Xingzhong Zhao

Associate Research Scientist, Yale UniversityBiomedical Informatics & Data Science

Brain image diffusion MRI, coloured by fibre directionGenome association scan

I study how genetic variation shapes the human body as seen in medical images, with a focus on brain ageing and neurological disease. I use AI to turn brain and heart scans into heritable traits, then map those traits across the genome in large biobanks.

I build tools to make this possible at scale, including TorchGWAS, which runs genome-wide association tests for thousands of image-derived phenotypes on a GPU. My PhD in Biomedical Engineering at Fudan University covered neuroimaging genomics and gene regulation in brain disorders. Before that, I trained in computer science.

2026 – now
Associate Research ScientistBiomedical Informatics & Data Science, Yale University
2026
Faculty AssociateUTHealth Houston
2024 – 2025
Postdoctoral FellowUTHealth Houston
2021 – 2024
Ph.D., Biomedical EngineeringFudan University
2018 – 2021
M.S., Biomedical EngineeringFudan University

From voxels to variants

Each project follows the same path: from images, to learned traits, to genetic associations, to biological mechanisms.

  1. Images

    Diffusion and structural brain MRI and cardiac MRI from large population biobanks.

  2. Representations

    Unsupervised and contrastive deep learning that turns each image into compact, heritable endophenotypes.

  3. Associations

    GPU-accelerated GWAS that tests thousands of phenotypes, including in samples with related individuals.

  4. Mechanisms

    Enhancer–promoter maps, cell type-specific Mendelian randomization and gene prioritization to explain the hits.

Selected work

Papers I led as first or co-first author. # marks equal contribution.

All publications

# co-first author, * corresponding author. Titles link to the paper DOI where available, otherwise to a Google Scholar search. See the full list on Google Scholar.

2026

  1. A review of self-supervised imaging phenotypes for genome-wide association studies

    K Patel, X Zhao, Z Xie, D Zhi

    Communications Biology

  2. TorchGWAS2: Cost-effective phenome- and genome-wide association testing in related samples

    M Zhang, Z Xie, SS Nasab, N Wang, X Zhao, T Alkis, J Barnard, et al.

    medRxivPreprint

  3. PerturbLDM: conditional latent diffusion for modelling single-cell perturbation responses

    L Yu, KL Hsieh, Y Chu, Q Lan, X Zhao, YC Hsu, CS Wood, L Rasmy, et al.

    bioRxivPreprint

  4. Deciphering cell type-specific causal genetic effects on brain imaging-derived phenotypes and disorders with single-cell Mendelian randomization

    A Yang#, X Zhao#, XM Zhao, YT Yang

    PLOS Computational BiologyCo-first author

  5. EIGNN: An explainable imaging-genetic neural network for robust Alzheimer's disease risk prediction

    ZC Zhang#, Z Cai#, X Zhao#, J Cao, F Chen, J Ding, YT Yang, XM Zhao

    IEEE Transactions on Medical ImagingCo-first author

  6. Genetic architecture of white matter microstructure captured by unsupervised deep representation learning of fractional anisotropy maps

    X Zhao, Z Xie, W He, HY Koh, B Guo, H Chen, M Fornage, D Zhi

    Nature CommunicationsFirst author

  7. Replicability of unsupervised deep learning derived image phenotypes

    T Xia, SMS Islam, Z Xie, X Zhao, D Zhi

    bioRxivPreprint

  8. Learning dynamics of unsupervised deep learning reveal epoch-specific genetic architectures of brain morphology

    SMS Islam, T Xia, X Zhao, Z Xie, D Zhi

    bioRxivPreprint

  9. Learning heritable multimodal brain representation via contrastive learning

    D Zhi, T Xia, X Zhao, SMS Islam, K Mohammed, Z Xie

    Research SquarePreprint

  10. Uncovering genetic architecture of the heart via genetic association studies of unsupervised deep learning derived endophenotypes

    L You#, X Zhao#, Z Xie#, KA Patel, C Chen, D Kitkungvan, KK Mohammed, N Narula, E Arbustini, CK Cassidy, J Narula, D Zhi

    Nature Communications (accepted)Co-first author

  11. TorchGWAS: GPU-accelerated GWAS for thousands of quantitative phenotypes

    X Zhao, Z Xie, SM Saiful, T Xia, D Zhi

    arXiv:2604.21095First authorPreprint

  12. A trispecific antibody engaging T cells with tumour and myeloid cells augments antitumour immunity

    C Yang#, S Guo#, K Ye#, Y Ding#, X Zhao, YT Yang, B Sun, S Qian, MC Cai, et al.

    Nature Biomedical Engineering

  13. Impacts of host genetics on gut microbiome composition in Alzheimer's disease

    J Liu, J Cao, L Jia, Z Gan, X Zhao, A Yang, S Lai, F Chen, YT Yang, et al.

