Bingyuan Zhang
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
Research Subjects
Bingyuan Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Yusuke Matsui
Nagoya University
8 shared publications - Koichi Himori
Nagoya University
6 shared publications - Akihiro Kitani
Nagoya University
3 shared publications - Akira Yokoi
Department of Obstetrics and Gynecology Nagoya University Graduate School of Medicine Nagoya Japan
1 shared publication - Chihiro Sato
Institute for Glyco-core Research (iGCORE), Nagoya University
1 shared publication - Christopher Ashwood
Protea Glycosciences Pty Ltd
1 shared publication
Latest Publications
- Open Access
CATEomics: model selection and ensembling for heterogeneous treatment effect estimation from high-dimensional omics data
CATEomics addresses the lack of a standardized and reproducible process for choosing among conditional average treatment effect (CATE) estimators in high-dimensional omics studies, where their estimation errors cannot be evaluated directly from observed outcomes. The R package accepts a SummarizedExperiment, applies common preprocessing and data partitions across R and Python estimators, compares their out-of-fold estimates using proxy losses, supports model selection and ensembling, and returns the resulting CATE estimates to the original object for downstream omics analysis. Availability and implementation: CATEomics is implemented in R and is freely available under the MIT license at https://github.com/matsui-lab/CATEomics. The software version described here (v0.99.0) is archived on Zenodo at https://doi.org/10.5281/zenodo.24189754. A vignette illustrates the complete workflow from a SummarizedExperiment to downstream analysis.
Open AccessCATEomics: model selection and ensembling for heterogeneous treatment effect estimation from high-dimensional omics data
CATEomics addresses the lack of a standardized and reproducible process for choosing among conditional average treatment effect (CATE) estimators in high-dimensional omics studies, where their estimation errors cannot be evaluated directly from observed outcomes. The R package accepts a SummarizedExperiment, applies common preprocessing and data partitions across R and Python estimators, compares their out-of-fold estimates using proxy losses, supports model selection and ensembling, and returns the resulting CATE estimates to the original object for downstream omics analysis. Availability and implementation: CATEomics is implemented in R and is freely available under the MIT license at https://github.com/matsui-lab/CATEomics. The software version described here (v0.99.0) is archived on Zenodo at https://doi.org/10.5281/zenodo.24189754. A vignette illustrates the complete workflow from a SummarizedExperiment to downstream analysis.
- Open Access
Real-time mass defect-driven prediction of glycopeptide precursors enables enrichment-free serum glycoproteomics
Glycopeptide enrichment remains a cornerstone in glycoproteomics, but bias and reproducibility issues continue to hinder biological insight and clinical translation. Using curated glycoproteomics datasets and machine learning, we trained a glycopeptide classifier to promptly recognize N-glycopeptide precursor ions in peptide mixtures through mass defect signatures. Integration of the classifier into a data-dependent acquisition framework facilitated efficient and unbiased real-time prediction of N-glycopeptides directly from serum opening avenues for enrichment-free glycoproteomics.
Open AccessReal-time mass defect-driven prediction of glycopeptide precursors enables enrichment-free serum glycoproteomics
Glycopeptide enrichment remains a cornerstone in glycoproteomics, but bias and reproducibility issues continue to hinder biological insight and clinical translation. Using curated glycoproteomics datasets and machine learning, we trained a glycopeptide classifier to promptly recognize N-glycopeptide precursor ions in peptide mixtures through mass defect signatures. Integration of the classifier into a data-dependent acquisition framework facilitated efficient and unbiased real-time prediction of N-glycopeptides directly from serum opening avenues for enrichment-free glycoproteomics.
- Open Access
- 27 March 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (4)
GlycanGT: a pretrained graph transformer framework for glycan graph representation and generative learning
Motivation: Glycans are highly diverse biological sequences, but their functional understanding has lagged behind proteins and nucleic acids. Many glycans remain ambiguously annotated, limiting computational analyses. Existing computational approaches are primarily graph-based, capturing local structural features but struggling to model global patterns and incomplete sequences. Results: We present GlycanGT, a graph-transformer-based pretrained model for glycans. Glycans were represented as graphs of monosaccharides and glycosidic bonds, and the model was pretrained using a masked language modeling objective. GlycanGT demonstrated higher performance than existing methods across 8 benchmark tasks (e.g., 0.844 AUPRC for immunogenicity classification), and its embeddings formed biologically relevant clusters that recovered known N- and O-glycan categories. Moreover, GlycanGT accurately proposed candidates for ambiguous sequences, maintaining >80% top-5 accuracy for both monosaccharide and glycosidic bond predictions under high masking levels. Availability and implementation: The source code used in this study is available at https://github.com/matsui-lab/GlycanGT and archived on Zenodo (DOI: 10.5281/zenodo.18636040); pretrained model weights are provided via Hugging Face (https://huggingface.co/Akikitani295/GlycanGT). Contact: matsui.yusuke.d4@f.mail.nagoya-u.ac.jp Supplementary information: Supplementary data are available at Bioinformatics online.
