SZSai Zhang

Sai Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Sai Zhang has a total of 160 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Altered age-dependent somatic mutational trajectories in ALS motor cortex neurons

    by Liyueyue Liu, Charlotte van Dijk, Sam Bonsall, Rodrigo Siqueira Kazu, Sai Zhang, Johnathan Cooper-Knock, Jan Veldink, Kevin Patrick Kenna

    Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease in which disease onset is influenced by genetic, age-associated and environmental factors. Somatic mutations accumulate throughout life and may provide a molecular link between aging and neuronal vulnerability. Here, we investigated neuronal somatic mutational patterns in ALS and control motor cortex using three previously generated 10X single-nucleus RNA and ATAC sequencing datasets. Within the genomic regions accessible to 10X sequencing, variant calls showed established features of neuronal somatic mutagenesis, including neuronal enrichment, age-associated accumulation and recovery of the clock-like SBS5 mutational signature. ALS was associated with a disease-specific age-dependent trajectory of neuronal somatic mutation burden, with higher burden in younger ALS donors and a decreasing difference with age. SBS5 represented the largest fitted mutational component and showed a corresponding age-dependent difference. A similar pattern was observed in an independent single-cell whole-genome sequencing dataset. These findings support age-dependent alterations in neuronal somatic mutational patterns in ALS.

  • Open Access

    Machine Learning Reveals the Contribution of Rare Genetic Variants and Enhances Risk Prediction for Coronary Artery Disease in the Japanese Population

    by Hirotaka Ieki, Sai Zhang, Satoshi Koyama, Martin Kjellberg, Hiroki Yoshida, Ryo Kurosawa, Hiroshi Matsunaga, Kazuo Miyazawa, Nobuyuki Enzan, Changhoon Kim, et al.

    BACKGROUND: GWASs (genome-wide association studies) have advanced our understanding of coronary artery disease (CAD) genetics and enabled the development of polygenic risk scores (PRSs) for estimating genetic risk based on common variant burden. However, GWASs have limitations in analyzing rare variants due to insufficient statistical power, thereby constraining PRS performance. METHODS: We conducted whole-genome sequencing of 1752 Japanese patients with CAD and 3019 controls. A machine learning-based analytical framework was applied to identify and interpret rare genetic variants associated with CAD pathogenesis. RESULTS: This approach identified 59 CAD-related genes, including known causal genes such as LDLR and those not previously captured by GWASs. A rare variant-based risk score derived from the framework demonstrated distinct clinical characteristics compared with a conventional common variant-based PRS. The rare variant-based risk score significantly discriminated CAD cases and predicted cardiovascular mortality in an independent cohort. Furthermore, combining the rare variant-based risk score with the traditional PRS improved CAD prediction compared with the PRS alone (area under the curve, 0.66 versus 0.61; P =0.007). CONCLUSIONS: These findings underscore the distinct and complementary value of the rare variant-based risk score compared with the conventional PRS, highlighting the enhanced predictive power achieved through their integration. This comprehensive approach proposes broader genetic profiling, offering substantial potential for improved clinical risk stratification and personalized prevention strategies.

  • Open Access

    When network biology meets human genetics

    by Sai Zhang

  • Open Access

    Single-nucleus multiomic atlas of ALS primary motor cortex nominates neuroprotective WDR49-expressing astrocytes

    by Johnathan Cooper-Knock, Sam Bonsall, Rodrigo Kazu, Marianne King, Diana Leung, Farah Mahiddine, J Highley, Andrew Strange, Yongzhuo Chen, Matilde Sassani, et al.

    Amyotrophic lateral sclerosis (ALS) causes selective neurodegeneration in primary motor cortex, yet cell-type-specific molecular changes driving this vulnerability remain poorly understood. We present an integrated single-nucleus RNA- and ATAC-sequencing atlas of 778,330 nuclei from the primary motor cortex of 140 genetically characterised donors. ALS is associated with widespread transcriptional reprogramming driven by a common set of transcription factors (TFs) across multiple cell-types. Astrocytes harbour the most differentially expressed genes. Within astrocytes, a WDR49-expressing subpopulation is spatially associated with TDP-43 pathology, and genetic variants within WDR49 confer risk for both sporadic and monogenic autosomal dominant ALS. In patient-derived induced astrocytes, WDR49 protein abundance predicts the survival of co-cultured neurons. WDR49 localises to PML nuclear bodies, where it regulates astrocyte reactivity and secretion of EVs containing protein chaperones. Together, these in vivo and in vitro findings suggest that WDR49+ astrocytes mount a compensatory secretory response to extracellular protein aggregates, and that loss of this capacity lowers the threshold for ALS pathogenesis.


