XANNpred

Neural nets that predict the propensity of a protein to yield diffraction-quality crystals

Ian M. Overton, C. A. Johannes van Niekerk, Geoffrey J. Barton

    Research output: Contribution to journalArticle

    15 Citations (Scopus)

    Abstract

    Production of diffracting crystals is a critical step in determining the three-dimensional structure of a protein by X-ray crystallography. Computational techniques to rank proteins by their propensity to yield diffraction-quality crystals can improve efficiency in obtaining structural data by guiding both protein selection and construct design. XANNpred comprises a pair of artificial neural networks that each predict the propensity of a selected protein sequence to produce diffraction- quality crystals by current structural biology techniques. Blind tests show XANNpred has accuracy and Matthews correlation values ranging from 75% to 81% and 0.50 to 0.63 respectively; values of area under the receiver operator characteristic (ROC) curve range from 0.81 to 0.88. On blind test data XANNpred outperforms the other available algorithms XtalPred, PXS, OB-Score, and ParCrys. XANNpred also guides construct design by presenting graphs of predicted propensity for diffraction-quality crystals against residue sequence position. The XANNpred-SG algorithm is likely to be most useful to target selection in structural genomics consortia, while the XANNpred-PDB algorithm is more suited to the general structural biology community. XANNpred predictions that include sliding window graphs are freely available from http://www.compbio.dundee.ac.uk/xannpred

    Original languageEnglish
    Pages (from-to)1027-1033
    Number of pages7
    JournalProteins: Structure, Function, and Bioinformatics
    Volume79
    Issue number4
    DOIs
    Publication statusPublished - Apr 2011

    Keywords

    • computational biology
    • bioinformatics
    • crystallization
    • software
    • artificial neural network
    • predictor
    • GENOMICS TARGET SELECTION
    • X-RAY CRYSTALLOGRAPHY
    • STRUCTURAL GENOMICS
    • SEQUENCE ALIGNMENTS
    • CRYSTALLIZATION
    • DATABASE
    • THROUGHPUT
    • PROTEOMICS
    • STRATEGY
    • IMPACT

    Cite this

    @article{b3144af582a644dab32d81daa7bca45a,
    title = "XANNpred: Neural nets that predict the propensity of a protein to yield diffraction-quality crystals",
    abstract = "Production of diffracting crystals is a critical step in determining the three-dimensional structure of a protein by X-ray crystallography. Computational techniques to rank proteins by their propensity to yield diffraction-quality crystals can improve efficiency in obtaining structural data by guiding both protein selection and construct design. XANNpred comprises a pair of artificial neural networks that each predict the propensity of a selected protein sequence to produce diffraction- quality crystals by current structural biology techniques. Blind tests show XANNpred has accuracy and Matthews correlation values ranging from 75{\%} to 81{\%} and 0.50 to 0.63 respectively; values of area under the receiver operator characteristic (ROC) curve range from 0.81 to 0.88. On blind test data XANNpred outperforms the other available algorithms XtalPred, PXS, OB-Score, and ParCrys. XANNpred also guides construct design by presenting graphs of predicted propensity for diffraction-quality crystals against residue sequence position. The XANNpred-SG algorithm is likely to be most useful to target selection in structural genomics consortia, while the XANNpred-PDB algorithm is more suited to the general structural biology community. XANNpred predictions that include sliding window graphs are freely available from http://www.compbio.dundee.ac.uk/xannpred",
    keywords = "computational biology, bioinformatics, crystallization, software, artificial neural network, predictor, GENOMICS TARGET SELECTION, X-RAY CRYSTALLOGRAPHY, STRUCTURAL GENOMICS, SEQUENCE ALIGNMENTS, CRYSTALLIZATION, DATABASE, THROUGHPUT, PROTEOMICS, STRATEGY, IMPACT",
    author = "Overton, {Ian M.} and {van Niekerk}, {C. A. Johannes} and Barton, {Geoffrey J.}",
    year = "2011",
    month = "4",
    doi = "10.1002/prot.22914",
    language = "English",
    volume = "79",
    pages = "1027--1033",
    journal = "Proteins: Structure, Function, and Bioinformatics",
    issn = "0887-3585",
    publisher = "Wiley",
    number = "4",

    }

    XANNpred : Neural nets that predict the propensity of a protein to yield diffraction-quality crystals. / Overton, Ian M.; van Niekerk, C. A. Johannes; Barton, Geoffrey J.

