Using graph convolutional neural networks to learn a representation for glycans

Burkholz, Rebekka; Quackenbush, John; Bojar, Daniel

doi:10.1016/j.celrep.2021.109251

Cited by 33 publications

(52 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To use the motif.analysis.plot_embeddings() function of glycowork, we trained SweetNet-type machine learning models (Burkholz et al, 2021) to obtain glycan representations. Briefly, SweetNet is a deep learning method based on graph convolutional neural networks (GCNNs).…”

Section: Machine Learning Model Training To Obtain Learned Similaritiesmentioning

confidence: 99%

“…For both models, we randomly split our data into 80/20% for train and test sets, respectively. Glycan representations or learned similarities were obtained after the graph convolutional layers of the trained neural network, as described in Burkholz et al (2021).…”

Section: Machine Learning Model Training To Obtain Learned Similaritiesmentioning

confidence: 99%

“…Because of the complexity of glycans, manual investigations are struggling to extract meaning from these constituents. To solve this problem, an increasing number of in silico approaches dedicated to their analysis have been recently developed, including molecular dynamics simulations of protein-associated glycans (Harbison et al, 2019;Fogarty et al, 2020) or glycan-focused machine learning efforts to link sequences to functions (Bojar et al, 2020b;Burkholz et al, 2021). Bioinformatics methods are well-suited to investigate such complex molecules in an efficient and automated manner, particularly with the synergy between classical computational approaches with pattern-finding machine learning models.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The Role of Fucose-Containing Glycan Motifs Across Taxonomic Kingdoms

Thomès

Bojar

2021

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

The extraordinary diversity of glycans leads to large differences in the glycomes of different kingdoms of life. Yet, while most monosaccharides are solely found in certain taxonomic groups, there is a small set of monosaccharides with widespread distribution across nearly all domains of life. These general monosaccharides are particularly relevant for glycan motifs, as they can readily be used by commensals and pathogens to mimic host glycans or hijack existing glycan recognition systems. Among these, the monosaccharide fucose is especially interesting, as it frequently presents itself as a terminal monosaccharide, primed for interaction with proteins. Here, we analyze fucose-containing glycan motifs across all taxonomic kingdoms. Using a hereby presented large species-specific glycan dataset and a plethora of methods for glycan-focused bioinformatics and machine learning, we identify characteristic as well as shared fucose-containing glycan motifs for various taxonomic groups, demonstrating clear differences in fucose usage. Even within domains, fucose is used differentially based on an organism’s physiology and habitat. We particularly highlight differences in fucose-containing motifs between vertebrates and invertebrates. With the example of pathogenic and non-pathogenic Escherichia coli strains, we also demonstrate the importance of fucose-containing motifs in molecular mimicry and thereby pathogenic potential. We envision that this study will shed light on an important class of glycan motifs, with potential new insights into the role of fucosylated glycans in symbiosis, pathogenicity, and immunity.

show abstract

Section: Machine Learning Model Training To Obtain Learned Similaritiesmentioning

confidence: 99%

Section: Machine Learning Model Training To Obtain Learned Similaritiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Role of Fucose-Containing Glycan Motifs Across Taxonomic Kingdoms

Thomès

Bojar

2021

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Machine Learning Model Training To Obtain Learned Similaritiesmentioning

confidence: 99%

The role of fucose-containing glycan motifs across taxonomic kingdoms

Thomès

Bojar

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The extraordinary diversity of glycans leads to large differences in the glycomes of different kingdoms of life. Yet, while most monosaccharides are solely found in certain taxonomic groups, there is a small set of monosaccharides with widespread distribution across nearly all domains of life. These general monosaccharides are particularly relevant for glycan motifs, as they can readily be used by commensals and pathogens to mimic host glycans or hijack existing glycan recognition systems. Among these, the monosaccharide fucose is especially interesting, as it frequently presents itself as a terminal monosaccharide, primed for interaction with proteins. Here, we analyze fucose-containing glycan motifs across all taxonomic kingdoms. Using a hereby presented large species-specific glycan dataset and a plethora of methods for glycan-focused bioinformatics and machine learning, we identify characteristic as well as shared fucose-containing glycan motifs for various taxonomic groups, demonstrating clear differences in fucose usage. Even within domains, fucose is used differentially based on an organism's physiology and habitat. We particularly highlight differences in fucose-containing motifs between vertebrates and invertebrates. With the example of pathogenic and non-pathogenic Escherichia coli strains, we also demonstrate the importance of fucose-containing motifs in molecular mimicry and thereby pathogenic potential. Finally, we also confirm and extend the role of fucosyltransferase-coding genes (FUT) in several important biological processes that include development, immunity, and diseases, especially cancer. We envision that this study will shed light on an important class of glycan motifs, with potential new insights into the role of fucosylated glycans in symbiosis, pathogenicity, and immunity.

show abstract

“…2020 ; Haab and Klamer 2020 ) or glycan-focused machine learning ( Bojar et al. 2021 ; Burkholz et al. 2021 ), have been recently developed.…”

Section: Introductionmentioning

confidence: 99%

Glycowork: A Python package for glycan data science and machine learning

2021

Self Cite

View full text Add to dashboard Cite

While glycans are crucial for biological processes, existing analysis modalities make it difficult for researchers with limited computational background to include these diverse carbohydrates into workflows. Here, we present glycowork, an open-source Python package designed for glycan-related data science and machine learning by end users. Glycowork includes functions to, for instance, automatically annotate glycan motifs and analyze their distributions via heatmaps and statistical enrichment. We also provide visualization methods, routines to interact with stored databases, trained machine learning models, and learned glycan representations. We envision that glycowork can extract further insights from glycan datasets and demonstrate this with workflows that analyze glycan motifs in various biological contexts. Glycowork can be freely accessed at https://github.com/BojarLab/glycowork/.

show abstract

Using graph convolutional neural networks to learn a representation for glycans

Cited by 33 publications

References 44 publications

The Role of Fucose-Containing Glycan Motifs Across Taxonomic Kingdoms

The Role of Fucose-Containing Glycan Motifs Across Taxonomic Kingdoms

The role of fucose-containing glycan motifs across taxonomic kingdoms

Glycowork: A Python package for glycan data science and machine learning

Contact Info

Product

Resources

About