  • Open Access

    ProMeta: A meta-learning framework for robust disease diagnosis and prediction from plasma proteomics

    by Han Li, Haoteng Gu, Lei Hu, Zimo Zhang, Yongji Lv, Peng Gao, Johnathan Cooper-Knock, Yaosen Min, Jianyang Zeng, Sai Zhang

    The plasma proteome offers a dynamic window of human health, capturing the real-time intersections between genetics and physiology. However, the application of deep learning to proteomics is currently hindered by a reliance on large-scale labeled datasets, rendering standard models ineffective for rare or novel diseases where patient samples are inherently scarce. Here, we present ProMeta, a meta-learning framework designed to enable robust disease modeling under extreme data restrictions. By integrating knowledge-guided pathway encoding with bi-level meta-optimization, ProMeta projects unstructured proteomic profiles into biologically interpretable functional tokens. This architecture allows the model to learn a global initialization containing transferable biological priors from biobank-scale data, facilitating rapid adaptation to novel tasks. Through comprehensive benchmark experiments, ProMeta consistently outperformed transfer learning and traditional machine learning baselines in both disease diagnosis and prediction tasks. In the most challenging 4-shot scenarios (utilizing only 2 cases and 2 controls), the model achieved robust generalization with an average AUROC of ∼ 0.69, representing a 24.6% relative improvement over the best-performing baseline methods. Mechanistic investigation revealed that ProMeta disentangles cases from controls in the latent space prior to task-specific adaptation, confirming the acquisition of universal biological rules rather than rote memorization. Furthermore, gradient-based interpretation identified disease-specific protein biomarkers and functional pathways consistent with known pathophysiology. Collectively, ProMeta overcomes the data-scarcity bottleneck in precision medicine, providing a scalable, interpretable framework for characterizing the full spectrum of human diseases, particularly for rare conditions lacking extensive clinical cohorts.

  • Open Access

    Poor Oral Health and Risk of Respiratory Tract Cancer: A Prospective Cohort Study from the UK Biobank

    by Danting Yang, Hyung-Suk Yoon, Tara Hashemian, Young-Rock Hong, Shama D. Karanth, Sai Zhang, Heba El-Ahmad, Shannon M. Wallet, Qiuyin Cai, Xiao-Ou Shu, et al.

    Background/Objectives: The individual and combined effects of diverse dental problems on site-specific respiratory tract cancer remain insufficiently addressed. This study investigated the associations between six oral conditions—dentures, loose teeth, painful gums, bleeding gums, toothache, and mouth ulcers—and the risk of developing cancers of the lung, bronchus, larynx, and trachea, both individually and collectively. Methods: This prospective cohort study, utilizing baseline data from the UK Biobank, analyzed 438,762 participants aged 40–69 years. Multivariable Cox proportional hazards models were employed to estimate hazard ratios (HRs) and 95% CIs for incident respiratory tract cancer associated with individual oral conditions and their cumulative impact. Effect modification by sociodemographics, lifestyle, and underlying medical conditions was further assessed. Results: During the follow-up (median = 11.0 years), 3568 participants developed respiratory tract cancer. After adjusting for confounders, including smoking history, individuals with any oral issues exhibited a 35–76% higher risk of respiratory tract cancer (HR [95% CI]: 1.35 [1.25–1.46] for the total risk, 1.34 [1.24–1.45] for bronchus/lung cancer, and 1.76 [1.23–2.52] for laryngeal cancer). Dentures (1.48 [1.36–1.60]), loose teeth (1.36 [1.20–1.54]), and painful gums (1.25 [1.04–1.50]) had a strong association with respiratory tract cancer. The overall risk escalated progressively with the number of concurrent problems (HR [95% CI] of 1.32 [1.22–1.43] for one, 1.42 [1.25–1.62] for two, 1.57 [1.23–1.98] for three, and 1.71 [1.16–2.50] for ≥four). Associations were pronounced among smokers (p-interaction = 0.002). Conclusions: Poor oral health is linked to a heightened risk of respiratory tract cancer, especially when coupled with smoking, underscoring the importance of oral health promotion in cancer prevention strategies.


  • Open Access

    Single-cell polygenic risk scores dissect cellular and molecular heterogeneity of complex human diseases

    by Sai Zhang, Hantao Shu, Jingtian Zhou, Jasper Rubin-Sigler, Xiaoyu Yang, Yuxi Liu, Johnathan Cooper-Knock, Emma Monte, Chenchen Zhu, Sharon Tu, et al.

    Polygenic risk scores (PRSs) predict an individual’s genetic risk for complex diseases, yet their utility in elucidating disease biology remains limited. We introduce scPRS, a graph neural network-based framework that computes single-cell-resolved PRSs by integrating reference single-cell chromatin accessibility profiles. scPRS outperforms traditional PRS approaches in genetic risk prediction, as demonstrated across multiple diseases including type 2 diabetes, hypertrophic cardiomyopathy, Alzheimer disease and severe COVID-19. Beyond risk prediction, scPRS prioritizes disease-critical cells and, when combined with a layered multiomic analysis, links risk variants to gene regulation in a cell-type-specific manner. Applied to these diseases, scPRS fine-maps causal cell types and cell-type-specific variants and genes, demonstrating its ability to bridge genetic risk with cell-specific biology. scPRS provides a unified framework for genetic risk prediction and mechanistic dissection of complex diseases, laying a methodological foundation for single-cell genetics.


