Kai Cao

I am a Postdoc Fellow at the Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, working with Dr. Caroline Uhler.

I received my Ph.D. degree in System Theory from the Academy of Mathematics and Systems Science, Chinese Academy of Sciences in June 2022 with Dr. Lin Wan and Dr. Yiguang Hong. I received my B.E. degree in Automation from University of Science and Technology of China in June 2017.

My research is at the interface between machine learning and computational biology. My primary research interest lies in developing new computational algorithms for the study of large-scale genomic data, especially related to the single-cell sequencing data. My current research focuses on:

• Computational method development for integration of single-cell multi-omics datasets
• High-performance transfer learning algorithm development for single-cell sequencing data

CV

Highlights:

• A unified computational framework for single-cell data integration with optimal transport
  We introduce uniPort, a unified single-cell data integration framework that combines a coupled variational autoencoder (coupled-VAE) and minibatch unbalanced optimal transport (Minibatch-UOT).

• Unsupervised topological alignment for single-cell multi-omics integration
  We present a novel algorithm, termed UnionCom, for the unsupervised topological alignment of single-cell multi-omics integration. UnionCom does not require any correspondence information, either among cells or among features.

• Manifold alignment for heterogeneous single-cell multi-omics data integration using Pamona
  We present Pamona, a partial Gromov-Wasserstein distance-based manifold alignment framework that integrates heterogeneous single-cell multi-omics datasets with the aim of delineating and representing the shared and dataset-specific cellular structures across modalities.