Shuangxi Ji

TmSNet predicts tumor cell-specific total mRNA expression from multi-omic data, achieving high accuracy across cancer types and external cohorts.

The paper develops CliPP to estimate subclonal mutation load (sML) and shows it predicts survival and immunotherapy response in cancers with low to moderate TMB.

The paper introduces MuSE2.0, a tool that accelerates somatic mutation calling for whole-genome and whole-exome sequencing data from heterogeneous tumor samples, achieving significant speed improvements over existing methods.

DeMixSC improves deconvolution accuracy by using single-cell RNA-seq and a benchmark dataset to account for technological discrepancies in complex tissue samples.

CliPP reconstructs subclonal architecture in cancer DNA sequencing data efficiently and accurately, outperforming existing methods in speed while maintaining high concordance with consensus calls.

The paper quantifies tumor-specific total mRNA expression from bulk data and shows its association with clinical outcomes across 15 cancer types.

This paper introduces DeepCDpred, a method that predicts inter-residue distances and contacts to improve protein structure prediction, showing better results than contact prediction alone.