Simultaneous inference of biological networks of multiple species from genome-wide data and evolutionary information

A semi-supervised approach

Hisashi Kashima, Yoshihiro Yamanishi, Tsuyoshi Kato, Masashi Sugiyama, Koji Tsuda

    Research output: Contribution to journalArticle

    15 Citations (Scopus)

    Abstract

    Motivation: The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. Results: We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of Caenorhabditis elegans, Helicobacter pylori and Saccharomyces cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

    Original languageEnglish
    Pages (from-to)2962-2968
    Number of pages7
    JournalBioinformatics
    Volume25
    Issue number22
    DOIs
    Publication statusPublished - Nov 15 2009

    Fingerprint

    Simultaneous Inference
    Biological Networks
    Gene expression
    Genome
    Genes
    Supervised learning
    Yeast
    Support vector machines
    Amino acids
    Genomics
    Amino Acids
    Gene Expression
    Semi-supervised Learning
    Metabolic Network
    Caenorhabditis elegans
    Saccharomyces Cerevisiae
    Amino Acid Sequence
    Gene Expression Data
    Metabolic Networks and Pathways
    Helicobacter pylori

    All Science Journal Classification (ASJC) codes

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

    Cite this

    Simultaneous inference of biological networks of multiple species from genome-wide data and evolutionary information : A semi-supervised approach. / Kashima, Hisashi; Yamanishi, Yoshihiro; Kato, Tsuyoshi; Sugiyama, Masashi; Tsuda, Koji.

    In: Bioinformatics, Vol. 25, No. 22, 15.11.2009, p. 2962-2968.

    Research output: Contribution to journalArticle

    Kashima, Hisashi ; Yamanishi, Yoshihiro ; Kato, Tsuyoshi ; Sugiyama, Masashi ; Tsuda, Koji. / Simultaneous inference of biological networks of multiple species from genome-wide data and evolutionary information : A semi-supervised approach. In: Bioinformatics. 2009 ; Vol. 25, No. 22. pp. 2962-2968.
    @article{135458cd67e543f8a56ef5226744ebcf,
    title = "Simultaneous inference of biological networks of multiple species from genome-wide data and evolutionary information: A semi-supervised approach",
    abstract = "Motivation: The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. Results: We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of Caenorhabditis elegans, Helicobacter pylori and Saccharomyces cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.",
    author = "Hisashi Kashima and Yoshihiro Yamanishi and Tsuyoshi Kato and Masashi Sugiyama and Koji Tsuda",
    year = "2009",
    month = "11",
    day = "15",
    doi = "10.1093/bioinformatics/btp494",
    language = "English",
    volume = "25",
    pages = "2962--2968",
    journal = "Bioinformatics",
    issn = "1367-4803",
    publisher = "Oxford University Press",
    number = "22",

    }

    TY - JOUR

    T1 - Simultaneous inference of biological networks of multiple species from genome-wide data and evolutionary information

    T2 - A semi-supervised approach

    AU - Kashima, Hisashi

    AU - Yamanishi, Yoshihiro

    AU - Kato, Tsuyoshi

    AU - Sugiyama, Masashi

    AU - Tsuda, Koji

    PY - 2009/11/15

    Y1 - 2009/11/15

    N2 - Motivation: The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. Results: We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of Caenorhabditis elegans, Helicobacter pylori and Saccharomyces cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

    AB - Motivation: The existing supervised methods for biological network inference work on each of the networks individually based only on intra-species information such as gene expression data. We believe that it will be more effective to use genomic data and cross-species evolutionary information from different species simultaneously, rather than to use the genomic data alone. Results: We created a new semi-supervised learning method called Link Propagation for inferring biological networks of multiple species based on genome-wide data and evolutionary information. The new method was applied to simultaneous reconstruction of three metabolic networks of Caenorhabditis elegans, Helicobacter pylori and Saccharomyces cerevisiae, based on gene expression similarities and amino acid sequence similarities. The experimental results proved that the new simultaneous network inference method consistently improves the predictive performance over the individual network inferences, and it also outperforms in accuracy and speed other established methods such as the pairwise support vector machine.

    UR - http://www.scopus.com/inward/record.url?scp=70449341660&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70449341660&partnerID=8YFLogxK

    U2 - 10.1093/bioinformatics/btp494

    DO - 10.1093/bioinformatics/btp494

    M3 - Article

    VL - 25

    SP - 2962

    EP - 2968

    JO - Bioinformatics

    JF - Bioinformatics

    SN - 1367-4803

    IS - 22

    ER -