Accurate prediction of protein structural classes using functional domains and predicted secondary structure sequences

Protein structural class prediction is one of the challenging problems in bioinformatics. Previous methods directly based on the similarity of amino acid (AA) sequences have been shown to be insufficient for low-similarity protein data-sets. To improve the prediction accuracy for such low-similarity proteins, different methods have been recently proposed that explore the novel feature sets based on predicted secondary structure propensities. In this paper, we focus on protein structural class prediction using combinations of the novel features including secondary structure propensities as well as functional domain (FD) features extracted from the InterPro signature database. Our comprehensive experimental results based on several benchmark data-sets have shown that the integration of new FD features substantially improves the accuracy of structural class prediction for low-similarity proteins as they capture meaningful relationships among AA residues that are far away in protein sequence. The proposed prediction method has also been tested to predict structural classes for partially disordered proteins with the reasonable prediction accuracy, which is a more difficult problem comparing to structural class prediction for commonly used benchmark data-sets and has never been done before to the best of our knowledge. In addition, to avoid overfitting with a large number of features, feature selection is applied to select discriminating features that contribute to achieve high prediction accuracy. The selected features have been shown to achieve stable prediction performance across different benchmark data-sets.     

Using principal component analysis and support vector machine to predict protein structural class for low-similarity sequences via PSSM

The accurate identification of protein structure class solely using extracted information from protein sequence is a complicated task in the current computational biology. Prediction of protein structural class for low-similarity sequences remains a challenging problem. In this study, the new computational method has been developed to predict protein structural class by fusing the sequence information and evolution information to represent a protein sample. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark data-sets, 1189 and 25PDB with sequence similarity lower than 40 and 25%, respectively. Comparison of our results with other methods shows that the proposed method by us is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity data-sets.     

Using principal component analysis and support vector machine to predict protein structural class for low-similarity sequences via PSSM

The accurate identification of protein structure class solely using extracted information from protein sequence is a complicated task in the current computational biology. Prediction of protein structural class for low-similarity sequences remains a challenging problem. In this study, the new computational method has been developed to predict protein structural class by fusing the sequence information and evolution information to represent a protein sample. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark data-sets, 1189 and 25PDB with sequence similarity lower than 40 and 25%, respectively. Comparison of our results with other methods shows that the proposed method by us is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity data-sets.     

High-accuracy prediction of protein structural class for low-similarity sequences based on predicted secondary structure

Information on the structural classes of proteins has been proven to be important in many fields of bioinformatics. Prediction of protein structural class for low-similarity sequences is a challenge problem. In this study, 11 features (including 8 re-used features and 3 newly-designed features) are rationally utilized to reflect the general contents and spatial arrangements of the secondary structural elements of a given protein sequence. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets, 1189 and 25PDB with sequence similarity lower than 40% and 25%, respectively. Comparison of our results with other methods shows that our proposed method is very promising and may provide a cost-effective alternative to predict protein structural class in particular for low-similarity datasets.     

Prediction of protein structural class for low-similarity sequences using support vector machine and PSI-BLAST profile

Knowledge of structural class plays an important role in understanding protein folding patterns. In this study, a simple and powerful computational method, which combines support vector machine with PSI-BLAST profile, is proposed to predict protein structural class for low-similarity sequences. The evolution information encoding in the PSI-BLAST profiles is converted into a series of fixed-length feature vectors by extracting amino acid composition and dipeptide composition from the profiles. The resulting vectors are then fed to a support vector machine classifier for the prediction of protein structural class. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets, 1189 (containing 1092 proteins) and 25PDB (containing 1673 proteins) with sequence similarity lower than 40% and 25%, respectively. The overall accuracies attain 70.7% and 72.9% for 1189 and 25PDB datasets, respectively. Comparison of our results with other methods shows that our method is very promising to predict protein structural class particularly for low-similarity datasets and may at least play an important complementary role to existing methods.     

The prediction of protein structural class using averaged chemical shifts

Knowledge of protein structural class can provide important information about its folding patterns. Many approaches have been developed for the prediction of protein structural classes. However, the information used by these approaches is primarily based on amino acid sequences. In this study, a novel method is presented to predict protein structural classes by use of chemical shift (CS) information derived from nuclear magnetic resonance spectra. Firstly, 399 non-homologue (about 15% identity) proteins were constructed to investigate the distribution of averaged CS values of six nuclei ((13)CO, (13)Cα, (13)Cβ, (1)HN, (1)Hα and (15)N) in three protein structural classes. Subsequently, support vector machine was proposed to predict three protein structural classes by using averaged CS information of six nuclei. Overall accuracy of jackknife cross-validation achieves 87.0%. Finally, the feature selection technique is applied to exclude redundant information and find out an optimized feature set. Results show that the overall accuracy increased to 88.0% by using the averaged CSs of (13)CO, (1)Hα and (15)N. The proposed approach outperformed other state-of-the-art methods in terms of predictive accuracy in particular for low-similarity protein data. We expect that our proposed approach will be an excellent alternative to traditional methods for protein structural class prediction.     

