workDeep identifiable modeling of single-cell atlases enables zero-shot query of cellular statesbioRxiv, 2023
- Ongoing work
- ICMLTowards Understanding and Reducing Graph Structural Noise for GNNsProceedings of the 40th International Conference on Machine Learning, 2023
- ICLRGEASS: Neural causal feature selection for high-dimensional biological dataThe Eleventh International Conference on Learning Representations (Spotlight), 2022