Shihua Zhang

This study introduces CSMF, a matrix factorization framework that combines data dimension reduction and differential analysis to reveal common and specific patterns across interrelated biological scenarios.

The paper introduces MSTD, a method to detect multi-scale topological domains from 3D genomic maps, showing its effectiveness in identifying promoter-anchored interaction domains and improving accuracy over existing methods.

This study uses a crowdsourcing approach to stratify ALS patients, identifying four distinct clusters with unique predictors and improving outcome prediction.

The paper introduces gkm-DNN, a deep learning framework to improve feature representation from gapped k-mer frequency vectors for sequence-based predictions, demonstrating comparable performance to gkm-SVM.

This study compares eight imputation methods for scRNA-seq data, finding no single method outperforms all others across different tasks and datasets.

The paper identifies and characterizes cell type-specific regulatory elements in the human genome using histone modification analysis across multiple tissues and cell types.