Amino acid propensities for secondary structures are influenced by the protein structural class

Amino acid propensities for secondary structures were used since the 1970s, when Chou and Fasman evaluated them within datasets of few tens of proteins and developed a method to predict secondary structure of proteins, still in use despite prediction methods having evolved to very different approaches and higher reliability. Propensity for secondary structures represents an intrinsic property of amino acid, and it is used for generating new algorithms and prediction methods, therefore our work has been aimed to investigate what is the best protein dataset to evaluate the amino acid propensities, either larger but not homogeneous or smaller but homogeneous sets, i.e., all-alpha, all-beta, alpha-beta proteins. As a first analysis, we evaluated amino acid propensities for helix, beta-strand, and coil in more than 2000 proteins from the PDBselect dataset. With these propensities, secondary structure predictions performed with a method very similar to that of Chou and Fasman gave us results better than the original one, based on propensities derived from the few tens of X-ray protein structures available in the 1970s. In a refined analysis, we subdivided the PDBselect dataset of proteins in three secondary structural classes, i.e., all-alpha, all-beta, and alpha-beta proteins. For each class, the amino acid propensities for helix, beta-strand, and coil have been calculated and used to predict secondary structure elements for proteins belonging to the same class by using resubstitution and jackknife tests. This second round of predictions further improved the results of the first round. Therefore, amino acid propensities for secondary structures became more reliable depending on the degree of homogeneity of the protein dataset used to evaluate them. Indeed, our results indicate also that all algorithms using propensities for secondary structure can be still improved to obtain better predictive results.     

SVM-based method for protein structural class prediction using secondary structural content and structural information of amino acids

The knowledge collated from the known protein structures has revealed that the proteins are usually folded into the four structural classes: all-α, all-β, α/β and α + β. A number of methods have been proposed to predict the protein's structural class from its primary structure; however, it has been observed that these methods fail or perform poorly in the cases of distantly related sequences. In this paper, we propose a new method for protein structural class prediction using low homology (twilight-zone) protein sequences dataset. Since protein structural class prediction is a typical classification problem, we have developed a Support Vector Machine (SVM)-based method for protein structural class prediction that uses features derived from the predicted secondary structure and predicted burial information of amino acid residues. The examination of different individual as well as feature combinations revealed that the combination of secondary structural content, secondary structural and solvent accessibility state frequencies of amino acids gave rise to the best leave-one-out cross-validation accuracy of ~81% which is comparable to the best accuracy reported in the literature so far.     

NetSurfP-2.0: Improved prediction of protein structural features by integrated deep learning

The ability to predict local structural features of a protein from the primary sequence is of paramount importance for unraveling its function in absence of experimental structural information. Two main factors affect the utility of potential prediction tools: their accuracy must enable extraction of reliable structural information on the proteins of interest, and their runtime must be low to keep pace with sequencing data being generated at a constantly increasing speed. Here, we present NetSurfP-2.0, a novel tool that can predict the most important local structural features with unprecedented accuracy and runtime. NetSurfP-2.0 is sequence-based and uses an architecture composed of convolutional and long short-term memory neural networks trained on solved protein structures. Using a single integrated model, NetSurfP-2.0 predicts solvent accessibility, secondary structure, structural disorder, and backbone dihedral angles for each residue of the input sequences. We assessed the accuracy of NetSurfP-2.0 on several independent test datasets and found it to consistently produce state-of-the-art predictions for each of its output features. We observe a correlation of 80% between predictions and experimental data for solvent accessibility, and a precision of 85% on secondary structure 3-class predictions. In addition to improved accuracy, the processing time has been optimized to allow predicting more than 1000 proteins in less than 2 hours, and complete proteomes in less than 1 day.     

Predicting DNA-binding sites of proteins based on sequential and 3D structural information

Protein–DNA interactions play important roles in many biological processes. To understand the molecular mechanisms of protein–DNA interaction, it is necessary to identify the DNA-binding sites in DNA-binding proteins. In the last decade, computational approaches have been developed to predict protein–DNA-binding sites based solely on protein sequences. In this study, we developed a novel predictor based on support vector machine algorithm coupled with the maximum relevance minimum redundancy method followed by incremental feature selection. We incorporated not only features of physicochemical/biochemical properties, sequence conservation, residual disorder, secondary structure, solvent accessibility, but also five three-dimensional (3D) structural features calculated from PDB data to predict the protein–DNA interaction sites. Feature analysis showed that 3D structural features indeed contributed to the prediction of DNA-binding site and it was demonstrated that the prediction performance was better with 3D structural features than without them. It was also shown via analysis of features from each site that the features of DNA-binding site itself contribute the most to the prediction. Our prediction method may become a useful tool for identifying the DNA-binding sites and the feature analysis described in this paper may provide useful insights for in-depth investigations into the mechanisms of protein–DNA interaction.     

