Tinyi Chu

CONCISE improves spatial ligand-receptor interaction inference by accounting for spatial autocorrelation and measurement errors, reducing false positives and enhancing detection power in spatial transcriptomics data.

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

The paper analyzes transcriptomic changes in metastatic pancreatic cancer using a patient's autopsy data to identify site-specific gene programs and clonal phylogeny.

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

This study identifies ASCL1 as a critical driver of neuroendocrine lineage transition in prostate cancer using an in vivo model and spatial transcriptomics.

This study uses plasma cell-free RNA profiles to monitor immune dynamics and predict graft-versus-host disease (GVHD) after hematopoietic stem cell transplantation.

This paper introduces dHICA, a deep learning framework that predicts histone modifications using chromatin accessibility and DNA sequences, outperforming existing methods and enabling downstream applications.

The paper uses machine learning to show that transcription predicts histone marks and chromatin states, and that transcription is required for maintaining active and repressive histone modifications.

The paper develops BayesPrism, a Bayesian method to infer cellular composition and gene expression from bulk RNA-seq using scRNA-seq as prior, revealing tumor-microenvironment interactions across multiple cancer types.

Funmap2 is an R package for QTL mapping with longitudinal phenotypes, using a functional mapping framework that integrates biological knowledge and automatically selects models.

The paper introduces an improved dREG implementation for identifying transcription initiation regions using PRO-seq data, showing higher accuracy, resolution, and efficiency.

This study introduces ChRO-seq to map nascent transcription in glioblastoma and identifies enhancers and transcription factors driving GBM subtypes and clinical outcomes.

The paper compares nascent transcription in primates to identify evolutionary patterns in coding and non-coding transcription, finding that transcription factor binding sites and adaptive substitutions drive species-specific differences.