Xinghua Lu

A Time-Resolved Single-Cell Atlas Reveals Infection-Status, Age-, and Sex-Dependent Immune Responses Drive Viral Disease Severity

This study uses time-resolved single-cell RNA sequencing in mice to show age and sex influence immune responses and viral disease severity through altered gene expression and inflammation.

Causal Modeling Reveals Cell-Cell Communication Dynamics in the Tumor Microenvironment During Anti-PD-1 Therapy in Breast Cancer Patients

This study uses single-cell RNA-seq data to analyze cell-cell communication changes in breast cancer patients during anti-PD-1 therapy, identifying key pathways and potential therapeutic targets.

Inferring Personalized Cell-Cell Communication Networks in Colorectal Cancer with Individualized Causal Discovery

This paper develops a framework to infer individualized cell-cell communication networks in colorectal cancer using causal discovery methods applied to single-cell RNA-seq data.

Deconvoluting single-cell transcriptomics reveals cellular programs regulated by cell-cell communication in colorectal cancer

The paper uses single-cell data to identify gene expression modules regulated by cell-cell communication in colorectal cancer and validates findings with spatial transcriptomics.

Current transcriptome database and biomarker discovery for immunotherapy by immune checkpoint blockade

This paper reviews biomarkers for immune checkpoint blockade therapy, compares existing databases, and introduces IOhub, a web portal for benchmarking biomarkers using bulk and single-cell transcriptome datasets.

An interpretable deep learning framework for genome-informed precision oncology

This paper introduces a deep learning framework that improves drug response prediction in cancer by modeling cellular state from somatic genome alterations.

Accurate estimation of rare cell type fractions fromtissue omics data via hierarchical deconvolution

HiDecon estimates rare cell type fractions in bulk transcriptomics data using hierarchical deconvolution with single-cell references and cell type trees.

Interpretable deep learning for chromatin-informed inference of transcriptional programs driven by somatic alterations across cancers

The paper introduces CITRUS, a deep learning model that infers transcriptional programs influenced by somatic alterations across 17 cancer types using genomic, transcriptomic, and epigenomic data from The Cancer Genome Atlas.

De novo Prediction of Cell-Drug Sensitivities Using Deep Learning-based Graph Regularized Matrix Factorization

This paper introduces DeepGRMF, a deep learning model that predicts cell-drug sensitivities by integrating drug structures, signaling impacts, and cell states, outperforming existing methods on cancer datasets.

PEAK2VEC ENABLES INFERRENCE OF TRANSCRIPTIONAL REGULATION FROM ATAC-SEQ

The paper introduces peak2vec, a method that uses a modified convolutional neural network to infer transcriptional regulation from ATAC-seq data, showing improved performance in distinguishing TFs compared to conventional methods.

New Gene Embedding Learned from Biomedical Literature and Its Application in Identifying Cancer Drivers

This study learns gene embeddings from biomedical literature to uncover functional relationships and improve identification of cancer driver genes and protein complexes.

Learning to Encode Cellular Responses to Systematic Perturbations with Deep Generative Models

This study uses deep generative models to learn representations of transcriptomic data from cells under various perturbations, revealing relationships between perturbagens and drug-target mappings.

Revealing the impact of genomic alterations on cancer cell signaling with a partially transparent deep learning model

This paper introduces RINN, a deep learning model with L1 regularization to map genomic alterations to cancer signaling pathways, showing partial interpretability and predictive accuracy for differential expression.

Tumor-specific Causal Inference (TCI): A Bayesian Method for Identifying Causative Genome Alterations within Individual Tumors

This paper introduces a Bayesian method to identify causative genome alterations in individual tumors by inferring their impact on transcriptomic changes.