Tongjun Gu

This paper introduces SurvMOCA-GNN, a multi-omics integration framework that improves patient stratification in AML by incorporating biological networks and clinical data.

This study identifies RNA editing-defined cellular states in CMML that correlate with clinical outcomes and therapeutic response.

This study identifies CEBPA-N-AML as having enhanced engraftment and defines a novel LSC signature in CEBPA-N-AML.

The paper identifies RNA editing signatures associated with AML disease stage and risk, showing their potential for peripheral blood-based disease assessment.

SurvMarker identifies survival-associated molecular features using PCA-based weighted scoring and provides an R package with documentation and examples.

The paper identifies cell type-specific RNA editing patterns in AML across disease states using single-cell and pseudo-bulk analyses, revealing condition-specific regulatory programs.

The paper identifies gene and miRNA biomarkers for AML risk stratification using PCA and SVM, validated across cohorts with high AUCs and regulatory insights.

This study identifies B4GALT1 as a key regulator of HSPC lineage decisions by modulating glycosylation and mechanosensing in the bone marrow niche.

The paper identifies miR-320a as a regulator of the unfolded protein response by analyzing TSS-miRNA targets in colorectal cancer cells using AGO-qCLASH.

The paper introduces miTAR, a hybrid deep learning model for miRNA target prediction, achieving higher accuracy than existing methods on two datasets.

The paper identifies genes associated with A-to-I RNA editing in four cancers using a logistic regression model and highlights cancer-specific and shared regulatory patterns.