DP-bind

Service

Example

  • protein FC-FOS (PDB: 1A02)

Classifier and Major method

  • Two encoding methods for transforming amino acids into numeric format for calculating, that are PSSM-based and sequence-based (divided into BLOSUM62 and binary encoding)

  • Three kinds of the classifier: These three methods are classified into supervised pattern recognition in the machine-learning.

    1. Support vector machine (SVM): developed by Vapnik in 1998
    2. Kernel logistic regression (KLR): developed by Zhu and Hastie in 2005
    3. Penalized logistic regression (PLR): developed by le Cessie and van Houwelingen in 1992

  • Combination among results: Results from 3 classifiers are combined as one consensus result.

Dataset

  • PDNA-62: This dataset consisted of 62 protein sequences (non-redundant) which are experimentally solved protein-DNA complexes, utilized many time in the previous studies [5] and downloaded from the Protein Data Bank (PDB).

  • The training and testing procedures: Test the predictors through leave-out-protein-out cross validation.

Results

  • The best single prediction combination: PSSM-based and KLR in this dataset.

  • The consensus result would be the best prediction of the DNA-binding residues. Three classifiers represent the three aspects of biological meanings and considerations so that the performance would be the best one.

  • The major and strict consensuses are determined by voting from three classifiers.

Independent dataset

  • There is no independent dataset tested in this paper.

Reference

  1. Jagat S Chauhan et al. (2009) Identification of ATP binding residues of a protein from its primary sequence. BMC Bioinformatics 10:434 doi:10.1186/1471-2105-10-434

  2. Lukasz Kurgan et al. (2011) ATPsite: sequence-based prediction of ATP-binding residues. Proteome Science 9(Suppl 1):S4

  3. Manning, G., Whyte, D.B., Martinez, R., Hunter, T. and Sudarsanam, S. (2002) The protein kinase complement of the human genome. Science 298, 1912-1934

  4. Zhou FF, Xue Y, Chen GL, Yao X. (2004) GPS: a novel group-based phosphorylation predicting and scoring method. Biochem Biophys Res Commun 24;325(4):1443-8.

  5. Shandar Ahmad, M. Michael Gromiha and Akinori Sarai (2004) Analysis and prediction of DNA-binding proteins and their binding residues based on composition, sequence and structural information. BIOINFORMATICS Vol. 20 no. 4, pages 477–486 DOI: 10.1093/bioinformatics/btg432

  6. Seungwoo Hwang, Zhenkun Gou and Igor B. Kuznetsov(2007) DP-Bind: a web server for sequence-based prediction of DNA-binding residues in DNA-binding proteins. BIOINFORMATICS Vol. 23 no. 5, pages 634–636 doi:10.1093/bioinformatics/btl672

results matching ""

    No results matching ""