COUSCOus: improved protein contact prediction using an empirical Bayes covariance estimator

BackgroundThe post-genomic era with its wealth of sequences gave rise to a broad range of protein residue-residue contact detecting methods. Although various coevolution methods such as PSICOV, DCA and plmDCA provide correct contact predictions, they do not completely overlap. Hence, new approaches and improvements of existing methods are needed to motivate further development and progress in the field. We present a new contact detecting method, COUSCOus, by combining the best shrinkage approach, the empirical Bayes covariance estimator and GLasso.ResultsUsing the original PSICOV benchmark dataset, COUSCOus achieves mean accuracies of 0.74, 0.62 and 0.55 for the top L/10 predicted long, medium and short range contacts, respectively. In addition, COUSCOus attains mean areas under the precision-recall curves of 0.25, 0.29 and 0.30 for long, medium and short contacts and outperforms PSICOV. We also observed that COUSCOus outperforms PSICOV w.r.t. Matthew’s correlation coefficient criterion on full list of residue contacts. Furthermore, COUSCOus achieves on average 10% more gain in prediction accuracy compared to PSICOV on an independent test set composed of CASP11 protein targets. Finally, we showed that when using a simple random forest meta-classifier, by combining contact detecting techniques and sequence derived features, PSICOV predictions should be replaced by the more accurate COUSCOus predictions.ConclusionWe conclude that the consideration of superior covariance shrinkage approaches will boost several research fields that apply the GLasso procedure, amongst the presented one of residue-residue contact prediction as well as fields such as gene network reconstruction.

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

[2]  Marcin J. Skwark,et al.  PconsC: combination of direct information methods and alignments improves contact prediction , 2013, Bioinform..

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

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

[5]  Erik van Nimwegen,et al.  Disentangling Direct from Indirect Co-Evolution of Residues in Protein Alignments , 2010, PLoS Comput. Biol..

[6]  David T. Jones,et al.  De Novo Structure Prediction of Globular Proteins Aided by Sequence Variation-Derived Contacts , 2014, PloS one.

[7]  Thomas A. Hopf,et al.  Protein structure prediction from sequence variation , 2012, Nature Biotechnology.

[8]  L. C. Martin,et al.  Using information theory to search for co-evolving residues in proteins , 2005, Bioinform..

[9]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[10]  Massimiliano Pontil,et al.  PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments , 2012, Bioinform..

[11]  Dominik Heider,et al.  Interpol: An R package for preprocessing of protein sequences , 2011, BioData Mining.

[12]  L. R. Haff.  Empirical Bayes Estimation of the Multivariate Normal Covariance Matrix , 1980 .

[13]  Ying Liu,et al.  Evol and ProDy for bridging protein sequence evolution and structural dynamics , 2014, Bioinform..

[14]  C. Yanofsky,et al.  Protein Structure Relationships Revealed by Mutational Analysis , 1964, Science.

[15]  Frank DiMaio,et al.  CASP11 refinement experiments with ROSETTA , 2016, Proteins.

[16]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[17]  David T. Jones,et al.  MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins , 2014, Bioinform..

[18]  Alfonso Valencia,et al.  Assessment of intramolecular contact predictions for CASP7 , 2007, Proteins.

[19]  D. Baker,et al.  Assessing the utility of coevolution-based residue–residue contact predictions in a sequence- and structure-rich era , 2013, Proceedings of the National Academy of Sciences.

[20]  Zhiyong Wang,et al.  Protein contact prediction by integrating joint evolutionary coupling analysis and supervised learning , 2013, Bioinform..

[21]  Alfonso Valencia,et al.  Emerging methods in protein co-evolution , 2013 .

[22]  S. Eddy,et al.  Pfam: the protein families database , 2013, Nucleic Acids Res..

[23]  T. Hwa,et al.  Identification of direct residue contacts in protein–protein interaction by message passing , 2009, Proceedings of the National Academy of Sciences.

[24]  Peter Dalgaard,et al.  R Development Core Team (2010): R: A language and environment for statistical computing , 2010 .

[25]  Olivier Ledoit,et al.  Improved estimation of the covariance matrix of stock returns with an application to portfolio selection , 2003 .

[26]  B. Matthews.  Comparison of the predicted and observed secondary structure of T4 phage lysozyme. , 1975, Biochimica et biophysica acta.

[27]  I. Johnstone.  On the distribution of the largest eigenvalue in principal components analysis , 2001 .

[28]  Michael I. Jordan.  Graphical Models , 2003 .

[29]  E. Aurell,et al.  Improved contact prediction in proteins: using pseudolikelihoods to infer Potts models. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[30]  Kevin M. Knight,et al.  NMR identification of the binding surfaces involved in the Salmonella and Shigella Type III secretion tip‐translocon protein–protein interactions , 2016, Proteins.

[31]  A. Horovitz,et al.  Mapping pathways of allosteric communication in GroEL by analysis of correlated mutations , 2002, Proteins.

[32]  Thomas A. Hopf,et al.  Three-Dimensional Structures of Membrane Proteins from Genomic Sequencing , 2012, Cell.

[33]  Burkhard Rost,et al.  FreeContact: fast and free software for protein contact prediction from residue co-evolution , 2014, BMC Bioinformatics.

[34]  N. Meinshausen,et al.  High-dimensional graphs and variable selection with the Lasso , 2006, math/0608017.

[35]  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.

[36]  W. Fitch,et al.  An improved method for determining codon variability in a gene and its application to the rate of fixation of mutations in evolution , 1970, Biochemical Genetics.

[37]  D. Baker,et al.  Robust and accurate prediction of residue–residue interactions across protein interfaces using evolutionary information , 2014, eLife.

[38]  Thomas A. Hopf,et al.  Protein 3D Structure Computed from Evolutionary Sequence Variation , 2011, PloS one.

[39]  Gregory B. Gloor,et al.  Mutual information without the influence of phylogeny or entropy dramatically improves residue contact prediction , 2008, Bioinform..

[40]  G. Gloor,et al.  Mutual information in protein multiple sequence alignments reveals two classes of coevolving positions. , 2005, Biochemistry.

[41]  C. Stein,et al.  Estimation with Quadratic Loss , 1992 .

[42]  Marcin J. Skwark,et al.  PconsFold: improved contact predictions improve protein models , 2014, Bioinform..

[43]  Thomas A. Hopf,et al.  Sequence co-evolution gives 3D contacts and structures of protein complexes , 2014, eLife.

[44]  Leo S. D. Caves,et al.  Bio3d: An R Package , 2022 .