Supervised enzyme network inference from the integration of genomic data and chemical information

Yoshihiro Yamanishi, Jean Philippe Vert, Minoru Kanehisa

    Research output: Contribution to journalArticle

    65 Citations (Scopus)

    Abstract

    Motivation: The metabolic network is an important biological network which relates enzyme proteins and chemical compounds. A large number of metabolic pathways remain unknown nowadays, and many enzymes are missing even in known metabolic pathways. There is, therefore, an incentive to develop methods to reconstruct the unknown parts of the metabolic network and to identify genes coding for missing enzymes. Results: This paper presents new methods to infer enzyme networks from the integration of multiple genomic data and chemical information, in the framework of supervised graph inference. The originality of the methods is the introduction of chemical compatibility as a constraint for refining the network predicted by the network inference engine. The chemical compatibility between two enzymes is obtained automatically from the information encoded by their Enzyme Commission (EC) numbers. The proposed methods are tested and compared on their ability to infer the enzyme network of the yeast Saccharomyces cerevisiae from four datasets for enzymes with assigned EC numbers: gene expression data, protein localization data, phylogenetic profiles and chemical compatibility information. It is shown that the prediction accuracy of the network reconstruction consistently improves owing to the introduction of chemical constraints, the use of a supervised approach and the weighted integration of multiple datasets. Finally, we conduct a comprehensive prediction of a global enzyme network consisting of all enzyme candidate proteins of the yeast to obtain new biological findings.

    Original languageEnglish
    Pages (from-to)i468-i477
    JournalBioinformatics
    Volume21
    Issue numberSUPPL. 1
    DOIs
    Publication statusPublished - Jun 1 2005

    Fingerprint

    Genomics
    Enzymes
    Metabolic Networks and Pathways
    Yeast
    Compatibility
    Metabolic Network
    Proteins
    Protein
    Pathway
    Unknown
    Inference engines
    Inference Engine
    Chemical compounds
    Aptitude
    Fungal Proteins
    Prediction
    Biological Networks
    Saccharomyces Cerevisiae
    Phylogenetics
    Gene Expression Data

    All Science Journal Classification (ASJC) codes

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

    Cite this

    Supervised enzyme network inference from the integration of genomic data and chemical information. / Yamanishi, Yoshihiro; Vert, Jean Philippe; Kanehisa, Minoru.

    In: Bioinformatics, Vol. 21, No. SUPPL. 1, 01.06.2005, p. i468-i477.

    Research output: Contribution to journalArticle

    Yamanishi, Yoshihiro ; Vert, Jean Philippe ; Kanehisa, Minoru. / Supervised enzyme network inference from the integration of genomic data and chemical information. In: Bioinformatics. 2005 ; Vol. 21, No. SUPPL. 1. pp. i468-i477.
    @article{4b858d7f06d24dd39e7d1b597f869b43,
    title = "Supervised enzyme network inference from the integration of genomic data and chemical information",
    abstract = "Motivation: The metabolic network is an important biological network which relates enzyme proteins and chemical compounds. A large number of metabolic pathways remain unknown nowadays, and many enzymes are missing even in known metabolic pathways. There is, therefore, an incentive to develop methods to reconstruct the unknown parts of the metabolic network and to identify genes coding for missing enzymes. Results: This paper presents new methods to infer enzyme networks from the integration of multiple genomic data and chemical information, in the framework of supervised graph inference. The originality of the methods is the introduction of chemical compatibility as a constraint for refining the network predicted by the network inference engine. The chemical compatibility between two enzymes is obtained automatically from the information encoded by their Enzyme Commission (EC) numbers. The proposed methods are tested and compared on their ability to infer the enzyme network of the yeast Saccharomyces cerevisiae from four datasets for enzymes with assigned EC numbers: gene expression data, protein localization data, phylogenetic profiles and chemical compatibility information. It is shown that the prediction accuracy of the network reconstruction consistently improves owing to the introduction of chemical constraints, the use of a supervised approach and the weighted integration of multiple datasets. Finally, we conduct a comprehensive prediction of a global enzyme network consisting of all enzyme candidate proteins of the yeast to obtain new biological findings.",
    author = "Yoshihiro Yamanishi and Vert, {Jean Philippe} and Minoru Kanehisa",
    year = "2005",
    month = "6",
    day = "1",
    doi = "10.1093/bioinformatics/bti1012",
    language = "English",
    volume = "21",
    pages = "i468--i477",
    journal = "Bioinformatics",
    issn = "1367-4803",
    publisher = "Oxford University Press",
    number = "SUPPL. 1",

