Shaojun Tang

The paper determines sample size requirements for ML classification in bulk RNA-seq data and finds that ML methods generally need larger samples than differential analysis power analysis.

EpiTADformer uses epigenomic signal embeddings to detect TAD boundaries with higher resolution than Hi-C-based methods.

This study identifies molecular features of triple-negative apocrine carcinoma through proteogenomic analysis, revealing resistance mechanisms and suggesting alternative therapeutic strategies.

The paper profiles proteome, phosphoproteome, and glycoproteome of 54 cancer cell lines using MS and RPPA, revealing tissue-specific patterns and drug targets.

This paper integrates bulk and single-cell transcriptomic data from glaucoma tissues to identify immune-related pathways and T-cell infiltration as key features of the disease.

The paper introduces neoantigeR, a pipeline for identifying tumor-specific peptide epitopes (neoantigens) from sequencing data to aid in cancer immunotherapy.