Fold Recognition Accuracy Research Articles

Structural protein fold recognition based on secondary structure and evolutionary information using machine learning algorithms

Understanding the function of protein is conducive to research in advanced fields such as gene therapy of diseases, the development and design of new drugs, etc. The prerequisite for understanding the function of a protein is to determine its tertiary structure. The realization of protein structure classification is indispensable for this problem and fold recognition is a commonly used method of protein structure classification. Protein sequences of 40% identity in the ASTRAL protein classification database are used for fold recognition research in current work to predict 27 folding types which mostly belong to four protein structural classes: α, β, α/β and α + β. We extract features from primary structure of protein using methods covering DSSP, PSSM and HMM which are based on secondary structure and evolutionary information to convert protein sequences into feature vectors that can be recognized by machine learning algorithm and utilize the combination of LightGBM feature selection algorithm and incremental feature selection method (IFS) to find the optimal classifiers respectively constructed by machine learning algorithms on the basis of tree structure including Random Forest, XGBoost and LightGBM. Bayesian optimization method is used for hyper-parameter adjustment of machine learning algorithms to make the accuracy of fold recognition reach as high as 93.45% at last. The result obtained by the model we propose is outstanding in the study of protein fold recognition.

An Enhanced Protein Fold Recognition for Low Similarity Datasets Using Convolutional and Skip-Gram Features With Deep Neural Network.

The protein fold recognition is one of the important tasks of structural biology, which helps in addressing further challenges like predicting the protein tertiary structures and its functions. Many machine learning works are published to identify the protein folds effectively. However, very few works have reported the fold recognition accuracy above 80% on benchmark datasets. In this study, an effective set of global and local features are extracted from the proposed Convolutional (Conv) and SkipXGram bi-gram (SXGbg) techniques, and the fold recognition is performed using the proposed deep neural network. The performance of the proposed model reported 91.4% fold accuracy on one of the derived low similarity (< 25%) datasets of latest extended version of SCOPe_2.07. The proposed model is further evaluated on three popular and publicly available benchmark datasets such as DD, EDD, and TG and obtained 85.9%, 95.8%, and 88.8% fold accuracies, respectively. This work is first to report fold recognition accuracy above 85% on all the benchmark datasets. The performance of the proposed model has outperformed the best state-of-the-art models by 5% to 23% on DD, 2% to 19% on EDD, and 3% to 30% on TG dataset.

DeepSF: deep convolutional neural network for mapping protein sequences to folds.

MotivationProtein fold recognition is an important problem in structural bioinformatics. Almost all traditional fold recognition methods use sequence (homology) comparison to indirectly predict the fold of a target protein based on the fold of a template protein with known structure, which cannot explain the relationship between sequence and fold. Only a few methods had been developed to classify protein sequences into a small number of folds due to methodological limitations, which are not generally useful in practice.ResultsWe develop a deep 1D-convolution neural network (DeepSF) to directly classify any protein sequence into one of 1195 known folds, which is useful for both fold recognition and the study of sequence–structure relationship. Different from traditional sequence alignment (comparison) based methods, our method automatically extracts fold-related features from a protein sequence of any length and maps it to the fold space. We train and test our method on the datasets curated from SCOP1.75, yielding an average classification accuracy of 75.3%. On the independent testing dataset curated from SCOP2.06, the classification accuracy is 73.0%. We compare our method with a top profile–profile alignment method—HHSearch on hard template-based and template-free modeling targets of CASP9-12 in terms of fold recognition accuracy. The accuracy of our method is 12.63–26.32% higher than HHSearch on template-free modeling targets and 3.39–17.09% higher on hard template-based modeling targets for top 1, 5 and 10 predicted folds. The hidden features extracted from sequence by our method is robust against sequence mutation, insertion, deletion and truncation, and can be used for other protein pattern recognition problems such as protein clustering, comparison and ranking.Availability and implementationThe DeepSF server is publicly available at: http://iris.rnet.missouri.edu/DeepSF/.Supplementary information Supplementary data are available at Bioinformatics online.

Effective inter-residue contact definitions for accurate protein fold recognition

BackgroundEffective encoding of residue contact information is crucial for protein structure prediction since it has a unique role to capture long-range residue interactions compared to other commonly used scoring terms. The residue contact information can be incorporated in structure prediction in several different ways: It can be incorporated as statistical potentials or it can be also used as constraints in ab initio structure prediction. To seek the most effective definition of residue contacts for template-based protein structure prediction, we evaluated 45 different contact definitions, varying bases of contacts and distance cutoffs, in terms of their ability to identify proteins of the same fold.ResultsWe found that overall the residue contact pattern can distinguish protein folds best when contacts are defined for residue pairs whose Cβ atoms are at 7.0 Å or closer to each other. Lower fold recognition accuracy was observed when inaccurate threading alignments were used to identify common residue contacts between protein pairs. In the case of threading, alignment accuracy strongly influences the fraction of common contacts identified among proteins of the same fold, which eventually affects the fold recognition accuracy. The largest deterioration of the fold recognition was observed for β-class proteins when the threading methods were used because the average alignment accuracy was worst for this fold class. When results of fold recognition were examined for individual proteins, we found that the effective contact definition depends on the fold of the proteins. A larger distance cutoff is often advantageous for capturing spatial arrangement of the secondary structures which are not physically in contact. For capturing contacts between neighboring β strands, considering the distance between Cα atoms is better than the Cβ−based distance because the side-chain of interacting residues on β strands sometimes point to opposite directions.ConclusionResidue contacts defined by Cβ−Cβ distance of 7.0 Å work best overall among tested to identify proteins of the same fold. We also found that effective contact definitions differ from fold to fold, suggesting that using different residue contact definition specific for each template will lead to improvement of the performance of threading.