    Microbiome

  14. TorchGWAS 1.0: GPU-accelerated GWAS at scale

    X Zhao, Z Xie, SMS Islam, T Xia, C Chen, D Zhi

    Bioinformatics AdvancesFirst author

  15. Sum-h2, enabling genetic discovery for deep learning-derived phenotypes through a fast evaluation framework and arena of performance

    T Xia, Z Xie, X Zhao, SMS Islam, A Naseri, Z Fan, H Chen, D Zhi

    bioRxivPreprint

2025

  1. Unveiling the genetic architecture of white matter tracks through unsupervised deep representation learning of fractional anisotropy images

    X Zhao, W He, Z Xie, M Fornage, D Zhi

    Alzheimer's & Dementia (AAIC abstract)First authorConference

  2. Regulatory genomic circuitry of brain age by integrative functional genomic analyses

    X Zhao, A Yang, J Ding, YT Yang, XM Zhao

    Genomics, Proteomics & BioinformaticsFirst author

  3. Multimodal profiling identifies CD4+ CXCR5+ PD-1– Tfh cells as prognostic and predictive biomarkers in diffuse large B-cell lymphoma

    S Yu, H Kong, H Luo, X Zhao, G Zhu, X Feng, J Yang, X Wu, Y Dai, C Wu, et al.

    Chinese Medical Journal

  4. Spatiotemporally resolved transcriptomics reveals the cellular dynamics of human retinal development

    J Zhang, J Wang, Q Zhou, Z Chen, J Zhuang, X Zhao, Z Gan, Y Wang, et al.

    Nature Communications

  5. Leveraging deep learning to enhance MRI for brain disorders

    Y Dai, R Yakupov, Y Xia, W Tang, T Lett, F Nees, E Polemiti, JC Roy, et al.

    medRxivPreprint

  6. Association between twin status with cognitive, behavioral development and brain structure in early adolescence: a retrospective cohort analysis based on the Adolescent Brain Cognitive Development study

    Q Zhou#, X Zhao#, J Chen#, J Xu, A Yang, Y Xiong, X Yin, XM Zhao, X Li

    European Child & Adolescent PsychiatryCo-first author

2024

  1. Association of birth weight with neuropsychological functioning in early adolescence: A retrospective cohort study

    Q Zhou#, X Zhao#, J Chen#, A Yang, XM Zhao, X Li

    Psychiatry ResearchCo-first author

  2. Effects of open-skill and closed-skill exercise on subthreshold depression in female adolescents: a randomized controlled trial

    Q Gu, X Zhao, L Lin, WP Teo, L Liu, S Yuan

    International Journal of Clinical and Health Psychology

  3. STAB2: an updated spatio-temporal cell atlas of the human and mouse brain

    YT Yang, Z Gan, J Zhang, X Zhao, Y Yang, S Han, W Wu, XM Zhao

    Nucleic Acids Research

2023

  1. Prioritizing genes associated with brain disorders by leveraging enhancer-promoter interactions in diverse neural cells and tissues

    X Zhao#, L Song#, A Yang, Z Zhang, J Zhang, YT Yang, XM Zhao

    Genome MedicineFirst author

  2. Improving Alzheimer's disease diagnosis with multi-modal PET embedding features by a 3D multi-task MLP-mixer neural network

    ZC Zhang, X Zhao, G Dong, XM Zhao

    IEEE Journal of Biomedical and Health Informatics

  3. Deciphering the genetic architecture of human brain structure and function: a brief survey on recent advances of neuroimaging genomics

    X Zhao#, A Yang#, ZC Zhang, YT Yang, XM Zhao

    Briefings in BioinformaticsFirst author

2022

  1. Low-dose aspirin in the prevention of preeclampsia in twin pregnancies: a real-world study

    Q Zhou#, X Zhao#, J Xu, Y Xiong, JFR Barrett, XM Zhao, X Li

    Frontiers in Cardiovascular MedicineCo-first author

2021

  1. Deep learning of brain magnetic resonance images: A brief review

    X Zhao, XM Zhao

    MethodsFirst author

  2. Integration of multimodal data for deciphering brain disorders

    J Chen, G Dong, L Song, X Zhao, J Cao, X Luo, J Feng, XM Zhao

    Annual Review of Biomedical Data Science

  3. Identifying age-specific gene signatures of the human cerebral cortex with joint analysis of transcriptomes and functional connectomes

    X Zhao#, J Chen#, P Xiao, J Feng, Q Nie, XM Zhao

    Briefings in BioinformaticsFirst author

  4. A 12-genus bacterial signature identifies a group of severe autistic children with differential sensory behavior and brain structures

    K Shi, L Zhang, J Yu, Z Chen, S Lai, X Zhao, WG Li, Q Luo, W Lin, J Feng, et al.

    Clinical and Translational Medicine

2019

  1. Predicting drug-disease associations with heterogeneous network embedding

    K Yang, X Zhao, D Waxman, XM Zhao

    Chaos: An Interdisciplinary Journal of Nonlinear Science

  2. Deep learning based multi-modal cardiac MR image segmentation

    R Zheng, X Zhao*, X Zhao, H Wang

    STACOM Workshop (MICCAI)Corresponding authorConference

Software & data

TorchGWAS

GPU-accelerated GWAS for thousands of quantitative phenotypes. TorchGWAS2 adds support for related samples.

Read the paper

Brain EPI atlas

Enhancer–promoter interactions for 439 neural cell and tissue types, plus prioritized genes for each brain disorder and cognitive trait.

Open the data portal