Minghua Deng

This paper introduces CoDA-hd, a compositional data analysis approach for scRNA-seq, showing its advantages in dimension reduction, clustering, and trajectory inference compared to log-normalization.

scRMD imputes dropout values in scRNA-seq data using robust matrix decomposition, improving downstream analysis accuracy.

Deepprune prunes and fine-tunes CNNs to improve motif inference with fewer kernels, achieving better performance on simulated and ChIP-seq data.

This paper introduces expectation pooling, an interpretable CNN pooling method that improves DNA-protein binding prediction by combining probabilistic ideas with deep learning.

This paper introduces a hybrid method combining clustering and deep learning to predict real-valued protein backbone dihedral angles and their confidence bounds, achieving better performance than existing methods.