Qiang Kang

RepGene: Auditing Condition-Specific Fusion Biases for Multi-View Gene Representations

The paper evaluates multi-view gene representations under a matched contract, showing condition-dependent fusion operator rankings across different view combinations and tasks.

A unified spatial transcriptome profiling of ten mouse organs

The paper presents a unified spatial transcriptomic dataset of 10 mouse organs, providing high-resolution expression matrices paired with histological images for method development and benchmarking.

BiOmics: A Foundational Agent for Grounded and Autonomous Multi-omics Interpretation

BiOmics introduces an AI agent that improves multi-omics interpretation by combining reasoning and embedding spaces, outperforming existing methods in variant discovery, cell annotation, and drug repurposing.

MicroGenomer: A Foundation Model for Transferable Microbial Genome Representations Enabling Multi-scale Genomic Understanding and Ecophysiological Trait Prediction

CellBin:a generalist framework to process spatial omics data to cell level

CellBin processes spatial omics data to create cell-level matrices, outperforming existing methods across multiple platforms and omics types.

Prediction of soil probiotics based on foundation model representation enhancement and stacked aggregation classifier

The paper develops a method to predict soil probiotics using enhanced foundation model representations and a stacked aggregation classifier, achieving high accuracy and AUC on both balanced and imbalanced datasets.

Stereopy: modeling comparative and spatiotemporal cellular heterogeneity via multi-sample spatial transcriptomics

Stereopy provides a framework for analyzing multi-sample spatial transcriptomics data to model comparative and spatiotemporal cellular heterogeneity through three key algorithms.

CellBinDB: A Large-Scale Multimodal Annotated Dataset for Cell Segmentation with Benchmarking of Universal Models

CellBinDB provides a large-scale multimodal annotated dataset for cell segmentation and benchmarks seven state-of-the-art methods.

Single-cell multi-omics and spatial multi-omics data integration via dual-path graph attention auto-encoder

This paper introduces SSGATE, a dual-path graph attention auto-encoder for integrating single-cell and spatial multi-omics data, showing improved performance and robustness over existing methods.

Generating single-cell gene expression profiles for high-resolution spatial transcriptomics based on cell boundary images

The paper updates a software tool to generate single-cell spatial gene expression profiles using cell boundary images from Stereo-seq data, showing improved performance on mouse liver and Arabidopsis seed datasets.

BatchEval Pipeline: Batch Effect Evaluation Workflow for Multiple Datasets Joint Analysis

BatchEval Pipeline evaluates batch effects in multi-dataset transcriptomics analysis and provides a report to guide batch correction.

spatiAlign: An Unsupervised Contrastive Learning Model for Data Integration of Spatially Resolved Transcriptomics

spatiAlign integrates spatially resolved transcriptomics datasets using contrastive learning, improving batch effect removal and enabling downstream analysis across multiple tissue sections.

CellBin: a highly accurate single-cell gene expression processing pipeline for high-resolution spatial transcriptomics

CellBin processes high-resolution spatial transcriptomics data to generate accurate single-cell gene expression profiles, improving accuracy and efficiency in mouse brain tissue analysis.