Predicting β-Turns in Protein Using Kernel Logistic Regression

A β-turn is a secondary protein structure type that plays a significant role in protein configuration and function. On average 25% of amino acids in protein structures are located in β-turns. It is very important to develope an accurate and efficient method for β-turns prediction. Most of the current successful β-turns prediction methods use support vector machines (SVMs) or neural networks (NNs). The kernel logistic regression (KLR) is a powerful classification technique that has been applied successfully in many classification problems. However, it is often not found in β-turns classification, mainly because it is computationally expensive. In this paper, we used KLR to obtain sparse β-turns prediction in short evolution time. Secondary structure information and position-specific scoring matrices (PSSMs) are utilized as input features. We achieved Q total of 80.7% and MCC of 50% on BT426 dataset. These results show that KLR method with the right algorithm can yield performance equivalent to or even better than NNs and SVMs in β-turns prediction. In addition, KLR yields probabilistic outcome and has a well-defined extension to multiclass case.

[1]  Chih-Jen Lin,et al.  Trust Region Newton Method for Logistic Regression , 2008, J. Mach. Learn. Res..

[2]  Rolf Apweiler,et al.  The SWISS-PROT protein sequence database and its supplement TrEMBL in 2000 , 2000, Nucleic Acids Res..

[3]  G. Singh.  Prediction of-turns in proteins from multiple alignment using neural network , 2002 .

[4]  T. N. Bhat,et al.  The Protein Data Bank , 2000, Nucleic Acids Res..

[5]  Menglong Li,et al.  Prediction of Beta-Turn in Protein Using E-SSpred and Support Vector Machine , 2009, The protein journal.

[6]  Chih-Jen Lin,et al.  Trust region Newton methods for large-scale logistic regression , 2007, ICML '07.

[7]  Pierre Baldi,et al.  Assessing the accuracy of prediction algorithms for classification: an overview , 2000, Bioinform..

[8]  G. Rose,et al.  Turns in peptides and proteins. , 1985, Advances in protein chemistry.

[9]  David S. Wishart,et al.  Improving the accuracy of protein secondary structure prediction using structural alignment , 2006, BMC Bioinformatics.

[10]  J. Thornton,et al.  A revised set of potentials for β‐turn formation in proteins , 1994 .

[11]  D Gorse,et al.  Prediction of the location and type of β‐turns in proteins using neural networks , 1999, Protein science : a publication of the Protein Society.

[12]  Hu Chen,et al.  A novel method for protein secondary structure prediction using dual‐layer SVM and profiles , 2004, Proteins.

[13]  G J Barton,et al.  Application of multiple sequence alignment profiles to improve protein secondary structure prediction , 2000, Proteins.

[14]  Lila M Gierasch,et al.  Roles of beta-turns in protein folding: from peptide models to protein engineering. , 2008, Biopolymers.

[15]  Lukasz A. Kurgan,et al.  Prediction of beta-turns at over 80% accuracy based on an ensemble of predicted secondary structures and multiple alignments , 2008, BMC Bioinformatics.

[16]  Xiuzhen Hu,et al.  Using support vector machine to predict β‐ and γ‐turns in proteins , 2008, J. Comput. Chem..

[17]  Liam J. McGuffin,et al.  Protein structure prediction servers at University College London , 2005, Nucleic Acids Res..

[18]  K. Chou,et al.  Prediction of protein structural classes. , 1995, Critical reviews in biochemistry and molecular biology.

[19]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[20]  Tu Bao Ho,et al.  Prediction and Analysis of β-Turns in Proteins by Support Vector Machine , 2003 .

[21]  S. Jois,et al.  Design of β-turn Based Therapeutic Agents , 2003 .

[22]  Liam J. McGuffin,et al.  The PSIPRED protein structure prediction server , 2000, Bioinform..

[23]  H. Dyson,et al.  Peptide conformation and protein folding , 1993 .

[24]  Axel T. Brünger,et al.  Amino-acid substitutions in a surface turn modulate protein stability , 1996, Nature Structural Biology.

[25]  Ivor W. Tsang,et al.  Improved Nyström low-rank approximation and error analysis , 2008, ICML '08.

[26]  D T Jones,et al.  Protein secondary structure prediction based on position-specific scoring matrices. , 1999, Journal of molecular biology.

[27]  Johan A. K. Suykens,et al.  Multi-class kernel logistic regression: a fixed-size implementation , 2007, IJCNN.

[28]  Morten Nielsen,et al.  Immunological bioinformatics , 2005, Computational molecular biology.

[29]  Claus Lundegaard,et al.  NetTurnP – Neural Network Prediction of Beta-turns by Use of Evolutionary Information and Predicted Protein Sequence Features , 2010, PloS one.

[30]  Peter Karsmakers,et al.  Sparse Kernel-Based Models for Speech Recognition (Spaarse kernel gebaseerde modellen voor spraakherkenning) , 2010 .

[31]  A. Alix,et al.  High accuracy prediction of β‐turns and their types using propensities and multiple alignments , 2005 .

[32]  Gajendra Pal Singh Raghava,et al.  Prediction of β‐turns in proteins from multiple alignment using neural network , 2003, Protein science : a publication of the Protein Society.

[33]  Jonathan D. Hirst,et al.  Predicting β-turns and their types using predicted backbone dihedral angles and secondary structures , 2010, BMC Bioinformatics.

[34]  Chun-Ting Zhang,et al.  Prediction of β‐turns in proteins by 1‐4 and 2‐3 correlation model , 1997 .