Yue Cao

BenchHub provides a modular ecosystem for community-focused benchmarking in computational biology by linking datasets, metrics, and ground truth to improve reproducibility and sustainability.

GHIST+ reconstructs tissue-wide molecular maps from H&E histology, enabling cohort-scale molecular reconstruction from sparse spatial transcriptomic data.

This study evaluates how large language models generate summaries of bioinformatics analyses, finding they produce readable and safe summaries but often misinterpret visualizations and lack novel insights.

GHIST predicts spatial gene expression at single-cell resolution from histology images, showing superior performance across different resolutions and datasets.

This paper benchmarks single-cell methods by analyzing 282 papers, highlighting challenges in combining benchmarking studies and preventing fatigue.

scClassify2 is a message-passing neural network for cell state identification, outperforming existing methods in annotating adjacent cell states and applicable to multiple data types.

The paper identifies distinct glutamine metabolism in a subset of proliferating cells using pathway-centric metabolomic analysis of cancer and non-cancer cell lines.

The paper benchmarks spatially resolved gene expression simulation models using a framework that evaluates 13 methods across 10 datasets and 35 metrics, highlighting performance differences and factors affecting model accuracy.

scMerge2 integrates large-scale multi-sample multi-condition single-cell data across cohorts, improving disease progression discrimination through cell-type expression signatures.

This study benchmarks analytical combinations for predicting COVID-19 outcomes using scRNA-seq data, finding that ensemble learning and multi-view features improve performance.

Scope+ provides an open-source architecture for accessing and analyzing large single-cell atlases at the cell level, demonstrated through the Covidscope portal for COVID-19 data.

scFeatures creates interpretable molecular representations of single-cell and spatial data to predict disease outcomes using diverse feature types.

This study benchmarks 12 scRNA-seq simulation methods using 35 experimental datasets, identifying performance differences and limitations in capturing biological signals and heterogeneity.

scClassify improves cell type classification in scRNA-seq data by using ensemble learning, achieving more accurate and fine-grained results than original publications.