- 27 March 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (4)
Open AccessGlycanGT: a pretrained graph transformer framework for glycan graph representation and generative learning
Motivation: Glycans are highly diverse biological sequences, but their functional understanding has lagged behind proteins and nucleic acids. Many glycans remain ambiguously annotated, limiting computational analyses. Existing computational approaches are primarily graph-based, capturing local structural features but struggling to model global patterns and incomplete sequences. Results: We present GlycanGT, a graph-transformer-based pretrained model for glycans. Glycans were represented as graphs of monosaccharides and glycosidic bonds, and the model was pretrained using a masked language modeling objective. GlycanGT demonstrated higher performance than existing methods across 8 benchmark tasks (e.g., 0.844 AUPRC for immunogenicity classification), and its embeddings formed biologically relevant clusters that recovered known N- and O-glycan categories. Moreover, GlycanGT accurately proposed candidates for ambiguous sequences, maintaining >80% top-5 accuracy for both monosaccharide and glycosidic bond predictions under high masking levels. Availability and implementation: The source code used in this study is available at https://github.com/matsui-lab/GlycanGT and archived on Zenodo (DOI: 10.5281/zenodo.18636040); pretrained model weights are provided via Hugging Face (https://huggingface.co/Akikitani295/GlycanGT). Contact: matsui.yusuke.d4@f.mail.nagoya-u.ac.jp Supplementary information: Supplementary data are available at Bioinformatics online.
- Open Access
- 7 January 2026
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 6 (1)
GlycoTraitR: an R package for characterizing structural heterogeneity in N-linked glycoproteomics data
Motivation: Glycoproteomics data are rapidly accumulating owing to advances in mass spectrometry and specialized search engines that identify N-linked glycopeptide spectrum matches together with glycan structures. However, the structural heterogeneity of glycosylation remains difficult to interpret, and no unified trait-based framework analyzes these data at both glycosylation-site and protein levels. Results: We developed GlycoTraitR, an R package for trait-based analysis of structural heterogeneity in N-linked glycoproteomics data. It imports search-engine outputs, extracts biologically interpretable glycan structural traits, quantifies microheterogeneity and macroheterogeneity, and compares heterogeneity across experimental conditions. Availability and implementation: The package and source code are freely available at https://github.com/matsui-lab/glycoTraitR. Documentation and a quick-start guide are available at https://matsui-lab.github.io/glycoTraitR/.
- 7 January 2026
- Published by Oxford University Press (OUP) in Bioinformatics Advances
- Vol. 6 (1)
Open AccessGlycoTraitR: an R package for characterizing structural heterogeneity in N-linked glycoproteomics data
Motivation: Glycoproteomics data are rapidly accumulating owing to advances in mass spectrometry and specialized search engines that identify N-linked glycopeptide spectrum matches together with glycan structures. However, the structural heterogeneity of glycosylation remains difficult to interpret, and no unified trait-based framework analyzes these data at both glycosylation-site and protein levels. Results: We developed GlycoTraitR, an R package for trait-based analysis of structural heterogeneity in N-linked glycoproteomics data. It imports search-engine outputs, extracts biologically interpretable glycan structural traits, quantifies microheterogeneity and macroheterogeneity, and compares heterogeneity across experimental conditions. Availability and implementation: The package and source code are freely available at https://github.com/matsui-lab/glycoTraitR. Documentation and a quick-start guide are available at https://matsui-lab.github.io/glycoTraitR/.
- Open Access
GlycoTraitR: an R package for characterizing structural heterogeneity in N-linked glycoproteomics data
Glycoproteomics data are rapidly accumulating due to advances in mass spectrometry instrumentation and the development of specialized search engines (e.g., pGlyco3, Glyco-Decipher) that enable identification of N-linked glycopeptide spectral matches (GPSMs) together with glycan structures. These advances have greatly expanded the scale and depth of N-linked glycopeptides; however, the intrinsic structural heterogeneity of glycosylation remains challenging to interpret. No existing tool provides a unified trait-based framework for analyzing N-linked GPSM data at both the glycosylation-site and protein levels. We developed glycoTraitR, an R package for trait-based analysis of structural heterogeneity in N-linked glycoproteomics data. GlycoTraitR provides a unified workflow to import GPSMs from search engine outputs, extract biologically interpretable glycan structural traits, and perform comparative analyses of micro- and macro-heterogeneity across experimental conditions using statistical testing.