  • Open Access

    Dissecting the genetic complexity of myalgic encephalomyelitis/chronic fatigue syndrome via deep learning-powered genome analysis

    by Sai Zhang, Fereshteh Jahanbani, Varuna Chander, Martin Kjellberg, Menghui Liu, Katherine A. Glass, David S. Iu, Faraz Ahmed, Han Li, Rajan Douglas Maynard, et al.

    Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex, heterogeneous, and systemic disease defined by a suite of symptoms, including unexplained persistent fatigue, post-exertional malaise (PEM), cognitive impairment, myalgia, orthostatic intolerance, and unrefreshing sleep. The disease mechanism of ME/CFS is unknown, with no effective curative treatments. In this study, we present a multi-site ME/CFS whole-genome analysis, which is powered by a novel deep learning framework, HEAL2. We show that HEAL2 not only has predictive value for ME/CFS based on personal rare variants, but also links genetic risk to various ME/CFS-associated symptoms. Model interpretation of HEAL2 identifies 115 ME/CFS-risk genes that exhibit significant intolerance to loss-of-function (LoF) mutations. Transcriptome and network analyses highlight the functional importance of these genes across a wide range of tissues and cell types, including the central nervous system (CNS) and immune cells. Patient-derived multi-omics data implicate reduced expression of ME/CFS risk genes within ME/CFS patients, including in the plasma proteome, and the transcriptomes of B and T cells, especially cytotoxic CD4 T cells, supporting their disease relevance. Pan-phenotype analysis of ME/CFS genes further reveals the genetic correlation between ME/CFS and other complex diseases and traits, including depression and long COVID-19. Overall, HEAL2 provides a candidate genetic-based diagnostic tool for ME/CFS, and our findings contribute to a comprehensive understanding of the genetic, molecular, and cellular basis of ME/CFS, yielding novel insights into therapeutic targets. Our deep learning model also offers a potent, broadly applicable framework for parallel rare variant analysis and genetic prediction for other complex diseases and traits.


  • Open Access

    A multistage, multitask transformer-based framework for multi-disease diagnosis and prediction using personal proteomes

    by Han Li, Yongkang Li, Yukuan Liu, Johnathan Cooper-Knock, Peng Gao, Xiaotao Shen, Shengquan Chen, Xudong Xing, Sai Zhang

    Recent advances in cohort-level proteomic profiling have offered unprecedented opportunities for discovering novel biomarkers and developing diagnostic and predictive tools for complex human diseases. However, the inherent complexity of proteomics data and the scarcity of phenotypic labels, particularly for rare diseases, pose significant challenges in modeling proteome-phenome relationships. Utilizing proteomics data from 2,924 plasma proteins measured in 53,014 UK Biobank participants, we introduce Prophet, an interpretable deep learning framework that combines transformer architecture with a multistage, multitask training strategy to improve disease prediction and biological discovery from personal proteomic profiles. Prophet begins with self-supervised pretraining to model protein interactions, followed by prompt-based fine-tuning for disease diagnosis, and concludes with continuous fine-tuning for disease prediction. Extensive benchmarking across more than 100 diseases demonstrates Prophet’s superior performance over multiple baseline methods, achieving the highest increase in the area under the precision-recall curve (AUPRC) by 132.71% for disease diagnosis and 60.29% for disease prediction. Specifically, Prophet enhances diagnostic accuracy for 95.83% of diseases and boosts predictive accuracy for 94.02% of diseases. Through model interpretation, Prophet identifies 21,549 and 25,915 protein-disease associations for prevalent and incident diseases, respectively, and uncovers prevailing proteomics-based similarities among diseases. Our work provides a powerful framework for proteomics-based disease diagnosis, prediction, and biomarker discovery.


  • Open Access

    Modeling gene interactions in polygenic prediction via geometric deep learning

    by Han Li, Jianyang Zeng, Michael P. Snyder, Sai Zhang

    Polygenic risk score (PRS) is a widely used approach for predicting individuals’ genetic risk of complex diseases, playing a pivotal role in advancing precision medicine. Traditional PRS methods, predominantly following a linear structure, often fall short in capturing the intricate relationships between genotype and phenotype. In this study, we present PRS-Net, an interpretable geometric deep learning–based framework that effectively models the nonlinearity of biological systems for enhanced disease prediction and biological discovery. PRS-Net begins by deconvoluting the genome-wide PRS at the single-gene resolution and then explicitly encapsulates gene–gene interactions leveraging a graph neural network (GNN) for genetic risk prediction, enabling a systematic characterization of molecular interplay underpinning diseases. An attentive readout module is introduced to facilitate model interpretation. Extensive tests across multiple complex traits and diseases demonstrate the superior prediction performance of PRS-Net compared with a wide range of conventional PRS methods. The interpretability of PRS-Net further enhances the identification of disease-relevant genes and gene programs. PRS-Net provides a potent tool for concurrent genetic risk prediction and biological discovery for complex diseases.