Glycan classification with tree kernels

Yoshihiro Yamanishi, Francis Bach, Jean Philippe Vert

    Research output: Contribution to journalArticle

    34 Citations (Scopus)

    Abstract

    Motivation: Glycans are covalent assemblies of sugar that play crucial roles in many cellular processes. Recently, comprehensive data about the structure and function of glycans have been accumulated, therefore the need for methods and algorithms to analyze these data is growing fast. Results: This article presents novel methods for classifying glycans and detecting discriminative glycan motifs with support vector machines (SVM). We propose a new class of tree kernels to measure the similarity between glycans. These kernels are based on the comparison of tree substructures, and take into account several glycan features such as the sugar type, the sugar bound type or layer depth. The proposed methods are tested on their ability to classify human glycans into four blood components: leukemia cells, erythrocytes, plasma and serum. They are shown to outperform a previously published method. We also applied a feature selection approach to extract glycan motifs which are characteristic of each blood component. We confirmed that some leukemia-specific glycan motifs detected by our method corresponded to several results in the literature.

    Original languageEnglish
    Pages (from-to)1211-1216
    Number of pages6
    JournalBioinformatics
    Volume23
    Issue number10
    DOIs
    Publication statusPublished - May 15 2007

    Fingerprint

    Sugars
    Polysaccharides
    kernel
    Blood
    Leukemia
    Support vector machines
    Feature extraction
    Erythrocyte
    Plasmas
    Substructure
    Feature Selection
    Support Vector Machine
    Plasma Cell Leukemia
    Plasma
    Classify
    Cellular Structures
    Cell
    Erythrocytes
    Serum

    All Science Journal Classification (ASJC) codes

    • Statistics and Probability
    • Biochemistry
    • Molecular Biology
    • Computer Science Applications
    • Computational Theory and Mathematics
    • Computational Mathematics

    Cite this

    Yamanishi, Y., Bach, F., & Vert, J. P. (2007). Glycan classification with tree kernels. Bioinformatics, 23(10), 1211-1216. https://doi.org/10.1093/bioinformatics/btm090

    Glycan classification with tree kernels. / Yamanishi, Yoshihiro; Bach, Francis; Vert, Jean Philippe.

    In: Bioinformatics, Vol. 23, No. 10, 15.05.2007, p. 1211-1216.

    Research output: Contribution to journalArticle

    Yamanishi, Y, Bach, F & Vert, JP 2007, 'Glycan classification with tree kernels', Bioinformatics, vol. 23, no. 10, pp. 1211-1216. https://doi.org/10.1093/bioinformatics/btm090
    Yamanishi, Yoshihiro ; Bach, Francis ; Vert, Jean Philippe. / Glycan classification with tree kernels. In: Bioinformatics. 2007 ; Vol. 23, No. 10. pp. 1211-1216.
    @article{2296083418b84fa190d34d3137518ffe,
    title = "Glycan classification with tree kernels",
    abstract = "Motivation: Glycans are covalent assemblies of sugar that play crucial roles in many cellular processes. Recently, comprehensive data about the structure and function of glycans have been accumulated, therefore the need for methods and algorithms to analyze these data is growing fast. Results: This article presents novel methods for classifying glycans and detecting discriminative glycan motifs with support vector machines (SVM). We propose a new class of tree kernels to measure the similarity between glycans. These kernels are based on the comparison of tree substructures, and take into account several glycan features such as the sugar type, the sugar bound type or layer depth. The proposed methods are tested on their ability to classify human glycans into four blood components: leukemia cells, erythrocytes, plasma and serum. They are shown to outperform a previously published method. We also applied a feature selection approach to extract glycan motifs which are characteristic of each blood component. We confirmed that some leukemia-specific glycan motifs detected by our method corresponded to several results in the literature.",
    author = "Yoshihiro Yamanishi and Francis Bach and Vert, {Jean Philippe}",
    year = "2007",
    month = "5",
    day = "15",
    doi = "10.1093/bioinformatics/btm090",
    language = "English",
    volume = "23",
    pages = "1211--1216",
    journal = "Bioinformatics",
    issn = "1367-4803",
    publisher = "Oxford University Press",
    number = "10",

    }

    TY - JOUR

    T1 - Glycan classification with tree kernels

    AU - Yamanishi, Yoshihiro

    AU - Bach, Francis

    AU - Vert, Jean Philippe

    PY - 2007/5/15

    Y1 - 2007/5/15

    N2 - Motivation: Glycans are covalent assemblies of sugar that play crucial roles in many cellular processes. Recently, comprehensive data about the structure and function of glycans have been accumulated, therefore the need for methods and algorithms to analyze these data is growing fast. Results: This article presents novel methods for classifying glycans and detecting discriminative glycan motifs with support vector machines (SVM). We propose a new class of tree kernels to measure the similarity between glycans. These kernels are based on the comparison of tree substructures, and take into account several glycan features such as the sugar type, the sugar bound type or layer depth. The proposed methods are tested on their ability to classify human glycans into four blood components: leukemia cells, erythrocytes, plasma and serum. They are shown to outperform a previously published method. We also applied a feature selection approach to extract glycan motifs which are characteristic of each blood component. We confirmed that some leukemia-specific glycan motifs detected by our method corresponded to several results in the literature.

    AB - Motivation: Glycans are covalent assemblies of sugar that play crucial roles in many cellular processes. Recently, comprehensive data about the structure and function of glycans have been accumulated, therefore the need for methods and algorithms to analyze these data is growing fast. Results: This article presents novel methods for classifying glycans and detecting discriminative glycan motifs with support vector machines (SVM). We propose a new class of tree kernels to measure the similarity between glycans. These kernels are based on the comparison of tree substructures, and take into account several glycan features such as the sugar type, the sugar bound type or layer depth. The proposed methods are tested on their ability to classify human glycans into four blood components: leukemia cells, erythrocytes, plasma and serum. They are shown to outperform a previously published method. We also applied a feature selection approach to extract glycan motifs which are characteristic of each blood component. We confirmed that some leukemia-specific glycan motifs detected by our method corresponded to several results in the literature.

    UR - http://www.scopus.com/inward/record.url?scp=34447328438&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34447328438&partnerID=8YFLogxK

    U2 - 10.1093/bioinformatics/btm090

    DO - 10.1093/bioinformatics/btm090

    M3 - Article

    C2 - 17344232

    AN - SCOPUS:34447328438

    VL - 23

    SP - 1211

    EP - 1216

    JO - Bioinformatics

    JF - Bioinformatics

    SN - 1367-4803

    IS - 10

    ER -