Fold recognition by scoring protein maps using the congruence coefficient.
Ontology highlight
ABSTRACT: Motivation
Protein fold recognition is a key step for template-based modeling approaches to protein structure prediction. Although closely related folds can be easily identified by sequence homology search in sequence databases, fold recognition is notoriously more difficult when it involves the identification of distantly related homologs. Recent progress in residue-residue contact and distance prediction opens up the possibility of improving fold recognition by using structural information contained in predicted distance and contact maps.Results
Here we propose to use the congruence coefficient as a metric of similarity between maps. We prove that this metric has several interesting mathematical properties which allow one to compute in polynomial time its exact mean and variance over all possible (exponentially many) alignments between two symmetric matrices, and assess the statistical significance of similarity between aligned maps. We perform fold recognition tests by recovering predicted target contact/distance maps from the two most recent Critical Assessment of Structure Prediction editions and over 27 000 non-homologous structural templates from the ECOD database. On this large benchmark, we compare fold recognition performances of different alignment tools with their own similarity scores against those obtained using the congruence coefficient. We show that the congruence coefficient overall improves fold recognition over other methods, proving its effectiveness as a general similarity metric for protein map comparison.Availability and implementation
The congruence coefficient software CCpro is available as part of the SCRATCH suite at: http://scratch.proteomics.ics.uci.edu/.Supplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Di Lena P
PROVIDER: S-EPMC8088323 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:MotivationVarious approaches based on features extracted from protein sequences and often machine learning methods have been used in the prediction of protein folds. Finding an efficient technique for integrating these different protein features has received increasing attention. In particular, kernel methods are an interesting class of techniques for integrating heterogeneous data. Various methods have been proposed to fuse multiple kernels. Most techniques for multiple kernel learning focus on learning a convex linear combination of base kernels. In addition to the limitation of linear combinations, working with such approaches could cause a loss of potentially useful information.ResultsWe design several techniques to combine kernel matrices by taking more involved, geometry inspired means of these matrices instead of convex linear combinations. We consider various sequence-based protein features including information extracted directly from position-specific scoring matrices and local sequence alignment. We evaluate our methods for classification on the SCOP PDB-40D benchmark dataset for protein fold recognition. The best overall accuracy on the protein fold recognition test set obtained by our methods is ∼ 86.7%. This is an improvement over the results of the best existing approach. Moreover, our computational model has been developed by incorporating the functional domain composition of proteins through a hybridization model. It is observed that by using our proposed hybridization model, the protein fold recognition accuracy is further improved to 89.30%. Furthermore, we investigate the performance of our approach on the protein remote homology detection problem by fusing multiple string kernels.Availability and implementationThe MATLAB code used for our proposed geometric kernel fusion frameworks are publicly available at http://people.cs.kuleuven.be/∼raf.vandebril/homepage/software/geomean.php?menu=5/.
| S-EPMC4071197 | biostudies-literature
Project description:MotivationOwing to the size and complexity of large multi-component biological assemblies, the most tractable approach to determining their atomic structure is often to fit high-resolution radiographic or nuclear magnetic resonance structures of isolated components into lower resolution electron density maps of the larger assembly obtained using cryo-electron microscopy (cryo-EM). This hybrid approach to structure determination requires that an atomic resolution structure of each component, or a suitable homolog, is available. If neither is available, then the amount of structural information regarding that component is limited by the resolution of the cryo-EM map. However, even if a suitable homolog cannot be identified using sequence analysis, a search for structural homologs should still be performed because structural homology often persists throughout evolution even when sequence homology is undetectable, As macromolecules can often be described as a collection of independently folded domains, one way of searching for structural homologs would be to systematically fit representative domain structures from a protein domain database into the medium/low resolution cryo-EM map and return the best fits. Taken together, the best fitting non-overlapping structures would constitute a 'mosaic' backbone model of the assembly that could aid map interpretation and illuminate biological function.ResultUsing the computational principles of the Scale-Invariant Feature Transform (SIFT), we have developed FOLD-EM-a computational tool that can identify folded macromolecular domains in medium to low resolution (4-15 Å) electron density maps and return a model of the constituent polypeptides in a fully automated fashion. As a by-product, FOLD-EM can also do flexible multi-domain fitting that may provide insight into conformational changes that occur in macromolecular assemblies.
