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.
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.
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
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.
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.
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.