Projects

Research projects

scMultiNODE: Integrative and Scalable Framework for Multi-Modal Temporal Single-Cell Data
We introduce scMultiNODE, an unsupervised integration model that combines gene expression and chromatin accessibility measurements in developing single cells, while preserving cell type variations and cellular dynamics. First, scMultiNODE uses a scalable, Quantized Gromov-Wasserstein optimal transport to align a large number of cells across different measurements. Next, it utilizes neural ordinary differential equations to explicitly model cell development with a regularization term to learn a dynamic latent space.
Code Related Paper
scMultiNODE: Integrative and Scalable Framework for Multi-Modal Temporal Single-Cell Data
scNODE: Generative Model for Temporal Single Cell Transcriptomic Data Prediction
We introduce scMultiNODE, an unsupervised integration model that combines gene expression and chromatin accessibility measurements in developing single cells, while preserving cell type variations and cellular dynamics. First, scMultiNODE uses a scalable, Quantized Gromov-Wasserstein optimal transport to align a large number of cells across different measurements. Next, it utilizes neural ordinary differential equations to explicitly model cell development with a regularization term to learn a dynamic latent space.
Code Related Paper
scNODE: Generative Model for Temporal Single Cell Transcriptomic Data Prediction
Dropout-Aware Weighted NMF on scRNA-seq Data
The final project for CS2952Q Robust Algorithms for Machine Learning.
Dropout-Aware Weighted NMF on scRNA-seq Data
Disease Prediction Using Deep Learning Methods
The final project for CS2470 Deep Learining.
Disease Prediction Using Deep Learning Methods
Image segmentation and layer replacement
The final project for CS1430 Computer Vision.
Image segmentation and layer replacement