Improving the protein fold recognition accuracy of a reduced state-space hidden Markov model

Fold recognition is a challenging field strongly associated with protein function determination, which is crucial for biologists and the pharmaceutical industry. Hidden Markov models (HMMs) have been widely used for this purpose. In this paper we demonstrate how the fold recognition performance of a recently introduced HMM with a reduced state-space topology can be improved. Our method employs an efficient architecture and a low complexity training algorithm based on likelihood maximization. The fold recognition performance of the model is further improved in two steps. In the first step we use a smaller model architecture based on the {E,H,L} alphabet instead of the DSSP secondary structure alphabet. In the second step secondary structure information (predicted or true) is additionally used in scoring the test set sequences. The Protein Data Bank and the annotation of the SCOP database are used for the training and evaluation of the proposed methodology. The results show that the fold recognition accuracy is substantially improved in both steps. Specifically, it is increased by 2.9% in the first step to 22%. In the second step it further increases and reaches up to 30% when predicted secondary structure information is additionally used and it increases even more and reaches up to 34.7% when we use the true secondary structure. The major advantage of the proposed improvements is that the fold recognition performance is substantially increased while the size of the model and the computational complexity of scoring are decreased.

Real‐value prediction of backbone torsion angles

The backbone structure of a protein is largely determined by the phi and psi torsion angles. Thus, knowing these angles, even if approximately, will be very useful for protein-structure prediction. However, in a previous work, a sequence-based, real-value prediction of psi angle could only achieve a mean absolute error of 54 degrees (83 degrees, 35 degrees, 33 degrees for coil, strand, and helix residues, respectively) between predicted and actual angles. Moreover, a real-value prediction of phi angle is not yet available. This article employs a neural-network based approach to improve psi prediction by taking advantage of angle periodicity and apply the new method to the prediction to phi angles. The 10-fold-cross-validated mean absolute error for the new method is 38 degrees (58 degrees, 33 degrees, 22 degrees for coil, strand, and helix, respectively) for psi and 25 degrees (35 degrees, 22 degrees, 16 degrees for coil, strand, and helix, respectively) for phi. The accuracy of real-value prediction is comparable to or more accurate than the predictions based on multistate classification of the phi-psi map. More accurate prediction of real-value angles will likely be useful for improving the accuracy of fold recognition and ab initio protein-structure prediction. The Real-SPINE 2.0 server is available on the website http://sparks.informatics.iupui.edu.

Fold recognition by concurrent use of solvent accessibility and residue depth

Recognizing the structural similarity without significant sequence identity (called fold recognition) is the key for bridging the gap between the number of known protein sequences and the number of structures solved. Previously, we developed a fold-recognition method called SP(3) which combines sequence-derived sequence profiles, secondary-structure profiles and residue-depth dependent, structure-derived sequence profiles. The use of residue-depth-dependent profiles makes SP(3) one of the best automatic predictors in CASP 6. Because residue depth (RD) and solvent accessible surface area (solvent accessibility) are complementary in describing the exposure of a residue to solvent, we test whether or not incorporation of solvent-accessibility profiles into SP(3) could further increase the accuracy of fold recognition. The resulting method, called SP(4), was tested in SALIGN benchmark for alignment accuracy and Lindahl, LiveBench 8 and CASP7 blind prediction for fold recognition sensitivity and model-structure accuracy. For remote homologs, SP(4) is found to consistently improve over SP(3) in the accuracy of sequence alignment and predicted structural models as well as in the sensitivity of fold recognition. Our result suggests that RD and solvent accessibility can be used concurrently for improving the accuracy and sensitivity of fold recognition. The SP(4) server and its local usage package are available on http://sparks.informatics.iupui.edu/SP4.

Pairwise sequence alignment below the twilight zone

Improved sequence alignment at low pairwise identity is important for identifying potential remote homologues in database searches and for obtaining accurate alignments as a prelude to modeling structures by homology. Our work is motivated by two observations: structural data provide superior training examples for developing techniques to improve the alignment of remote homologues; and general substitution patterns for remote homologues differ from those of closely related proteins. We introduce a new set of amino acid residue interchange matrices built from structural superposition data. These matrices exploit known structural homology as a means of characterizing the effect evolution has on residue-substitution profiles. Given their origin, it is not surprising that the individual residue-residue interchange frequencies are chemically sensible.The structural interchange matrices show a significant increase both in pairwise alignment accuracy and in functional annotation/fold recognition accuracy across distantly related sequences. We demonstrate improved pairwise alignment by using superpositions of homologous domains extracted from a structural database as a gold standard and go on to show an increase in fold recognition accuracy using a database of homologous fold families. This was applied to the unassigned open reading frames from the genome of Helicobacter pylori to identify five matches, two of which are not represented by new annotations in the sequence databases. In addition, we describe a new cyclic permutation strategy to identify distant homologues that experienced gene duplication and subsequent deletions. Using this method, we have identified a potential homologue to one additional previously unassigned open reading frame from the H. pylori genome.

3D-1D threading methods for protein fold recognition.

The threading approach to protein fold recognition attempts to evaluate how well a query sequence fits into an already-solved fold. 3D-1D threaders rely on matching 1-dimensional strings of 3-dimensional information predicted from the query sequence with corresponding features of the target structure. In many cases this is combined with a sequence comparison. The combination of sequence and structure information has been shown to improve the accuracy of fold recognition, relative to the exclusive use of sequence or structure. In this paper, we review progress made since the introduction of threading methods a decade ago, highlighting recent advances. We focus on two emerging methods that are unconventional 3D-1D threaders: proximity correlation matrices and parallel cascade identification.