Open AccessGlycoTraitR: an R package for characterizing structural heterogeneity in N-linked glycoproteomics data
Glycoproteomics data are rapidly accumulating due to advances in mass spectrometry instrumentation and the development of specialized search engines (e.g., pGlyco3, Glyco-Decipher) that enable identification of N-linked glycopeptide spectral matches (GPSMs) together with glycan structures. These advances have greatly expanded the scale and depth of N-linked glycopeptides; however, the intrinsic structural heterogeneity of glycosylation remains challenging to interpret. No existing tool provides a unified trait-based framework for analyzing N-linked GPSM data at both the glycosylation-site and protein levels. We developed glycoTraitR, an R package for trait-based analysis of structural heterogeneity in N-linked glycoproteomics data. GlycoTraitR provides a unified workflow to import GPSMs from search engine outputs, extract biologically interpretable glycan structural traits, and perform comparative analyses of micro- and macro-heterogeneity across experimental conditions using statistical testing.
- Open Access
GlycanGT: A Foundation Model for Glycan Graphs with Pretrained Representation and Generative Learning
Motivation: Glycans are highly diverse biological sequences, but their functional understanding has lagged behind that of proteins and nucleic acids. Many glycans remain incompletely characterized or ambiguously annotated, limiting computational analyses. Existing computational approaches are primarily graph-based, capturing local structural features but struggling to model global patterns and incomplete sequences. Results: We present GlycanGT, a foundation model for glycans built on a graph transformer architecture. Glycans were represented as graphs with monosaccharides as nodes and glycosidic bonds as edges, and the model was pretrained using a masked language modeling objective. GlycanGT demonstrated higher performance than existing methods across 8 benchmark classification tasks (e.g., 0.734 Macro-F1 in domain prediction and 0.844 AUPRC for immunogenicity classification), and its embeddings formed biologically meaningful clusters that recovered known N- and O-glycan categories. Moreover, GlycanGT accurately proposed candidates for ambiguous sequences, maintaining >80% top-5 accuracy for both monosaccharide and glycosidic bond predictions under high masking levels. Availability and implementation: The pretrained GlycanGT model weights and usage scripts are available on Hugging Face: https://huggingface.co/Akikitani295/GlycanGT . Additional scripts used for analyses in the paper are publicly available on GitHub: https://github.com/matsui-lab/GlycanGT . Contact: matsui.yusuke.d4@f.mail.nagoya-u.ac.jp
Open AccessGlycanGT: A Foundation Model for Glycan Graphs with Pretrained Representation and Generative Learning
Motivation: Glycans are highly diverse biological sequences, but their functional understanding has lagged behind that of proteins and nucleic acids. Many glycans remain incompletely characterized or ambiguously annotated, limiting computational analyses. Existing computational approaches are primarily graph-based, capturing local structural features but struggling to model global patterns and incomplete sequences. Results: We present GlycanGT, a foundation model for glycans built on a graph transformer architecture. Glycans were represented as graphs with monosaccharides as nodes and glycosidic bonds as edges, and the model was pretrained using a masked language modeling objective. GlycanGT demonstrated higher performance than existing methods across 8 benchmark classification tasks (e.g., 0.734 Macro-F1 in domain prediction and 0.844 AUPRC for immunogenicity classification), and its embeddings formed biologically meaningful clusters that recovered known N- and O-glycan categories. Moreover, GlycanGT accurately proposed candidates for ambiguous sequences, maintaining >80% top-5 accuracy for both monosaccharide and glycosidic bond predictions under high masking levels. Availability and implementation: The pretrained GlycanGT model weights and usage scripts are available on Hugging Face: https://huggingface.co/Akikitani295/GlycanGT . Additional scripts used for analyses in the paper are publicly available on GitHub: https://github.com/matsui-lab/GlycanGT . Contact: matsui.yusuke.d4@f.mail.nagoya-u.ac.jp
- Open Access
HuTAge: a Comprehensive Human Tissue- and Cell-specific Ageing Signature Atlas
Summary Ageing is a complex process that involves interorgan and intercellular interactions. To obtain a clear understanding of ageing, cross-tissue single-cell data resources are required. However, a complete resource for humans is not available. To bridge this gap, we developed HuTAge, a comprehensive resource that integrates cross-tissue age-related information from The Genotype-Tissue Expression project with cross-tissue single-cell information from Tabula Sapiens to provide human tissue- and cell-specific ageing molecular information. Availability and Implementation HuTAge is implemented within an R Shiny application and can be freely accessed at https://igcore.cloud/GerOmics/HuTAge/home. The source code is available at https://github.com/matsui-lab/HuTAge. Contact himori.koichi.b5{at}f.mail.nagoya-u.ac.jp
