Thuc Duy Le

TACO: TabPFN Augmented Causal Outcomes for Early Detection of Long COVID

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

Omics-Based Computational Approaches for Biomarker Identification, Prediction, and Treatment of Long COVID

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

Integrative Multi-Omics Framework for Causal Gene Discovery in Long COVID

This paper identifies 32 causal genes for Long COVID using a multi-omics framework combining TWMR and CT, revealing novel genetic factors and symptom subtypes.

Identifying cooperative genes causing cancer progression with dynamic causal inference

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.

Stable breast cancer prognosis

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.

Scanning sample-specific miRNA regulation from bulk and single-cell RNA-sequencing data

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.

Pan-cancer characterization of ncRNA synergistic competition uncovers potential carcinogenic biomarkers

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

Exploring cell-specific miRNA regulation with single-cell miRNA-mRNA co-sequencing data

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.

PAN: Personalized Annotation-based Networks for the Prediction of Breast Cancer Relapse

This paper introduces PAN, a method to create sample-specific gene networks using annotations, improving breast cancer relapse prediction compared to existing methods.

pDriver: A novel method for unravelling personalised coding and miRNA cancer drivers

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

DriverGroup: A novel method for identifying drivergene groups

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.

GraphDTA: Predicting drug-target binding affinity with graph neural networks

Representing drugs as molecular graphs, GraphDTA lowers drug-target affinity prediction error to MSE 0.229 on Davis and 0.139 on Kiba versus deep learning baselines.

A Pseudo-Temporal Causality Approach to Identifying miRNA-mRNA Interactions During Biological Processes

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.

Predicting cellular position in the Drosophila embryo from Single-Cell Transcriptomics data

The paper predicts cellular positions in the Drosophila embryo using scRNA-seq data by benchmarking methods against spatially annotated genes.

A novel single-cell based method for breast cancer prognosis

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 winning methods for predicting cellular position in the DREAM single cell transcriptomics challenge

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: a modular approach for identifying lncRNA related miRNA sponge modules in breast cancer

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

Identifying miRNA synergism using multiple-intervention causal inference

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: an R/Bioconductor package for the identification and analysis of miRNA sponge interaction networks and modules

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

Identifying miRNA-mRNA regulatory relationships in breast cancer with invariant causal prediction

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

miRBaseConverter: An R/Bioconductor Package for Converting and Retrieving miRNA Name, Accession, Sequence and Family Information in Different Versions of miRBase

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

Estimating heterogeneous treatment effects by balancing heterogeneity and fitness

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.