Predicting protein residue-residue contacts using random forests and deep networks

BackgroundThe ability to predict which pairs of amino acid residues in a protein are in contact with each other offers many advantages for various areas of research that focus on proteins. For example, contact prediction can be used to reduce the computational complexity of predicting the structure of proteins and even to help identify functionally important regions of proteins. These predictions are becoming especially important given the relatively low number of experimentally determined protein structures compared to the amount of available protein sequence data.ResultsHere we have developed and benchmarked a set of machine learning methods for performing residue-residue contact prediction, including random forests, direct-coupling analysis, support vector machines, and deep networks (stacked denoising autoencoders). These methods are able to predict contacting residue pairs given only the amino acid sequence of a protein. According to our own evaluations performed at a resolution of +/− two residues, the predictors we trained with the random forest algorithm were our top performing methods with average top 10 prediction accuracy scores of 85.13% (short range), 74.49% (medium range), and 54.49% (long range). Our ensemble models (stacked denoising autoencoders combined with support vector machines) were our best performing deep network predictors and achieved top 10 prediction accuracy scores of 75.51% (short range), 60.26% (medium range), and 43.85% (long range) using the same evaluation. These tests were blindly performed on targets from the CASP11 dataset; and the results suggested that our models achieved comparable performance to contact predictors developed by groups that participated in CASP11.ConclusionsDue to the challenging nature of contact prediction, it is beneficial to develop and benchmark a variety of different prediction methods. Our work has produced useful tools with a simple interface that can provide contact predictions to users without requiring a lengthy installation process. In addition to this, we have released our C++ implementation of the direct-coupling analysis method as a standalone software package. Both this tool and our RFcon web server are freely available to the public at http://dna.cs.miami.edu/RFcon/.

[1]  Jianlin Cheng,et al.  NNcon: improved protein contact map prediction using 2D-recursive neural networks , 2009, Nucleic Acids Res..

[2]  Jianlin Cheng,et al.  A study and benchmark of DNcon: a method for protein residue-residue contact prediction using deep networks , 2013, BMC Bioinformatics.

[3]  W. Atchley,et al.  Solving the protein sequence metric problem. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[4]  A. Biegert,et al.  HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment , 2011, Nature Methods.

[5]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[6]  A. Tramontano,et al.  Critical assessment of methods of protein structure prediction: Progress and new directions in round XI , 2016, Proteins.

[7]  Dong Xu,et al.  Predicting DNA Methylation State of CpG Dinucleotide Using Genome Topological Features and Deep Networks , 2016, Scientific Reports.

[8]  Zhen Li,et al.  Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model , 2016, bioRxiv.

[9]  Jianlin Cheng,et al.  MULTICOM: a multi-level combination approach to protein structure prediction and its assessments in CASP8 , 2010, Bioinform..

[10]  Yang Zhang,et al.  A comprehensive assessment of sequence-based and template-based methods for protein contact prediction , 2008, Bioinform..

[11]  M Michael Gromiha,et al.  Inter-residue interactions in protein folding and stability. , 2004, Progress in biophysics and molecular biology.

[12]  Zhendong Bei,et al.  COMSAT: Residue contact prediction of transmembrane proteins based on support vector machines and mixed integer linear programming , 2016, Proteins.

[13]  D. Higgins,et al.  Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega , 2011, Molecular systems biology.

[14]  Pierre Baldi,et al.  SCRATCH: a protein structure and structural feature prediction server , 2005, Nucleic Acids Res..

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

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

[17]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[18]  A. Tramontano,et al.  New encouraging developments in contact prediction: Assessment of the CASP11 results , 2016, Proteins.

[19]  Tao Zhang,et al.  Advances in human cytochrome p450 and personalized medicine. , 2011, Current drug metabolism.

[20]  C. Sander,et al.  Direct-coupling analysis of residue coevolution captures native contacts across many protein families , 2011, Proceedings of the National Academy of Sciences.

[21]  Jianlin Cheng,et al.  Predicting protein residue-residue contacts using deep networks and boosting , 2012, Bioinform..

[22]  Zheng Wang,et al.  Benchmarking Deep Networks for Predicting Residue-Specific Quality of Individual Protein Models in CASP11 , 2016, Scientific Reports.

[23]  Daniel J Rigden,et al.  Applications of contact predictions to structural biology , 2017, IUCrJ.

[24]  Christopher Bystroff,et al.  Predicting interresidue contacts using templates and pathways , 2003, Proteins.

[25]  Jianwen Fang,et al.  Predicting residue-residue contacts using random forest models , 2011, Bioinform..

[26]  P. Baldi,et al.  Prediction of coordination number and relative solvent accessibility in proteins , 2002, Proteins.

[27]  Jie Hou,et al.  DNCON2: improved protein contact prediction using two-level deep convolutional neural networks , 2017, bioRxiv.

[28]  Thorsten Joachims,et al.  Making large-scale support vector machine learning practical , 1999 .

[29]  Marcin J. Skwark,et al.  Improved Contact Predictions Using the Recognition of Protein Like Contact Patterns , 2014, PLoS Comput. Biol..

[30]  Pierre Baldi,et al.  Improved residue contact prediction using support vector machines and a large feature set , 2007, BMC Bioinformatics.

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

[32]  Conrad C. Huang,et al.  UCSF Chimera—A visualization system for exploratory research and analysis , 2004, J. Comput. Chem..