Deep learning explains the biology of branched glycans from single-cell sequencing data

Qin, Rui; Mahal, Lara K.; Bojar, Daniel

doi:10.1016/j.isci.2022.105163

Cited by 10 publications

(6 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we also observed that the expression of glycans detected by lectins is only partially supported by the expression of the corresponding glycosyltransferase genes, as previously reported. [ 7,37 ] For example, we were unable to detect the expression of α1‐2 fucosyltransferase genes, FUT1 and FUT2 , in platelets (Figure S15, Supporting Information), although the presence of their product “α1‐2Fuc” on the cell surface was confirmed both by flow cytometry as well as scGR‐seq. This indicates that quantifying glycan expression at the single‐cell level is challenging due to the low expression nature of glycosyltransferase genes as previously described.…”

Section: Discussionmentioning

confidence: 95%

“…In this sense, Qin et al recently utilized a deep learning model to predict the glycan phenotypes of cells. [37] Deep learning models using scGR-seq data sets are promising for uncovering novel functions and regulatory mechanisms of glycans.…”

Section: Discussionmentioning

confidence: 99%

“…Further technology innovation such as the incorporation of a glycoinformatic approach is essential to extend the single-cell glycomics. [7,37]…”

Section: Discussionmentioning

confidence: 99%

“…This indicates that quantifying glycan expression at the single‐cell level is challenging due to the low expression nature of glycosyltransferase genes as previously described. [ 7,37 ] In another example, PHAL with specificity to β1‐6GlcNAc branching of N‐glycans showed higher binding to the myeloid lineage than the lymphoid lineage (Figure 3d) [ 38 ] , while MGAT5 involved in the synthesis of this glycan conversely showed lower expression in the myeloid lineage (Figure S12, Supporting Information). [ 39 ] One of the reasons for this discrepancy is that the products of MGAT3 , bisecting GlcNAc, may inhibit the generation of β1‐6GlcNAc branching of N‐glycans catalyzed by MGAT5 .…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Droplet‐Based Glycan and RNA Sequencing for Profiling the Distinct Cellular Glyco‐States in Single Cells

Keisham,

Saito,

Kowashi

et al. 2024

Small Methods

View full text Add to dashboard Cite

Plate‐based single‐cell glycan and RNA sequencing (scGR‐seq) is previously developed to realize the integrated analysis of glycome and transcriptome in single cells. However, the sample size is limited to only a few hundred cells. Here, a droplet‐based scGR‐seq is developed to address this issue by adopting a 10x Chromium platform to simultaneously profile ten thousand cells' glycome and transcriptome in single cells. To establish droplet‐based scGR‐seq, a comparative analysis of two distinct cell lines is performed: pancreatic ductal adenocarcinoma cells and normal pancreatic duct cells. Droplet‐based scGR‐seq revealed distinct glycan profiles between the two cell lines that showed a strong correlation with the results obtained by flow cytometry. Next, droplet‐based scGR‐seq is applied to a more complex sample: peripheral blood mononuclear cells (PBMC) containing various immune cells. The method can systematically map the glycan signature for each immune cell in PBMC as well as glycan alterations by cell lineage. Prediction of the association between the glycan expression and the gene expression using regression analysis ultimately leads to the identification of a glycan epitope that impacts cellular functions. In conclusion, the droplet‐based scGR‐seq realizes the high‐throughput profiling of the distinct cellular glyco‐states in single cells.

show abstract

Section: Discussionmentioning

confidence: 95%

Section: Discussionmentioning

confidence: 99%

“…Further technology innovation such as the incorporation of a glycoinformatic approach is essential to extend the single-cell glycomics. [7,37]…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Droplet‐Based Glycan and RNA Sequencing for Profiling the Distinct Cellular Glyco‐States in Single Cells

Keisham,

Saito,

Kowashi

et al. 2024

Small Methods

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence including machine learning and deep learning, where the latter uses artificial neural networks and is a subset of machine learning, are methods revolutionizing science. The ability to predict NMR chemical shifts of molecules by machine learning, − understand the biology of branched N -glycans, or unveil the origin of glycan-mediated host-microbe interactions by deep learning methods opens new avenues for exploring the importance of glycan structure in biology using NMR spectroscopy as the experimental technique. With the introduction of AlphaFold to predict three-dimensional structure of proteins, analysis of carbohydrate binding proteins, structures of glycosyl transferases, and possible functions of proteins as well as modules thereof has been completely changed.…”

Section: Outlook and Summarymentioning

confidence: 99%

Glycan Shape, Motions, and Interactions Explored by NMR Spectroscopy

Widmalm

2024

JACS Au

View full text Add to dashboard Cite

Glycans in the form of oligosaccharides, polysaccharides, and glycoconjugates are ubiquitous in nature, and their structures range from linear assemblies to highly branched and decorated constructs. Solution state NMR spectroscopy facilitates elucidation of preferred conformations and shapes of the saccharides, motions, and dynamic aspects related to processes over time as well as the study of transient interactions with proteins. Identification of intermolecular networks at the atomic level of detail in recognition events by carbohydrate-binding proteins known as lectins, unraveling interactions with antibodies, and revealing substrate scope and action of glycosyl transferases employed for synthesis of oligo-and polysaccharides may efficiently be analyzed by NMR spectroscopy. By utilizing NMR active nuclei present in glycans and derivatives thereof, including isotopically enriched compounds, highly detailed information can be obtained by the experiments. Subsequent analysis may be aided by quantum chemical calculations of NMR parameters, machine learning-based methodologies and artificial intelligence. Interpretation of the results from NMR experiments can be complemented by extensive molecular dynamics simulations to obtain three-dimensional dynamic models, thereby clarifying molecular recognition processes involving the glycans.

show abstract

Emerging technologies for single-cell glycomics

Keisham,

Tateno

2024

BBA Advances

View full text Add to dashboard Cite

Deep learning explains the biology of branched glycans from single-cell sequencing data

Cited by 10 publications

References 138 publications

Droplet‐Based Glycan and RNA Sequencing for Profiling the Distinct Cellular Glyco‐States in Single Cells

Droplet‐Based Glycan and RNA Sequencing for Profiling the Distinct Cellular Glyco‐States in Single Cells

Glycan Shape, Motions, and Interactions Explored by NMR Spectroscopy

Emerging technologies for single-cell glycomics

Contact Info

Product

Resources

About