| S-EPMC3519459 | biostudies-literature
Project description:BackgroundSequence matching is extremely important for applications throughout biology, particularly for discovering information such as functional and evolutionary relationships, and also for discriminating between unimportant and disease mutants. At present the functions of a large fraction of genes are unknown; improvements in sequence matching will improve gene annotations. Universal amino acid substitution matrices such as Blosum62 are used to measure sequence similarities and to identify distant homologues, regardless of the structure class. However, such single matrices do not take into account important structural information evident within the different topologies of proteins and treats substitutions within all protein folds identically. Others have suggested that the use of structural information can lead to significant improvements in sequence matching but this has not yet been very effective. Here we develop novel substitution matrices that include not only general sequence information but also have a topology specific component that is unique for each CATH topology. This novel feature of using a combination of sequence and structure information for each protein topology significantly improves the sequence matching scores for the sequence pairs tested. We have used a novel multi-structure alignment method for each homology level of CATH in order to extract topological information.ResultsWe obtain statistically significant improved sequence matching scores for 73 % of the alpha helical test cases. On average, 61 % of the test cases showed improvements in homology detection when structure information was incorporated into the substitution matrices. On average z-scores for homology detection are improved by more than 54 % for all cases, and some individual cases have z-scores more than twice those obtained using generic matrices. Our topology specific similarity matrices also outperform other traditional similarity matrices and single matrix based structure methods. When default amino acid substitution matrix in the Psi-blast algorithm is replaced by our structure-based matrices, the structure matching is significantly improved over conventional Psi-blast. It also outperforms results obtained for the corresponding HMM profiles generated for each topology.ConclusionsWe show that by incorporating topology-specific structure information in addition to sequence information into specific amino acid substitution matrices, the sequence matching scores and homology detection are significantly improved. Our topology specific similarity matrices outperform other traditional similarity matrices, single matrix based structure methods, also show improvement over conventional Psi-blast and HMM profile based methods in sequence matching. The results support the discriminatory ability of the new amino acid similarity matrices to distinguish between distant homologs and structurally dissimilar pairs.
| S-EPMC5006591 | biostudies-literature
Project description:NMR offers the possibility of accurate secondary structure for proteins that would be too large for structure determination. In the absence of an X-ray crystal structure, this information should be useful as an adjunct to protein fold recognition methods based on low resolution force fields. The value of this information has been tested by adding varying amounts of artificial secondary structure data and threading a sequence through a library of candidate folds. Using a literature test set, the threading method alone has only a one-third chance of producing a correct answer among the top ten guesses. With realistic secondary structure information, one can expect a 60-80% chance of finding a homologous structure. The method has then been applied to examples with published estimates of secondary structure. This implementation is completely independent of sequence homology, and sequences are optimally aligned to candidate structures with gaps and insertions allowed. Unlike work using predicted secondary structure, we test the effect of differing amounts of relatively reliable data.
| S-EPMC2144327 | biostudies-other
Project description:Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer's representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue-residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/.
| S-EPMC8768454 | biostudies-literature
Project description:Optical coherence tomography (OCT) has shown potential in differentiating normal colonic mucosa from neoplasia. In this study of 33 fresh human colon specimens, we report the first use of texture features and computer vision-based imaging features acquired from en face scattering coefficient maps to characterize colorectal tissue. En face scattering coefficient maps were generated automatically using a new fast integral imaging algorithm. From these maps, a gray-level cooccurrence matrix algorithm was used to extract texture features, and a scale-invariant feature transform algorithm was used to derive novel computer vision-based features. In total, 25 features were obtained, and the importance of each feature in diagnosis was evaluated using a random forest model. Two classifiers were assessed on two different classification tasks. A support vector machine model was found to be optimal for distinguishing normal from abnormal tissue, with 94.7% sensitivity and 94.0% specificity, while a random forest model performed optimally in further differentiating abnormal tissues (i.e., cancerous tissue and adenomatous polyp) with 86.9% sensitivity and 85.0% specificity. These results demonstrated the potential of using OCT to aid the diagnosis of human colorectal disease.
