Dataset Information

RDb2C2: an improved method to identify the residue-residue pairing in ? strands.

ABSTRACT: BACKGROUND:Despite the great advance of protein structure prediction, accurate prediction of the structures of mainly ? proteins is still highly challenging, but could be assisted by the knowledge of residue-residue pairing in ? strands. Previously, we proposed a ridge-detection-based algorithm RDb2C that adopted a multi-stage random forest framework to predict the ?-? pairing given the amino acid sequence of a protein. RESULTS:In this work, we developed a second version of this algorithm, RDb2C2, by employing the residual neural network to further enhance the prediction accuracy. In the benchmark test, this new algorithm improves the F1-score by >?10 percentage points, reaching impressively high values of ~?72% and ~?73% in the BetaSheet916 and BetaSheet1452 sets, respectively. CONCLUSION:Our new method promotes the prediction accuracy of ?-? pairing to a new level and the prediction results could better assist the structure modeling of mainly ? proteins. We prepared an online server of RDb2C2 at http://structpred.life.tsinghua.edu.cn/rdb2c2.html.

SUBMITTER: Shao D

PROVIDER: S-EPMC7126467 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

RDb<sub>2</sub>C2: an improved method to identify the residue-residue pairing in β strands.

Shao Di D Mao Wenzhi W Xing Yaoguang Y Gong Haipeng H

BMC bioinformatics 20200403 1

<h4>Background</h4>Despite the great advance of protein structure prediction, accurate prediction of the structures of mainly β proteins is still highly challenging, but could be assisted by the knowledge of residue-residue pairing in β strands. Previously, we proposed a ridge-detection-based algorithm RDb<sub>2</sub>C that adopted a multi-stage random forest framework to predict the β-β pairing given the amino acid sequence of a protein.<h4>Results</h4>In this work, we developed a second versio ...[more]

PMID: 32245403

Similar Datasets

Project description:BACKGROUND:Despite the rapid progress of protein residue contact prediction, predicted residue contact maps frequently contain many errors. However, information of residue pairing in ? strands could be extracted from a noisy contact map, due to the presence of characteristic contact patterns in ?-? interactions. This information may benefit the tertiary structure prediction of mainly ? proteins. In this work, we propose a novel ridge-detection-based ?-? contact predictor to identify residue pairing in ? strands from any predicted residue contact map. RESULTS:Our algorithm RDb2C adopts ridge detection, a well-developed technique in computer image processing, to capture consecutive residue contacts, and then utilizes a novel multi-stage random forest framework to integrate the ridge information and additional features for prediction. Starting from the predicted contact map of CCMpred, RDb2C remarkably outperforms all state-of-the-art methods on two conventional test sets of ? proteins (BetaSheet916 and BetaSheet1452), and achieves F1-scores of ~?62% and ~?76% at the residue level and strand level, respectively. Taking the prediction of the more advanced RaptorX-Contact as input, RDb2C achieves impressively higher performance, with F1-scores reaching ~?76% and ~?86% at the residue level and strand level, respectively. In a test of structural modeling using the top 1 L predicted contacts as constraints, for 61 mainly ? proteins, the average TM-score achieves 0.442 when using the raw RaptorX-Contact prediction, but increases to 0.506 when using the improved prediction by RDb2C. CONCLUSION:Our method can significantly improve the prediction of ?-? contacts from any predicted residue contact maps. Prediction results of our algorithm could be directly applied to effectively facilitate the practical structure prediction of mainly ? proteins. AVAILABILITY:All source data and codes are available at http://166.111.152.91/Downloads.html or the GitHub address of https://github.com/wzmao/RDb2C .

Project description:BackgroundA protein binding hot spot is a small cluster of residues tightly packed at the center of the interface between two interacting proteins. Though a hot spot constitutes a small fraction of the interface, it is vital to the stability of protein complexes. Recently, there are a series of hypotheses proposed to characterize binding hot spots, including the pioneering O-ring theory, the insightful 'coupling' and 'hot region' principle, and our 'double water exclusion' (DWE) hypothesis. As the perspective changes from the O-ring theory to the DWE hypothesis, we examine the physicochemical properties of the binding hot spots under the new hypothesis and compare with those under the O-ring theory.ResultsThe requirements for a cluster of residues to form a hot spot under the DWE hypothesis can be mathematically satisfied by a biclique subgraph if a vertex is used to represent a residue, an edge to indicate a close distance between two residues, and a bipartite graph to represent a pair of interacting proteins. We term these hot spots as DWE bicliques. We identified DWE bicliques from crystal packing contacts, obligate and non-obligate interactions. Our comparative study revealed that there are abundant unique bicliques to the biological interactions, indicating specific biological binding behaviors in contrast to crystal packing. The two sub-types of biological interactions also have their own signature bicliques. In our analysis on residue compositions and residue pairing preferences in DWE bicliques, the focus was on interaction-preferred residues (ipRs) and interaction-preferred residue pairs (ipRPs). It is observed that hydrophobic residues are heavily involved in the ipRs and ipRPs of the obligate interactions; and that aromatic residues are in favor in the ipRs and ipRPs of the biological interactions, especially in those of the non-obligate interactions. In contrast, the ipRs and ipRPs in crystal packing are dominated by hydrophilic residues, and most of the anti-ipRs of crystal packing are the ipRs of the obligate or non-obligate interactions.ConclusionsThese ipRs and ipRPs in our DWE bicliques describe a diverse binding features among the three types of interactions. They also highlight the specific binding behaviors of the biological interactions, sharply differing from the artifact interfaces in the crystal packing. It can be noted that DWE bicliques, especially the unique bicliques, can capture deep insights into the binding characteristics of protein interfaces.

Project description:BackgroundIn structural biology area, protein residue-residue contacts play a crucial role in protein structure prediction. Some researchers have found that the predicted residue-residue contacts could effectively constrain the conformational search space, which is significant for de novo protein structure prediction. In the last few decades, related researchers have developed various methods to predict residue-residue contacts, especially, significant performance has been achieved by using fusion methods in recent years. In this work, a novel fusion method based on rank strategy has been proposed to predict contacts. Unlike the traditional regression or classification strategies, the contact prediction task is regarded as a ranking task. First, two kinds of features are extracted from correlated mutations methods and ensemble machine-learning classifiers, and then the proposed method uses the learning-to-rank algorithm to predict contact probability of each residue pair.ResultsFirst, we perform two benchmark tests for the proposed fusion method (RRCRank) on CASP11 dataset and CASP12 dataset respectively. The test results show that the RRCRank method outperforms other well-developed methods, especially for medium and short range contacts. Second, in order to verify the superiority of ranking strategy, we predict contacts by using the traditional regression and classification strategies based on the same features as ranking strategy. Compared with these two traditional strategies, the proposed ranking strategy shows better performance for three contact types, in particular for long range contacts. Third, the proposed RRCRank has been compared with several state-of-the-art methods in CASP11 and CASP12. The results show that the RRCRank could achieve comparable prediction precisions and is better than three methods in most assessment metrics.ConclusionsThe learning-to-rank algorithm is introduced to develop a novel rank-based method for the residue-residue contact prediction of proteins, which achieves state-of-the-art performance based on the extensive assessment.

Dataset Information

RDb2C2: an improved method to identify the residue-residue pairing in ? strands.

Publications

RDb<sub>2</sub>C2: an improved method to identify the residue-residue pairing in β strands.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure