Li Chen

This study identifies TREM2 as a regulator of myeloid cell function and immune dysregulation in pulmonary hypertension, showing its role in disease progression and potential as a therapeutic target.

This paper introduces GraphScrDom, a contrastive learning model for spatial domain detection in spatial transcriptomics using weak supervision and reference data, showing strong performance across platforms and resolutions.

The paper maps spatial metabolome coherence across mouse brain regions using MALDI imaging and optimal transport, showing preserved coherence in Alzheimer's model despite metabolic changes and demonstrating intervention effects.

BayesCNet improves inference of cell type-specific regulatory networks by leveraging cell type hierarchy, outperforming existing methods, especially for rare cell types.

This paper introduces a Bayesian framework for detecting circadian rhythmicity biomarkers across the genome, showing improved false discovery rate control and performance in RNA-sequencing data.

This study identifies hyper-glycosylation as a driver of Alzheimer's disease through metabolic analysis and interventions, showing its impact on cognitive decline and mortality.

Deep5hmC predicts genome-wide 5hmC modification using a multimodal deep learning model, outperforming unimodal models and existing methods in both qualitative and quantitative predictions.

This paper introduces scaDA, a statistical method for differential chromatin accessibility analysis in scATAC-seq data, showing improved power and FDR control compared to existing methods.

The paper introduces MpraVAE, a deep generative model that generates and augments regulatory variant data from MPRA, improving prediction performance for regulatory variants in autoimmune diseases.

MPRAVarDB provides a database and web server to explore the regulatory effects of genetic variants using MPRA data across multiple cell lines and diseases.

MetaVision3D converts serial 2D MALDI mass spectrometry imaging sections into a 3D spatial metabolome atlas using computer vision techniques.

The paper presents a method for simultaneous spatial analysis of metabolome, lipidome, and glycome from a single tissue section using mass spectrometry imaging and a computational framework called Sami.

Destin2 improves cross-modality analysis of scATAC-seq data by integrating multiple epigenomic features for dimension reduction, clustering, and trajectory inference.

TIVAN-indel scores noncoding sindels for their regulatory potential using XGBoost and multi-omics features, achieving strong cross-tissue prediction performance.

DeepPHiC predicts promoter-centered chromatin interactions using a deep learning model that outperforms existing methods and is robust to anchor distance features.

DeepPerVar predicts epigenetic signals and prioritizes causal variants in Alzheimer's disease using whole genome sequencing and epigenetic data.

The paper uses deep transfer learning to predict functional noncoding variants, outperforming existing methods on MPRA and GWAS datasets.

The paper develops multi-task deep autoencoders to predict Alzheimer's disease progression using longitudinal DNA methylation data from peripheral blood and shows improved performance over existing methods.

WEVar integrates functional scores from multiple methods to predict noncoding regulatory variants, outperforming existing approaches in simulation and empirical studies.

The paper evaluates seven circadian rhythm detection algorithms using empirical datasets and simulations, providing guidelines for selecting methods based on data characteristics.

BAMM-SC clusters droplet-based scRNA-seq data from multiple individuals by accounting for batch effects and heterogeneity, improving accuracy over existing methods.

Destin is a framework for analyzing scATAC-seq data, outperforming existing methods in clustering and identifying cell type-specific associations with schizophrenia GWAS loci.

GMPR is a normalization method for microbiome sequencing data that addresses zero-inflation, outperforming existing methods in simulations and real datasets.

This study identifies virus- and strain-specific molecular signatures of ZIKV infection in human cortical neural progenitors, showing distinct impacts on DNA replication and apoptosis.