Predicting the errors of predicted local backbone angles and non-local solvent- accessibilities of proteins by deep neural networks

MOTIVATION Backbone structures and solvent accessible surface area of proteins are benefited from continuous real value prediction because it removes the arbitrariness of defining boundary between different secondary-structure and solvent-accessibility states. However, lacking the confidence score for predicted values has limited their applications. Here we investigated whether or not we can make a reasonable prediction of absolute errors for predicted backbone torsion angles, Cα-atom-based angles and torsion angles, solvent accessibility, contact numbers and half-sphere exposures by employing deep neural networks. RESULTS We found that angle-based errors can be predicted most accurately with Spearman correlation coefficient (SPC) between predicted and actual errors at about 0.6. This is followed by solvent accessibility (SPC∼0.5). The errors on contact-based structural properties are most difficult to predict (SPC between 0.2 and 0.3). We showed that predicted errors are significantly better error indicators than the average errors based on secondary-structure and amino-acid residue types. We further demonstrated the usefulness of predicted errors in model quality assessment. These error or confidence indictors are expected to be useful for prediction, assessment, and refinement of protein structures. AVAILABILITY AND IMPLEMENTATION The method is available at http://sparks-lab.org as a part of SPIDER2 package. CONTACT yuedong.yang@griffith.edu.au or yaoqi.zhou@griffith.edu.auSupplementary information: Supplementary data are available at Bioinformatics online.

[1]  James G. Lyons,et al.  Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning , 2015, Scientific Reports.

[2]  Y. Duan,et al.  Trends in template/fragment-free protein structure prediction , 2010, Theoretical chemistry accounts.

[3]  K. Dill,et al.  The Protein-Folding Problem, 50 Years On , 2012, Science.

[4]  Gajendra P. S. Raghava,et al.  Evaluation of Protein Dihedral Angle Prediction Methods , 2014, PloS one.

[5]  Kuldip K. Paliwal,et al.  Highly accurate sequence-based prediction of half-sphere exposures of amino acid residues in proteins , 2016, Bioinform..

[6]  Jian Peng,et al.  Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields , 2015, Scientific Reports.

[7]  Yaoqi Zhou,et al.  A new size‐independent score for pairwise protein structure alignment and its application to structure classification and nucleic‐acid binding prediction , 2012, Proteins.

[8]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Asimul Islam,et al.  A review of methods available to estimate solvent-accessible surface areas of soluble proteins in the folded and unfolded states. , 2014, Current protein & peptide science.

[10]  Hongjun Bai,et al.  Assessment of template‐free modeling in CASP10 and ROLL , 2014, Proteins.

[11]  Yuedong Yang,et al.  Predicting continuous local structure and the effect of its substitution for secondary structure in fragment-free protein structure prediction. , 2009, Structure.

[12]  Jagath C Rajapakse,et al.  Prediction of protein relative solvent accessibility with a two‐stage SVM approach , 2005, Proteins.

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

[14]  Haesun Park,et al.  Prediction of protein relative solvent accessibility with support vector machines and long‐range interaction 3D local descriptor , 2004, Proteins.

[15]  Björn Wallner,et al.  Improved model quality assessment using ProQ2 , 2012, BMC Bioinformatics.

[16]  Rasmus Berg Palm,et al.  Prediction as a candidate for learning deep hierarchical models of data , 2012 .

[17]  T. Hamelryck.  An amino acid has two sides: A new 2D measure provides a different view of solvent exposure , 2005, Proteins.

[18]  Yaoqi Zhou,et al.  Prediction of One‐Dimensional Structural Properties Of Proteins by Integrated Neural Networks , 2010 .

[19]  N. Colloc'h,et al.  Comparison of three algorithms for the assignment of secondary structure in proteins: the advantages of a consensus assignment. , 1993, Protein engineering.

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

[21]  Yaoqi Zhou,et al.  Improving protein fold recognition and template-based modeling by employing probabilistic-based matching between predicted one-dimensional structural properties of query and corresponding native properties of templates , 2011, Bioinform..

[22]  Lukasz Kurgan,et al.  Structural protein descriptors in 1-dimension and their sequence-based predictions. , 2011, Current protein & peptide science.

[23]  Kuldip K. Paliwal,et al.  Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto‐encoder deep neural network , 2014, J. Comput. Chem..

[24]  Lukasz Kurgan,et al.  Sequence-Based Methods for Real Value Predictions of Protein Structure , 2008 .

[25]  A Keith Dunker,et al.  Assessing secondary structure assignment of protein structures by using pairwise sequence‐alignment benchmarks , 2008, Proteins.

[26]  Bela Stantic,et al.  EASE-MM: Sequence-Based Prediction of Mutation-Induced Stability Changes with Feature-Based Multiple Models. , 2016, Journal of molecular biology.