Decoding glycosylation potential from protein structure across human glycoproteins with a multi-view recurrent neural network
Kellman, B.; Mariethoz, J.; Zhang, Y.; Shaul, S.; Jeffris, M.; Sandoval, D.; Jeffris, M.; Armingol, E.; Bao, B.; Lisacek, F.; Bojar, D.; Lewis, N.
Show abstract
Glycosylation is described as a non-templated biosynthesis. Yet, the template-free premise is antithetical to the observation that different N-glycans are consistently placed at specific sites. It has been proposed that glycosite-proximal protein structures could constrain glycosylation and explain the observed microheterogeneity. Using site-specific glycosylation data, we trained a hybrid neural network to parse glycosites (recurrent neural network) and match them to feasible N-glycosylation events (graph neural network). From glycosite-flanking sequences, the algorithm predicts most human N-glycosylation events documented in the GlyConnect database and proposed structures corresponding to observed monosaccharide composition of the glycans at these sites. The algorithm also recapitulated glycosylation in Enhanced Aromatic Sequons, SARS-CoV-2 spike, and IgG3 variants, thus demonstrating the ability of the algorithm to predict both glycan structure and abundance. Thus, protein structure constrains glycosylation, and the neural network enables predictive in silico glycosylation of uncharacterized or novel protein sequences and genetic variants.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Glycoproteomic landscape and structural dynamics of TIM family immune checkpoints enabled by mucinase SmE 96%
- Vulnerabilities in coronavirus glycan shields despite extensive glycosylation 94%
- Prominent members of the human gut microbiota express endo-acting O-glycanases to initiate mucin breakdown 94%
Similar papers in this journal
- Comprehensive analysis of lectin-glycan interactions reveals determinants of lectin specificity 94%
- Paraplume: A fast and accurate paratope prediction method provides insights into repertoire-scale binding dynamics 92%
- THLANet: A Deep Learning Framework for Predicting TCR-pHLA Binding in Immunotherapy Applications 91%
Similar papers in this journal
- Structural and Functional Glycosylation of the Abdala COVID-19 Vaccine 94%
- Distinct shifts in site-specific glycosylation pattern of SARS-CoV-2 spike proteins associated with arising mutations in the D614G and Alpha variants 94%
- Simple and practical sialoglycan encoding system reveals vast diversity in nature and identifies a universal sialoglycan-recognizing probe derived from AB5 toxin B subunits 93%
Similar papers in this journal
- Sitetack: A Deep Learning Model that Improves PTM Predictionby Using Known PTMs 95%
- Pepsickle rapidly and accurately predicts proteasomal cleavage sites for improved neoantigen identification 93%
- SHEPHARD: a modular and extensible software architecture for analyzing and annotating large protein datasets 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.