Lin Liu

TACO detects presymptomatic Long COVID by combining causal inference with a foundation model, achieving higher precision with fewer features and no hyperparameter tuning.

This paper reviews computational methods and datasets for understanding Long COVID's mechanisms and developing diagnostic and therapeutic strategies using multi-omics data.

This paper introduces a dynamic causal inference method to identify cooperative cancer driver genes by analyzing gene interactions across cancer progression, showing significant overlap with known drivers and uncovering novel ones.

This paper develops a three-in-one mucosal vaccine, 3Rs-NC, that elicits broad neutralizing antibodies against three ACE2-using sarbecovirus clusters and provides durable protection in mice.

This paper introduces DGBCox, a stable prediction method for breast cancer prognosis under data distribution shift, showing improved accuracy and stability compared to existing methods.

The paper introduces Scan, a framework that infers sample-specific miRNA regulation from bulk and single-cell RNA-sequencing data using multiple network inference methods.

GP-HTNLoc is a multi-label subcellular localization model for ncRNAs that addresses class imbalance and outperforms existing methods.

This paper introduces SCOM, a framework to identify ncRNA synergistic competition across cancers, revealing hub ncRNAs and potential biomarkers for diagnosis and prognosis.

The paper introduces CSmiR, a method to identify cell-specific miRNA-mRNA regulatory networks using single-cell co-sequencing data, revealing unique miRNA regulation in individual cells.

pDriver identifies personalized coding and miRNA cancer drivers for individual patients using gene networks and outperforms existing methods on TCGA datasets.

DriverGroup identifies driver gene groups in cancer by analyzing gene expression and interaction data, showing improved performance over existing methods in detecting gene group regulation and providing insights into breast cancer.

This paper introduces a pseudo-time causality method to identify miRNA-mRNA interactions during biological processes, showing improved performance over existing methods in both single-cell and bulk data.

This paper introduces scPrognosis, a method using scRNA-seq data to improve breast cancer prognosis by analyzing EMT-related gene expression dynamics, outperforming bulk RNA-seq based methods.

The paper presents methods and tools for predicting cell locations in Drosophila embryos using single-cell transcriptomic data, achieving top results in two sub-challenges.

LMSM identifies lncRNA-related miRNA sponge modules in breast cancer using heterogeneous data, finding subtype-specific modules and improved classification performance over baselines.

The paper introduces miRsyn, a causal inference framework to identify miRNA synergism using observational data, finding that many miRNA pairs with shared targets do not synergize at the expression level.

miRspongeR is an R/Bioconductor package that identifies and analyzes miRNA sponge interaction networks and modules using seven methods and an integrative approach.

This paper identifies miRNA-mRNA regulatory relationships in breast cancer using invariant causal prediction and shows improved performance over existing methods.

miRBaseConverter provides tools to convert and retrieve miRNA information across miRBase versions, addressing inconsistencies in miRNA data.

The paper proposes a multi-objective splitting procedure to estimate heterogeneous treatment effects by balancing fitness and heterogeneity criteria, achieving better performance than existing methods.