Xueying Fan

A Systematic Comparison of Single-Cell Perturbation Response Prediction Models

The paper benchmarks 13 models for predicting single-cell perturbation responses across 25 datasets, finding performance varies with perturbation effect size and evaluation metric.

Virtual-cell verification enables self-auditing AI discovery for immune rejuvenation

The paper introduces a framework for self-auditing AI in drug discovery, using verifiers to validate predictions and adjust objectives based on experimental results.

Graph-based Contrastive Learning Enables Unified Integration and Niche Transfer Across Single-Cell and Spatial Multi-Omics

Garfield integrates single-cell and spatial multi-omics data into a shared space, outperforming existing methods in identifying spatial niches and revealing immune microenvironment heterogeneity.

Peripheral blood cell-type and sex-specific signatures of alcohol misuse revealed by single-cell transcriptomics

This study uses scRNA-seq on PBMCs to identify cell-type and sex-specific immune signatures associated with alcohol misuse and its dose-dependent effects.

Multimodal foundation model predicts zero-shot functional perturbations and cell fate dynamics

PertFormer, a multimodal foundation model, predicts zero-shot functional perturbations and cell fate dynamics, outperforming existing methods and identifying novel tumor treatment targets.

Characterization of the human fetal rete region by single cell transcriptional analysis of gonads and mesonephros/epididymis

The paper uses single-cell transcriptomics to study fetal rete testis development, identifying molecular markers and cell types in human gonads and mesonephros/epididymis.

A clusterability measure for single-cell transcriptomics reveals phenotypic subpopulations

The paper introduces SIGMA, a clusterability measure to identify meaningful subpopulations in single-cell transcriptomics data, leading to the discovery of previously overlooked phenotypes.