Prediction of the types of ion channel-targeted conotoxins based on radial basis function network.

Conotoxins are small disulfide-rich peptide toxins, which have the exceptional diversity of sequences. Because conotoxins are able to specifically bind to ion channels and interfere with neurotransmission, they are considered as the excellent pharmacological candidates in drug design. Appropriate type assignment of newly sequenced mature ion channel-targeted conotoxins with computational method is conducive to explore the biological and pharmacological functions of conotoxins. In this paper, we developed a novel method based on binomial distribution and radial basis function network to predict the types of ion-channel targeted conotoxins. We achieved the overall accuracy of 89.3% with average accuracy of 89.7% in the prediction of three types of ion channel-targeted conotoxins in jackknife cross-validation test, indicating that the method is superior to other state-of-the-art methods. In addition, we evaluated the proposed model with an independent dataset including 77 conotoxins. The overall accuracy of 85.7% was achieved, validating that our model is reliable. Moreover, we used the proposed method to annotate 336 function-undefined mature conotoxins in the UniProt Database. The model provides the valuable instructions for theoretical and experimental research on conotoxins.

[1]  Daisuke Kihara,et al.  Prediction of Membrane Proteins in Post-Genomic Era , 2007 .

[2]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[3]  Hong-Bin Shen,et al.  Conotoxin superfamily prediction using diffusion maps dimensionality reduction and subspace classifier. , 2011, Current protein & peptide science.

[4]  M. Gromiha,et al.  Classification of transporters using efficient radial basis function networks with position‐specific scoring matrices and biochemical properties , 2010, Proteins.

[5]  Chin-Teng Lin,et al.  Protein Metal Binding Residue Prediction Based on Neural Networks , 2004, ICONIP.

[6]  Adam Godzik,et al.  Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences , 2006, Bioinform..

[7]  Kuo-Chen Chou,et al.  QuatIdent: a web server for identifying protein quaternary structural attribute by fusing functional domain and sequential evolution information. , 2009, Journal of proteome research.

[8]  Yu-Dong Cai,et al.  Predicting protease types by hybridizing gene ontology and pseudo amino acid composition , 2006, Proteins.

[9]  Lin Lu,et al.  GalNAc-transferase specificity prediction based on feature selection method , 2009, Peptides.

[10]  J C Lindon,et al.  Classification of toxin-induced changes in 1H NMR spectra of urine using an artificial neural network. , 1995, Journal of pharmaceutical and biomedical analysis.

[11]  Norelle L Daly,et al.  Structural studies of conotoxins , 2009, IUBMB life.

[12]  Hui Ding,et al.  Predicting ion channels and their types by the dipeptide mode of pseudo amino acid composition. , 2011, Journal of theoretical biology.

[13]  Paul Horton,et al.  Discrimination of outer membrane proteins using support vector machines , 2005, Bioinform..

[14]  Yu-Yen Ou,et al.  Prediction of transporter targets using efficient RBF networks with PSSM profiles and biochemical properties , 2011, Bioinform..

[15]  Xiaoyong Zou,et al.  Using pseudo-amino acid composition and support vector machine to predict protein structural class. , 2006, Journal of theoretical biology.

[16]  Vladimir Brusic,et al.  Bioinformatics for Venom and Toxin Sciences , 2003, Briefings Bioinform..

[17]  Nazar Zaki,et al.  Conotoxin protein classification using pairwise comparison and amino acid composition: toxin-aam , 2011, GECCO '11.

[18]  K. Chou.  Some remarks on protein attribute prediction and pseudo amino acid composition , 2010, Journal of Theoretical Biology.

[19]  Kuo-Chen Chou,et al.  Using pseudo amino acid composition to predict protein structural classes: Approached with complexity measure factor , 2006, J. Comput. Chem..

[20]  Liaofu Luo,et al.  Use of  tetrapeptide signals for protein secondary-structure prediction , 2008, Amino Acids.

[21]  Michele Magrane,et al.  UniProt Knowledgebase: a hub of integrated protein data , 2011, Database J. Biol. Databases Curation.

[22]  Mohammed Yeasin,et al.  Prediction of membrane proteins using split amino acid and ensemble classification , 2011, Amino Acids.

[23]  K. Chou.  Prediction of protein cellular attributes using pseudo‐amino acid composition , 2001, Proteins.

[24]  Nazar Zaki,et al.  Conotoxin protein classification using free scores of words and support vector machines , 2011, BMC Bioinformatics.

[25]  C. Chi,et al.  Identification of a novel class of conotoxins defined as V-conotoxins with a unique cysteine pattern and signal peptide sequence , 2008, Peptides.

[26]  B. Olivera,et al.  Conus venoms: a rich source of novel ion channel-targeted peptides. , 2004, Physiological reviews.

[27]  P. Iengar,et al.  Probing peptide libraries from Conus achatinus using mass spectrometry and cDNA sequencing: identification of delta and omega-conotoxins. , 2008, Journal of mass spectrometry : JMS.

[28]  Jiangning Song,et al.  PredCSF: an integrated feature-based approach for predicting conotoxin superfamily. , 2011, Protein and peptide letters.

[29]  G. Bulaj,et al.  Conus venoms - a rich source of peptide-based therapeutics. , 2008, Current pharmaceutical design.

[30]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Hao Lin,et al.  Predicting conotoxin superfamily and family by using pseudo amino acid composition and modified Mahalanobis discriminant. , 2007, Biochemical and biophysical research communications.

[32]  Yu-Yen Ou,et al.  TMBETADISC-RBF: Discrimination of beta-barrel membrane proteins using RBF networks and PSSM profiles , 2008, Comput. Biol. Chem..

[33]  Kuo-Chen Chou,et al.  Predict and analyze S-nitrosylation modification sites with the mRMR and IFS approaches. , 2012, Journal of proteomics.

[34]  C. Chi,et al.  Identification of a novel S-superfamily conotoxin from vermivorous Conus caracteristicus. , 2008, Toxicon : official journal of the International Society on Toxinology.

[35]  Kuo-Chen Chou,et al.  GPCR-2 L : predicting G protein-coupled receptors and their types by hybridizing two different modes of pseudo amino acid compositions w , 2010 .

[36]  A. Cappello,et al.  Feature selection of stabilometric parameters based on principal component analysis , 2006, Medical and Biological Engineering and Computing.

[37]  Sukanta Mondal,et al.  Pseudo amino acid composition and multi-class support vector machines approach for conotoxin superfamily classification. , 2006, Journal of theoretical biology.

[38]  Kuo-Chen Chou,et al.  Classification and Analysis of Regulatory Pathways Using Graph Property, Biochemical and Physicochemical Property, and Functional Property , 2011, PloS one.

[39]  M. Watters.  Tropical marine neurotoxins: venoms to drugs. , 2005, Seminars in neurology.