| S-EPMC8196414 | biostudies-literature
Project description:BACKGROUND:Contradicting evidence has been presented in the literature concerning the effectiveness of empirical contact energies for fold recognition. Empirical contact energies are calculated on the basis of information available from selected protein structures, with respect to a defined reference state, according to the quasi-chemical approximation. Protein-solvent interactions are estimated from residue solvent accessibility. RESULTS:In the approach presented here, contact energies are derived from the potential of mean force theory, several definitions of contact are examined and their performance in fold recognition is evaluated on sets of decoy structures. The best definition of contact is tested, on a more realistic scenario, on all predictions including sidechains accepted in the CASP4 experiment. In 30 out of 35 cases the native structure is correctly recognized and best predictions are usually found among the 10 lowest energy predictions. CONCLUSION:The definition of contact based on van der Waals radii of alpha carbon and side chain heavy atoms is seen to perform better than other definitions involving only alpha carbons, only beta carbons, all heavy atoms or only backbone atoms. An important prerequisite for the applicability of the approach is that the protein structure under study should not exhibit anomalous solvent accessibility, compared to soluble proteins whose structure is deposited in the Protein Data Bank. The combined evaluation of a solvent accessibility parameter and contact energy allows for an effective gross screening of predictive models.
| S-EPMC153506 | biostudies-literature
Project description:For accurate recognition of protein folds, a deep learning network method (DN-Fold) was developed to predict if a given query-template protein pair belongs to the same structural fold. The input used stemmed from the protein sequence and structural features extracted from the protein pair. We evaluated the performance of DN-Fold along with 18 different methods on Lindahl's benchmark dataset and on a large benchmark set extracted from SCOP 1.75 consisting of about one million protein pairs, at three different levels of fold recognition (i.e., protein family, superfamily, and fold) depending on the evolutionary distance between protein sequences. The correct recognition rate of ensembled DN-Fold for Top 1 predictions is 84.5%, 61.5%, and 33.6% and for Top 5 is 91.2%, 76.5%, and 60.7% at family, superfamily, and fold levels, respectively. We also evaluated the performance of single DN-Fold (DN-FoldS), which showed the comparable results at the level of family and superfamily, compared to ensemble DN-Fold. Finally, we extended the binary classification problem of fold recognition to real-value regression task, which also show a promising performance. DN-Fold is freely available through a web server at http://iris.rnet.missouri.edu/dnfold.
| S-EPMC4669437 | biostudies-literature
Project description:BackgroundCurrent state-of-the-art deep learning approaches for protein fold recognition learn protein embeddings that improve prediction performance at the fold level. However, there still exists aperformance gap at the fold level and the (relatively easier) family level, suggesting that it might be possible to learn an embedding space that better represents the protein folds.ResultsIn this paper, we propose the FoldHSphere method to learn a better fold embedding space through a two-stage training procedure. We first obtain prototype vectors for each fold class that are maximally separated in hyperspherical space. We then train a neural network by minimizing the angular large margin cosine loss to learn protein embeddings clustered around the corresponding hyperspherical fold prototypes. Our network architectures, ResCNN-GRU and ResCNN-BGRU, process the input protein sequences by applying several residual-convolutional blocks followed by a gated recurrent unit-based recurrent layer. Evaluation results on the LINDAHL dataset indicate that the use of our hyperspherical embeddings effectively bridges the performance gap at the family and fold levels. Furthermore, our FoldHSpherePro ensemble method yields an accuracy of 81.3% at the fold level, outperforming all the state-of-the-art methods.ConclusionsOur methodology is efficient in learning discriminative and fold-representative embeddings for the protein domains. The proposed hyperspherical embeddings are effective at identifying the protein fold class by pairwise comparison, even when amino acid sequence similarities are low.
| S-EPMC8507389 | biostudies-literature
Project description:Protein structure prediction based on comparative modeling is the most efficient way to produce structural models when it can be performed. ORION is a dedicated webserver based on a new strategy that performs this task. The identification by ORION of suitable templates is performed using an original profile-profile approach that combines sequence and structure evolution information. Structure evolution information is encoded into profiles using structural features, such as solvent accessibility and local conformation -with Protein Blocks-, which give an accurate description of the local protein structure. ORION has recently been improved, increasing by 5% the quality of its results. The ORION web server accepts a single protein sequence as input and searches homologous protein structures within minutes. Various databases such as PDB, SCOP and HOMSTRAD can be mined to find an appropriate structural template. For the modeling step, a protein 3D structure can be directly obtained from the selected template by MODELLER and displayed with global and local quality model estimation measures. The sequence and the predicted structure of 4 examples from the CAMEO server and a recent CASP11 target from the 'Hard' category (T0818-D1) are shown as pertinent examples. Our web server is accessible at http://www.dsimb.inserm.fr/ORION/.
| S-EPMC4913311 | biostudies-literature