MetaPSICOV: combining coevolution methods for accurate prediction of contacts and long range hydrogen bonding in proteins

By David T. Jones, Tanya Singh, T. Kościółek, Stuart J. Tetchner. 2014

335 citations recorded by the source corpus.

Motivation: Recent developments of statistical techniques to infer direct evolutionary couplings between residue pairs have rendered covariation-based contact prediction a viable means for accurate 3D modelling of proteins, with no information other than the sequence required. To extend the usefulness of contact prediction, we have designed a new meta-predictor (MetaPSICOV) which combines three distinct approaches for inferring covariation signals from multiple sequence alignments, considers a broad range of other sequence-derived features and, uniquely, a range of metrics which describe both the local and global quality of the input multiple sequence alignment. Finally, we use a two-stage predictor, where the second stage filters the output of the first stage. This two-stage predictor is additionally evaluated on its ability to accurately predict the long range network of hydrogen bonds, including correctly assigning the donor and acceptor residues. Results: Using the original PSICOV benchmark set of 150 protein families, MetaPSICOV achieves a mean precision of 0.54 for top-L predicted long range contacts—around 60% higher than PSICOV, and around 40% better than CCMpred. In de novo protein structure prediction using FRAGFOLD, MetaPSICOV is able to improve the TM-scores of models by a median of 0.05 compared with PSICOV. Lastly, for predicting long range hydrogen bonding, MetaPSICOV-HB achieves a precision of 0.69 for the top-L/10 hydrogen bonds compared with just 0.26 for the baseline MetaPSICOV. Availability and implementation: MetaPSICOV is available as a freely available web server at http://bioinf.cs.ucl.ac.uk/MetaPSICOV. Raw data (predicted contact lists and 3D models) and source code can be downloaded from http://bioinf.cs.ucl.ac.uk/downloads/MetaPSICOV. Contact: d.t.jones@ucl.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.

Subfields: Molecular Biology, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Computational Biology & Bioinformatics

Citations in the corpus

Opportunities and obstacles for deep learning in biology and medicine (2017, methodology): “By combining co-evolution information with a few other protein features, shallow neural network methods such as MetaPSICOV [188] and CoinDCA-NN [195] have shown some advantage over pure co-evolution analysis for proteins with few sequence homologs, but their accuracy is still far from satisfactory.”
Evolutionary context-integrated deep sequence modeling for protein engineering (2020, background): “Rational design is oftentimes assisted by quantitative approaches to evaluate sequences that fold into a specific structure, including biophysical modeling [3,4] , force field approximations [5–7] , structure prediction [8–10] , and molecular dynamics simulations [11] .”
DEEPCON: Protein Contact Prediction using Dilated Convolutional Neural Networks with Dropout (2019, methodology): “In addition, a typical protein contact map, which is a binary matrix, is around 95% zeros and 5% ones [15].”
Distance-based protein folding powered by deep learning (2018, methodology): “10 and 12, without extensive fragment-based conformation sampling, the 3D models constructed from contacts predicted by RaptorX-Contact have much better quality than those built from contacts predicted by DCA methods such as CCMpred (6) and the CASP11 winner MetaPSICOV (18).”
Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13) (2019, methodology): “Contact predictionhas been extensively used instructure prediction 16,20,29,31 but previous work has also made residue distance predictions, 3,35 and these were used for structure prediction in CASP13 by other groups in distance geometry approaches.”
Enhancing Evolutionary Couplings with Deep Convolutional Neural Networks (2017, methodology): “Despite only submitting 54/57 targets for the joint set of FM and FM/TBM targets due to the submission script bug, DeepContact achieved an experiment best overall average F1 score, including 0 for the 3 missed targets, of 23.226 (iFold_1) with MetaPSICOV (Jones et al., 2015) the next best non-DeepCo”
Folding membrane proteins by deep transfer learning (2017, background): “Supervised learning predicts contacts from a variety of information, e.g., SVMSEQ(Wu and Zhang, 2008), CMAPpro (Di Lena et al., 2012), PconsC2 (Skwark et al., 2014) and PconsC3 (Skwark et al., 2016), MetaPSICOV (Jones et al., 2015), PhyCMAP (Wang and Xu, 2013) and CoinDCA-NN (Ma et al., 2015).”
Accurate contact predictions using covariation techniques and machine learning (2015, methodology): “An important aspect of MetaPSICOV is its ability to modulate the relative impact of covariation-based and classical features depending on the quality and depth of the MSA.”
Blind prediction of homo- and hetero-protein complexes: The CASP13-CAPRI experiment (2019, neutral): “10-12 Owing to the recent explosion of the number of available protein sequences, and progress in computational methods for exploiting them to predict residue-residue contacts, 13-15 the ability to model protein structures in absence of available templates has also made significant strides forward.”