    In: Proteins: Structure, Function, and Bioinformatics, Vol. 79, No. 4, 04.2011, p. 1027-1033.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - XANNpred

    T2 - Neural nets that predict the propensity of a protein to yield diffraction-quality crystals

    AU - Overton, Ian M.

    AU - van Niekerk, C. A. Johannes

    AU - Barton, Geoffrey J.

    PY - 2011/4

    Y1 - 2011/4

    N2 - Production of diffracting crystals is a critical step in determining the three-dimensional structure of a protein by X-ray crystallography. Computational techniques to rank proteins by their propensity to yield diffraction-quality crystals can improve efficiency in obtaining structural data by guiding both protein selection and construct design. XANNpred comprises a pair of artificial neural networks that each predict the propensity of a selected protein sequence to produce diffraction- quality crystals by current structural biology techniques. Blind tests show XANNpred has accuracy and Matthews correlation values ranging from 75% to 81% and 0.50 to 0.63 respectively; values of area under the receiver operator characteristic (ROC) curve range from 0.81 to 0.88. On blind test data XANNpred outperforms the other available algorithms XtalPred, PXS, OB-Score, and ParCrys. XANNpred also guides construct design by presenting graphs of predicted propensity for diffraction-quality crystals against residue sequence position. The XANNpred-SG algorithm is likely to be most useful to target selection in structural genomics consortia, while the XANNpred-PDB algorithm is more suited to the general structural biology community. XANNpred predictions that include sliding window graphs are freely available from http://www.compbio.dundee.ac.uk/xannpred

    AB - Production of diffracting crystals is a critical step in determining the three-dimensional structure of a protein by X-ray crystallography. Computational techniques to rank proteins by their propensity to yield diffraction-quality crystals can improve efficiency in obtaining structural data by guiding both protein selection and construct design. XANNpred comprises a pair of artificial neural networks that each predict the propensity of a selected protein sequence to produce diffraction- quality crystals by current structural biology techniques. Blind tests show XANNpred has accuracy and Matthews correlation values ranging from 75% to 81% and 0.50 to 0.63 respectively; values of area under the receiver operator characteristic (ROC) curve range from 0.81 to 0.88. On blind test data XANNpred outperforms the other available algorithms XtalPred, PXS, OB-Score, and ParCrys. XANNpred also guides construct design by presenting graphs of predicted propensity for diffraction-quality crystals against residue sequence position. The XANNpred-SG algorithm is likely to be most useful to target selection in structural genomics consortia, while the XANNpred-PDB algorithm is more suited to the general structural biology community. XANNpred predictions that include sliding window graphs are freely available from http://www.compbio.dundee.ac.uk/xannpred

    KW - computational biology

    KW - bioinformatics

    KW - crystallization

    KW - software

    KW - artificial neural network

    KW - predictor

    KW - GENOMICS TARGET SELECTION

    KW - X-RAY CRYSTALLOGRAPHY

    KW - STRUCTURAL GENOMICS

    KW - SEQUENCE ALIGNMENTS

    KW - CRYSTALLIZATION

    KW - DATABASE

    KW - THROUGHPUT

    KW - PROTEOMICS

    KW - STRATEGY

    KW - IMPACT

    U2 - 10.1002/prot.22914

    DO - 10.1002/prot.22914

    M3 - Article

    VL - 79

    SP - 1027

    EP - 1033

    JO - Proteins: Structure, Function, and Bioinformatics

    JF - Proteins: Structure, Function, and Bioinformatics

    SN - 0887-3585

    IS - 4

    ER -