Xiaoqian Jiang

GlioVision predicts four glioma molecular biomarkers from MRI data using a multi-modal framework, achieving high AUC scores across multiple cohorts.

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.

PerturbLDM predicts single-cell transcriptional responses to perturbations using a latent diffusion model, outperforming existing methods in drug-dose-cell line combinations and capturing key biological programs.

This paper develops a low-input, ultrasensitive diagnostic platform for detecting Avocado Sunblotch Viroid using RPA-CRISPR and nanopore-array fluorescence readout, achieving a detection limit of 1.68 copies/L.

This paper introduces a Multiple Domain Adversarial Neural Network (MDANN) to improve fairness in disease prediction by reducing biases in brain imaging data for Alzheimer's and Autism populations.

HeteroRepur models a heterogeneous disease graph for depression drug repurposing using graph neural networks, identifying new drug candidates and outperforming baseline methods.

The paper introduces a privacy-preserving genotype imputation method using haplotype classifiers, improving accuracy and throughput compared to linear models.

FedGMMAT enables privacy-preserving genetic association testing across institutions using federated learning and homomorphic encryption.

ProxyTyper generates proxy panels to protect genetic data privacy during genotype imputation with minimal accuracy loss.

This paper evaluates local hidden Markov models for genotype imputation, showing they can accurately impute common, uncommon, and rare variants.

This paper develops a privacy-aware kinship inference method for admixed populations using reference panels and homomorphic encryption to protect genetic data.

The paper introduces a secure imputation server that provides encrypted genotype imputation with provable privacy, demonstrating its utility through benchmarking and simulated GWAS.

SVAT securely outsources variant annotation and genotype aggregation using homomorphic encryption to protect genetic privacy during analysis and data sharing.

This paper develops secure genotype imputation methods using homomorphic encryption, showing comparable accuracy and efficiency to non-secure methods while protecting genetic data privacy.

This paper develops a drug synergy prediction model using transfer learning to address data scarcity in understudied cancer tissues.

HaploHide hides individual haplotypes within population haplotypes to protect privacy during genetic data sharing without changing infrastructure.