Qianqian Song

irAEGIS: Pathway-guided interpretable prediction of immune-related adverse events

irAEGIS predicts immune-related adverse events from pre-treatment scRNA-seq data using a pathway-guided interpretable model, outperforming existing methods and identifying biologically relevant immune programs.

Mechanotransduction tuned by intermediate filaments promotes DNA repair in stiff environments

The paper shows that rigid tissue environments enhance DNA repair efficiency and may contribute to cancer risk by promoting survival of damaged cells.

Octave: Scale-resolved Evaluation of Spatial Gene Expression Prediction from Histology

The paper introduces OCTAVE, a scale-resolved evaluation method for spatial gene expression prediction from histology, showing that fine-scale differences are missed by standard metrics.

Socioeconomic and Clinical Determinants Driving Access to BRCA Genetic Testing in Cancer : A Case-Control Study Using Observational Electronic Health Records Across Multiple Sites

This study identifies socioeconomic and clinical factors influencing BRCA genetic testing uptake among cancer patients using electronic health records and develops a predictive model to identify those at risk for underuse.

MVCBench: A Multimodal Benchmark for Drug-induced Virtual Cell Phenotypes

MVCBench evaluates drug molecular and gene representation methods for predicting drug-induced multimodal cell phenotypes using transcriptomic and imaging data.

SpaGene: A Deep Adversarial Framework for Spatial Gene Imputation

SpaGene improves spatial transcriptomics by imputing missing gene expressions, achieving higher accuracy than existing methods and revealing immune dynamics in lung tumors.

A real-world cohort study of immune-related adverse events in patients receiving immune checkpoint inhibitors

This study identifies risk factors and patterns of immune-related adverse events (irAEs) in patients receiving immune checkpoint inhibitors using real-world data.

SpaIM: Single-cell Spatial Transcriptomics Imputation via Style Transfer

SpaIM improves spatial transcriptomics by imputing missing gene expressions using scRNA-seq data, outperforming 12 existing methods across 53 datasets.

GatorST: A Versatile Contrastive Meta-Learning Framework for Spatial Transcriptomic Data Analysis

GatorST improves spatial transcriptomic analysis by integrating graph-based modeling, pseudo-labeling, and contrastive meta-learning to enhance spatial domain identification and downstream tasks.

Gene Expression Prediction from Histology Images via Hypergraph Neural Networks

This paper introduces HGGEP, a hypergraph neural network model that predicts gene expression from histology images by capturing cell morphology and higher-order feature associations.

xSiGra: Explainable model for single-cell spatial data elucidation

xSiGra is a graph-based AI model that identifies interpretable features in spatial single-cell data, showing that cell activity is influenced by neighboring cells and revealing endothelial-tumor interactions.

SiGra: Single-cell spatial elucidation through image-augmented graph transformer

SiGra integrates spatial images and transcriptomics data to enhance spatial domain detection and improve characterization of cellular heterogeneity and communication in tissues.

SpaRx: Elucidate single-cell spatial heterogeneity of drug responses for personalized treatment

SpaRx identifies spatial cellular heterogeneity in drug responses across tumor lesions and reveals mechanisms of drug resistance through a graph-based domain adaptation model.

scGCN: a Graph Convolutional Networks Algorithm for Knowledge Transfer in Single Cell Omics

scGCN transfers labels across single-cell omics datasets with superior accuracy by using a graph-based AI model.

scLM: automatic detection of consensus gene clusters across multiple single-cell datasets

scLM detects consensus gene clusters across multiple single-cell datasets, improving accuracy over existing methods and enabling novel comparative analysis.

DSTG: Deconvoluting Spatial Transcriptomics Data through Graph-based Artificial Intelligence

DSTG deconvolutes spatial transcriptomics data to reveal cell compositions and spatial architecture of cellular heterogeneity in tissues.