14-3-3-Pred

Improved methods to predict 14-3-3-binding phosphopeptides

Fábio Madeira, Michele Tinti, Gavuthami Murugesan, Emily Berrett, Margaret Stafford, Rachel Toth, Christian Cole, Carol MacKintosh, Geoffrey J. Barton (Lead / Corresponding author)

    Research output: Contribution to journalArticle

    40 Citations (Scopus)
    238 Downloads (Pure)

    Abstract

    Motivation: The 14-3-3 family of phosphoprotein-binding proteins regulate many cellular processes by docking onto pairs of phosphorylated Ser and Thr residues in a constellation of intracellular targets. Therefore, there is a pressing need to develop new prediction methods that use an updated set of 14-3-3-binding motifs for the identification of new 14-3-3 targets, and to prioritize the downstream analysis of >2000 potential interactors identified in high-throughput experiments.

    Results: Here, a comprehensive set of 14-3-3-binding targets from the literature was used to develop 14-3-3-binding phosphosite predictors. Position-specific scoring matrix (PSSM), support vector machines (SVM), and artificial neural network (ANN) classification methods were trained to discriminate experimentally-determined 14-3-3-binding motifs from non-binding phosphopeptides. ANN, PSSM and SVM methods showed best performance for a motif window spanning from -6 to +4 around the binding phosphosite, achieving Matthews correlation coefficient of up to 0.60. Blind prediction showed that all three methods outperform two popular 14-3-3-binding site predictors, Scansite and ELM. The new methods were used for prediction of 14-3-3-binding phosphosites in the human proteome. Experimental analysis of high-scoring predictions in the FAM122A and FAM122B proteins confirms the predictions and suggests the new 14-3-3-predictors will be generally useful.

    Availability: A standalone prediction webserver is available at http://www.compbio.dundee.ac.uk/1433pred. Human candidate 14-3-3-binding phosphosites were integrated in ANIA: ANnotation and Integrated Analysis of the 14-3-3 interactome database.

    Contact: cmackintosh@dundee.ac.uk and gjbarton@dundee.ac.uk

    Supplementary information: Supplementary data are available at Bioinformatics online.

    Original languageEnglish
    JournalBioinformatics
    Early online date3 Mar 2015
    DOIs
    Publication statusPublished - 2015

    Fingerprint

    Phosphopeptides
    Predict
    Position-Specific Scoring Matrices
    Prediction
    Scoring
    Support vector machines
    Predictors
    Phosphoproteins
    Neural networks
    Proteins
    Proteome
    Computational Biology
    Target
    Artificial Neural Network
    Support Vector Machine
    Binding sites
    Bioinformatics
    Carrier Proteins
    Protein
    Binding Sites

    Cite this

    @article{d2bcb6df6f0c41a6be366d23184ea60e,
    title = "14-3-3-Pred: Improved methods to predict 14-3-3-binding phosphopeptides",
    abstract = "Motivation: The 14-3-3 family of phosphoprotein-binding proteins regulate many cellular processes by docking onto pairs of phosphorylated Ser and Thr residues in a constellation of intracellular targets. Therefore, there is a pressing need to develop new prediction methods that use an updated set of 14-3-3-binding motifs for the identification of new 14-3-3 targets, and to prioritize the downstream analysis of >2000 potential interactors identified in high-throughput experiments.Results: Here, a comprehensive set of 14-3-3-binding targets from the literature was used to develop 14-3-3-binding phosphosite predictors. Position-specific scoring matrix (PSSM), support vector machines (SVM), and artificial neural network (ANN) classification methods were trained to discriminate experimentally-determined 14-3-3-binding motifs from non-binding phosphopeptides. ANN, PSSM and SVM methods showed best performance for a motif window spanning from -6 to +4 around the binding phosphosite, achieving Matthews correlation coefficient of up to 0.60. Blind prediction showed that all three methods outperform two popular 14-3-3-binding site predictors, Scansite and ELM. The new methods were used for prediction of 14-3-3-binding phosphosites in the human proteome. Experimental analysis of high-scoring predictions in the FAM122A and FAM122B proteins confirms the predictions and suggests the new 14-3-3-predictors will be generally useful. Availability: A standalone prediction webserver is available at http://www.compbio.dundee.ac.uk/1433pred. Human candidate 14-3-3-binding phosphosites were integrated in ANIA: ANnotation and Integrated Analysis of the 14-3-3 interactome database.Contact: cmackintosh@dundee.ac.uk and gjbarton@dundee.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.",
    author = "F{\'a}bio Madeira and Michele Tinti and Gavuthami Murugesan and Emily Berrett and Margaret Stafford and Rachel Toth and Christian Cole and Carol MacKintosh and Barton, {Geoffrey J.}",
    note = "{\circledC} The Author(s) 2015. Published by Oxford University Press.",
    year = "2015",
    doi = "10.1093/bioinformatics/btv133",
    language = "English",
    journal = "Bioinformatics",
    issn = "1367-4803",
    publisher = "Oxford University Press",

    }

    14-3-3-Pred : Improved methods to predict 14-3-3-binding phosphopeptides. / Madeira, Fábio; Tinti, Michele; Murugesan, Gavuthami; Berrett, Emily; Stafford, Margaret; Toth, Rachel; Cole, Christian; MacKintosh, Carol; Barton, Geoffrey J. (Lead / Corresponding author).

