Yunhe Liu

UniST reconstructs dense 3D spatial transcriptomics data from sparse serial sections, restoring structural continuity and biologically meaningful expression patterns in multiple tissue contexts.

COSIE is a computational framework that integrates multiple spatial omics modalities to generate high-resolution molecular landscapes, outperforming existing methods across diverse datasets.

UTOPIA quantifies confidence in virtual spatial transcriptomics predictions across scales, improving reliability and preventing false conclusions.

REMAP reconstructs spatial tissue architecture from scRNA-seq using deep learning and ST references, revealing microenvironmental features and cancer subtypes.

This study introduces a deep learning model called spacer to analyze spatially resolved transcriptomics data, revealing novel insights into cellular recruitment mechanisms in tumors and heart tissue during myocarditis.

S2Omics automatically selects regions of interest from histology images to maximize molecular information content in spatial omics experiments, improving reproducibility and downstream biological discovery.

The paper improves scRNA-seq analysis by using deep generative models to identify and remove noise cells, enhancing clustering and gene analysis consistency.

The paper introduces an attention-based deep multiple instance learning model for circRNA identification from lncRNA, showing improved performance and identifying key sequence motifs.

This study simulates scRNA-seq data to evaluate how sequencing parameters and clustering algorithms affect cell clustering accuracy.