Tianyu Liu

Cell-type-specific polygenic risk scores reveal adipocyte-related interactions with lipids in coronary artery disease

The paper develops cell-type-specific polygenic risk scores for CAD using scRNA-seq data and identifies lipid interactions specific to adipocytes and other cell types.

INSPIRE: interpretable, flexible and spatially-aware integration of multiple spatial transcriptomics datasets from diverse sources

INSPIRE integrates and interprets multiple spatial transcriptomics datasets, revealing tissue structures and biological processes across diverse samples and technologies.

EA-PheWAS: Integrating Phenotype Embeddings with PheWAS for Enhanced Gene-Phenotype Discovery

EA-PheWAS improves gene-phenotype discovery by integrating phenotype embeddings with PheWAS, outperforming conventional methods in detecting associations.

Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states

PaSCient learns patient-level disease representations from scRNA-seq data, enabling disease classification and downstream analyses like dimensionality reduction and patient subgroup discovery.

Evaluating the Utilities of Foundation Models in Single-cell Data Analysis

This study evaluates foundation models for single-cell data analysis across eight tasks, finding that task-specific methods may outperform them in some cases and proposing guidelines for improving FM performance.

spRefine Denoises and Imputes Spatial Transcriptomics with a Reference-Free Framework Powered by Genomic Language Model

spRefine denoises and imputes spatial transcriptomics data using a reference-free deep learning framework, improving data integration and revealing new aging-related biological insights.

scELMo: Embeddings from Language Models are Good Learners for Single-cell Data Analysis

scELMo uses Large Language Models to analyze single-cell data for clustering, batch correction, and cell-type annotation without retraining, outperforming existing methods.

VISTA Uncovers Missing Gene Expression and Spatial-induced Information for Spatial Transcriptomic Data Analysis

VISTA improves spatial transcriptomic data by imputing missing gene expression and enables downstream analyses like ligand-receptor discovery and spatial velocity inference.

Improving polygenic risk prediction performance through integrating electronic health records by phenotype embedding

This paper introduces EEPRS, a framework that improves polygenic risk prediction by integrating electronic health records through phenotype embeddings, showing significant performance gains over traditional methods.

UNICORN: Towards Universal Cellular Expression Prediction with a Multi-Task Learning Framework

UNICORN improves gene expression and multi-omic phenotype prediction using multi-task learning with foundation model embeddings and custom loss functions.

spVelo: RNA velocity inference for multi-batch spatial transcriptomics data

spVelo infers RNA velocity in multi-batch spatial transcriptomics data, showing improved velocity consistency, transition accuracy, and direction correctness compared to existing methods.

scMODAL: A general deep learning framework for comprehensive single-cell multi-omics data alignment with feature links

scMODAL is a deep learning framework for aligning single-cell multi-omics data using feature links, effectively removing unwanted variation and identifying cell subpopulations.

Building A Unified Model for Drug Synergy Analysis Powered by Large Language Models

This paper introduces BAITSAO, a unified model for drug synergy prediction using large language models, showing improved performance over existing methods.

Modeling and predicting single-cell multi-gene perturbation responses with scLAMBDA

scLAMBDA models and predicts single-cell transcriptional responses to genetic perturbations, outperforming existing methods in accuracy and generalization.

CosGeneGate Selects Multi-functional and Credible Biomarkers for Single-cell Analysis

CosGeneGate selects non-redundant, cell-type-specific marker genes for single-cell analysis, outperforming existing methods in downstream applications.

ResPAN: a powerful batch correction model forscRNA-seq data through residual adversarialnetworks

ResPAN corrects batch effects in scRNA-seq data using a deep learning framework, outperforming existing methods in batch correction and biological information preservation.