Open AccessHuTAge: a Comprehensive Human Tissue- and Cell-specific Ageing Signature Atlas
Summary Ageing is a complex process that involves interorgan and intercellular interactions. To obtain a clear understanding of ageing, cross-tissue single-cell data resources are required. However, a complete resource for humans is not available. To bridge this gap, we developed HuTAge, a comprehensive resource that integrates cross-tissue age-related information from The Genotype-Tissue Expression project with cross-tissue single-cell information from Tabula Sapiens to provide human tissue- and cell-specific ageing molecular information. Availability and Implementation HuTAge is implemented within an R Shiny application and can be freely accessed at https://igcore.cloud/GerOmics/HuTAge/home. The source code is available at https://github.com/matsui-lab/HuTAge. Contact himori.koichi.b5{at}f.mail.nagoya-u.ac.jp
- Open Access
A Computational Approach to Interpreting the Embedding Space of Dimension Reduction
Summary: Nonlinear dimension reduction methods are widely applied in studies analyzing gene and protein expression, by revealing patterns of discrete groups and continuous orders in high-dimensional data. However, the tools are limited to understanding the obtained embedding structures of biological mechanisms, hindering the full exploitation of data. Here, we propose a novel framework to interpret embedding systematically by identifying and mapping associated biological functions. The method performs statistical tests and visualizes significantly enriched functions essential for the organization of the embedding structure, by applying it to the embedding results of two datasets: the Genotype Tissue Expression dataset and a Caenorhabditis elegans embryogenesis dataset, one capturing distinct cluster structures and the other capturing continuous developmental trajectories. We identified the associated functions for interpreting the two embeddings and confirmed it as a useful explainable AI tool in exploratory data analysis by providing annotations to the embedding space.
Open AccessA Computational Approach to Interpreting the Embedding Space of Dimension Reduction
Summary: Nonlinear dimension reduction methods are widely applied in studies analyzing gene and protein expression, by revealing patterns of discrete groups and continuous orders in high-dimensional data. However, the tools are limited to understanding the obtained embedding structures of biological mechanisms, hindering the full exploitation of data. Here, we propose a novel framework to interpret embedding systematically by identifying and mapping associated biological functions. The method performs statistical tests and visualizes significantly enriched functions essential for the organization of the embedding structure, by applying it to the embedding results of two datasets: the Genotype Tissue Expression dataset and a Caenorhabditis elegans embryogenesis dataset, one capturing distinct cluster structures and the other capturing continuous developmental trajectories. We identified the associated functions for interpreting the two embeddings and confirmed it as a useful explainable AI tool in exploratory data analysis by providing annotations to the embedding space.
- Open Access
Extending Hilbert–Schmidt Independence Criterion for Testing Conditional Independence
The Conditional Independence (CI) test is a fundamental problem in statistics. Many nonparametric CI tests have been developed, but a common challenge exists: the current methods perform poorly with a high-dimensional conditioning set. In this paper, we considered a nonparametric CI test using a kernel-based test statistic, which can be viewed as an extension of the Hilbert–Schmidt Independence Criterion (HSIC). We propose a local bootstrap method to generate samples from the null distribution . The experimental results showed that our proposed method led to a significant performance improvement compared with previous methods. In particular, our method performed well against the growth of the dimension of the conditioning set. Meanwhile, our method can be computed efficiently against the growth of the sample size and the dimension of the conditioning set.Open AccessExtending Hilbert–Schmidt Independence Criterion for Testing Conditional Independence
The Conditional Independence (CI) test is a fundamental problem in statistics. Many nonparametric CI tests have been developed, but a common challenge exists: the current methods perform poorly with a high-dimensional conditioning set. In this paper, we considered a nonparametric CI test using a kernel-based test statistic, which can be viewed as an extension of the Hilbert–Schmidt Independence Criterion (HSIC). We propose a local bootstrap method to generate samples from the null distribution . The experimental results showed that our proposed method led to a significant performance improvement compared with previous methods. In particular, our method performed well against the growth of the dimension of the conditioning set. Meanwhile, our method can be computed efficiently against the growth of the sample size and the dimension of the conditioning set.