Hong Zheng

The paper identifies a novel framework to quantify immune dysregulation in critical illness by analyzing transcriptomic data across multiple cohorts.

The paper identifies a conserved immune signature linked to infection severity, risk factors, and treatment response using multi-cohort transcriptomic and proteomic data.

This paper benchmarks HLA genotype prediction from single-cell RNA-seq data against molecular genotyping, showing improved accuracy with composite models and meta-analytic approaches.

This paper proposes a meta-learning framework for genomic survival analysis, showing it outperforms transfer learning with fewer samples and identifies important genes and pathways in cancer.

The paper develops a 6-mRNA classifier using non-COVID-19 viral infection data to predict COVID-19 severity, achieving high accuracy in independent cohorts.

This paper benchmarks lncRNA quantification methods on cancer RNA-Seq data, finding that pseudoalignment methods with full transcriptome annotation outperform alignment-based methods.

This paper introduces a deep learning framework called DAPL for imputing missing values in genomic data, showing improved performance and reduced computational cost compared to traditional methods.