Daniel Bojar

This paper introduces ELCA, a method for ultra-sensitive detection of secreted sialoglycoproteins, showing rapid response to pharmacological perturbations and compatibility with serum-containing conditions.

The paper introduces a method to analyze glycan motifs using a containment order, improving sensitivity and uncovering motif redistributions across multiple glycomics datasets.

GlycoForge generates synthetic glycomics data with known ground truth to benchmark methods, supporting motif-level effects, batch effects, and missing data simulation.

The paper introduces a structure-aware algorithm for glycan biosynthetic network construction and demonstrates its application in analyzing metabolic shifts in cancer.

The paper shows that extended O-glycans are present on intranuclear proteins and demonstrate their role in RNA processing through specific examples.

PyCycleBio models non-sinusoidal-oscillator systems in temporal biology, offering improved sensitivity and uncovering new relationships between data modalities and rhythmic behaviors.

This study characterizes the structural and functional dynamics of milk oligosaccharides in Atlantic grey seals throughout lactation, revealing complexity comparable to human milk.

GlyContact analyzes glycan 3D structures from MD, NMR, or X-ray data to understand structure-function relationships and improve AI models for lectin-glycan binding.

This paper introduces a framework for automated glycan nomenclature conversion that accepts any input format and outputs a standardized IUPAC-condensed format, enabling seamless integration of glycan data.

This study demonstrates that O-glycosylation contributes to sialoglycoRNA biogenesis and shows increased sialylation in ulcerative colitis-derived organoids.

This paper develops a machine learning workflow to identify generalizable diagnostic ions for O-glycan isomer differentiation using a curated dataset of 237,000 spectra.

The paper introduces CandyCrunch, a deep learning model that predicts glycan structures from tandem mass spectrometry data with high accuracy, enabling high-throughput glycomics.

This paper introduces a compositional data analysis framework for glycomics to address statistical issues in comparative glycan data, reducing false positives and revealing new biological insights.

The paper trains a hybrid neural network to predict N-glycosylation events and structures from protein sequences using glycosite-flanking data, demonstrating its ability to predict glycan composition and abundance.

The paper introduces a regular expression framework for glycan structures to automate analysis of glycan sequences and annotate motifs, enabling differential expression and lectin binding specificity studies.

This paper introduces a computational framework for differential glycomics expression analysis, demonstrating improved robustness and reliability through specialized methods and an open-source tool.

GlycoDraw generates high-quality, SNFG-compliant glycan figures in Python, enabling automated annotation and integration into glycan analysis workflows.

The paper develops a pipeline to analyze milk oligosaccharide biosynthetic networks across mammals, identifying evolutionary patterns and biosynthetic constraints.

GlyLES converts IUPAC-condensed glycan notation to SMILES using a grammar-based approach, enabling atomic-level representation and applications in molecular modeling and machine learning.

The paper uses deep learning to predict branched glycan phenotypes from single-cell transcriptomic data, identifying key genes influencing glycan biology.

LectinOracle predicts lectin-glycan interactions using deep learning, showing agreement with literature and generalizing to new glycans and lectins.

This study analyzes fucose-containing glycan motifs across taxonomic kingdoms, identifying differences in fucose usage and its role in molecular mimicry and biological processes.

Glycowork is a Python package for glycan data science and machine learning, offering tools for annotation, visualization, and analysis of glycan data.

This paper introduces SweetNet, a graph convolutional neural network for glycan sequence representation, showing it outperforms existing methods and predicts organismal traits and viral glycan-binding.

This paper develops a deep learning model to extract evolutionary information from glycans, revealing insights into host-pathogen interactions and phenotypic diversity.

This paper develops a language model for glycans, SweetTalk, to analyze substructure motifs, classify linkages, and predict immunogenicity with 92% accuracy.

The paper improves a surfaceome predictor using meta-ensemble learning and feature engineering, achieving higher accuracy in classifying plasma membrane proteins.