    }

    TY - JOUR

    T1 - Supervised enzyme network inference from the integration of genomic data and chemical information

    AU - Yamanishi, Yoshihiro

    AU - Vert, Jean Philippe

    AU - Kanehisa, Minoru

    PY - 2005/6/1

    Y1 - 2005/6/1

    N2 - Motivation: The metabolic network is an important biological network which relates enzyme proteins and chemical compounds. A large number of metabolic pathways remain unknown nowadays, and many enzymes are missing even in known metabolic pathways. There is, therefore, an incentive to develop methods to reconstruct the unknown parts of the metabolic network and to identify genes coding for missing enzymes. Results: This paper presents new methods to infer enzyme networks from the integration of multiple genomic data and chemical information, in the framework of supervised graph inference. The originality of the methods is the introduction of chemical compatibility as a constraint for refining the network predicted by the network inference engine. The chemical compatibility between two enzymes is obtained automatically from the information encoded by their Enzyme Commission (EC) numbers. The proposed methods are tested and compared on their ability to infer the enzyme network of the yeast Saccharomyces cerevisiae from four datasets for enzymes with assigned EC numbers: gene expression data, protein localization data, phylogenetic profiles and chemical compatibility information. It is shown that the prediction accuracy of the network reconstruction consistently improves owing to the introduction of chemical constraints, the use of a supervised approach and the weighted integration of multiple datasets. Finally, we conduct a comprehensive prediction of a global enzyme network consisting of all enzyme candidate proteins of the yeast to obtain new biological findings.

    AB - Motivation: The metabolic network is an important biological network which relates enzyme proteins and chemical compounds. A large number of metabolic pathways remain unknown nowadays, and many enzymes are missing even in known metabolic pathways. There is, therefore, an incentive to develop methods to reconstruct the unknown parts of the metabolic network and to identify genes coding for missing enzymes. Results: This paper presents new methods to infer enzyme networks from the integration of multiple genomic data and chemical information, in the framework of supervised graph inference. The originality of the methods is the introduction of chemical compatibility as a constraint for refining the network predicted by the network inference engine. The chemical compatibility between two enzymes is obtained automatically from the information encoded by their Enzyme Commission (EC) numbers. The proposed methods are tested and compared on their ability to infer the enzyme network of the yeast Saccharomyces cerevisiae from four datasets for enzymes with assigned EC numbers: gene expression data, protein localization data, phylogenetic profiles and chemical compatibility information. It is shown that the prediction accuracy of the network reconstruction consistently improves owing to the introduction of chemical constraints, the use of a supervised approach and the weighted integration of multiple datasets. Finally, we conduct a comprehensive prediction of a global enzyme network consisting of all enzyme candidate proteins of the yeast to obtain new biological findings.

    UR - http://www.scopus.com/inward/record.url?scp=29144446142&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=29144446142&partnerID=8YFLogxK

    U2 - 10.1093/bioinformatics/bti1012

    DO - 10.1093/bioinformatics/bti1012

    M3 - Article

    C2 - 15961492

    AN - SCOPUS:29144446142

    VL - 21

    SP - i468-i477

    JO - Bioinformatics

    JF - Bioinformatics

    SN - 1367-4803

    IS - SUPPL. 1

    ER -