    In: Bioinformatics, 2015.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - 14-3-3-Pred

    T2 - Improved methods to predict 14-3-3-binding phosphopeptides

    AU - Madeira, Fábio

    AU - Tinti, Michele

    AU - Murugesan, Gavuthami

    AU - Berrett, Emily

    AU - Stafford, Margaret

    AU - Toth, Rachel

    AU - Cole, Christian

    AU - MacKintosh, Carol

    AU - Barton, Geoffrey J.

    N1 - © The Author(s) 2015. Published by Oxford University Press.

    PY - 2015

    Y1 - 2015

    N2 - Motivation: The 14-3-3 family of phosphoprotein-binding proteins regulate many cellular processes by docking onto pairs of phosphorylated Ser and Thr residues in a constellation of intracellular targets. Therefore, there is a pressing need to develop new prediction methods that use an updated set of 14-3-3-binding motifs for the identification of new 14-3-3 targets, and to prioritize the downstream analysis of >2000 potential interactors identified in high-throughput experiments.Results: Here, a comprehensive set of 14-3-3-binding targets from the literature was used to develop 14-3-3-binding phosphosite predictors. Position-specific scoring matrix (PSSM), support vector machines (SVM), and artificial neural network (ANN) classification methods were trained to discriminate experimentally-determined 14-3-3-binding motifs from non-binding phosphopeptides. ANN, PSSM and SVM methods showed best performance for a motif window spanning from -6 to +4 around the binding phosphosite, achieving Matthews correlation coefficient of up to 0.60. Blind prediction showed that all three methods outperform two popular 14-3-3-binding site predictors, Scansite and ELM. The new methods were used for prediction of 14-3-3-binding phosphosites in the human proteome. Experimental analysis of high-scoring predictions in the FAM122A and FAM122B proteins confirms the predictions and suggests the new 14-3-3-predictors will be generally useful. Availability: A standalone prediction webserver is available at http://www.compbio.dundee.ac.uk/1433pred. Human candidate 14-3-3-binding phosphosites were integrated in ANIA: ANnotation and Integrated Analysis of the 14-3-3 interactome database.Contact: cmackintosh@dundee.ac.uk and gjbarton@dundee.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.

    AB - Motivation: The 14-3-3 family of phosphoprotein-binding proteins regulate many cellular processes by docking onto pairs of phosphorylated Ser and Thr residues in a constellation of intracellular targets. Therefore, there is a pressing need to develop new prediction methods that use an updated set of 14-3-3-binding motifs for the identification of new 14-3-3 targets, and to prioritize the downstream analysis of >2000 potential interactors identified in high-throughput experiments.Results: Here, a comprehensive set of 14-3-3-binding targets from the literature was used to develop 14-3-3-binding phosphosite predictors. Position-specific scoring matrix (PSSM), support vector machines (SVM), and artificial neural network (ANN) classification methods were trained to discriminate experimentally-determined 14-3-3-binding motifs from non-binding phosphopeptides. ANN, PSSM and SVM methods showed best performance for a motif window spanning from -6 to +4 around the binding phosphosite, achieving Matthews correlation coefficient of up to 0.60. Blind prediction showed that all three methods outperform two popular 14-3-3-binding site predictors, Scansite and ELM. The new methods were used for prediction of 14-3-3-binding phosphosites in the human proteome. Experimental analysis of high-scoring predictions in the FAM122A and FAM122B proteins confirms the predictions and suggests the new 14-3-3-predictors will be generally useful. Availability: A standalone prediction webserver is available at http://www.compbio.dundee.ac.uk/1433pred. Human candidate 14-3-3-binding phosphosites were integrated in ANIA: ANnotation and Integrated Analysis of the 14-3-3 interactome database.Contact: cmackintosh@dundee.ac.uk and gjbarton@dundee.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.

    U2 - 10.1093/bioinformatics/btv133

    DO - 10.1093/bioinformatics/btv133

    M3 - Article

    JO - Bioinformatics

    JF - Bioinformatics

    SN - 1367-4803

    ER -