SPSSM8: An accurate approach for predicting eight-state secondary structures of proteins

Protein eight-state secondary structure prediction is challenging, but is necessary to determine protein structure and function. Here, we report the development of a novel approach, SPSSM8, to predict eight-state secondary structures of proteins accurately from sequences based on the structural position-specific scoring matrix (SPSSM). The SPSSM has been successfully utilized to predict three-state secondary structures. Now we employ an eight-state SPSSM as a feature that is obtained from sequence structure alignment against a large database of 9 million sequences with putative structural information. The SPSSM8 uses a low sequence identity dataset (9062 entries) as a training set and conditional random field for the classification algorithm. The SPSSM8 achieved an average eight-state secondary structure accuracy (Q8) of 71.7% (Q3, 81.6%) for an independent testing set (463 entries), which had an improved accuracy of 10.1% and 4.6% compared with SSPro8 and CNF, respectively, and significantly improved the accuracy of eight-state secondary structure prediction. For CASP 9 dataset (92 entries) the SPSSM8 achieved a Q8 accuracy of 80.1% (Q3, 83.0%). The SPSSM8 was confirmed as an outstanding predictor for eight-state secondary structures of proteins. SPSSM8 is freely available at http://cal.tongji.edu.cn/SPSSM8.     

Distinguishing enzyme structures from non-enzymes without alignments

The ability to predict protein function from structure is becoming increasingly important as the number of structures resolved is growing more rapidly than our capacity to study function. Current methods for predicting protein function are mostly reliant on identifying a similar protein of known function. For proteins that are highly dissimilar or are only similar to proteins also lacking functional annotations, these methods fail. Here, we show that protein function can be predicted as enzymatic or not without resorting to alignments. We describe 1178 high-resolution proteins in a structurally non-redundant subset of the Protein Data Bank using simple features such as secondary-structure content, amino acid propensities, surface properties and ligands. The subset is split into two functional groupings, enzymes and non-enzymes. We use the support vector machine-learning algorithm to develop models that are capable of assigning the protein class. Validation of the method shows that the function can be predicted to an accuracy of 77% using 52 features to describe each protein. An adaptive search of possible subsets of features produces a simplified model based on 36 features that predicts at an accuracy of 80%. We compare the method to sequence-based methods that also avoid calculating alignments and predict a recently released set of unrelated proteins. The most useful features for distinguishing enzymes from non-enzymes are secondary-structure content, amino acid frequencies, number of disulphide bonds and size of the largest cleft. This method is applicable to any structure as it does not require the identification of sequence or structural similarity to a protein of known function.     

On predicting foldability of a protein from its sequence

Several properties of amino acid sequences corresponding to proteins that are known to fold are compared to those of randomly generated sequences and to sequences of intrinsically disordered proteins in order to find properties that distinguish folding sequences from the rest. The properties studied included helix and sheet propensities from secondary structure prediction, adjacency correlations, directionality correlations, as well as propensities of all possible triplets and quadruplets. Small differences between known folded and random sequences were observed for the adjacency and directional correlations, and significant differences were seen on the triplet and especially on the quadruplet propensities. Based on the differences in the adjacency, triplet or quadruplet propensities folding scores were defined and used to test the accuracy of foldability prediction based on these statistics. The best predictions were obtained from the quadruplet propensities.     

Neural networks for secondary structure and structural class predictions

A pair of neural network-based algorithms is presented for predicting the tertiary structural class and the secondary structure of proteins. Each algorithm realizes improvements in accuracy based on information provided by the other. Structural class prediction of proteins nonhomologous to any in the training set is improved significantly, from 62.3% to 73.9%, and secondary structure prediction accuracy improves slightly, from 62.26% to 62.64%. A number of aspects of neural network optimization and testing are examined. They include network overtraining and an output filter based on a rolling average. Secondary structure prediction results vary greatly depending on the particular proteins chosen for the training and test sets; consequently, an appropriate measure of accuracy reflects the more unbiased approach of “jackknife” cross-validation (testing each protein in the database individually).     

Machine learning approaches for prediction of linear B-cell epitopes on proteins

Identification and characterization of antigenic determinants on proteins has received considerable attention utilizing both, experimental as well as computational methods. For computational routines mostly structural as well as physicochemical parameters have been utilized for predicting the antigenic propensity of protein sites. However, the performance of computational routines has been low when compared to experimental alternatives. Here we describe the construction of machine learning based classifiers to enhance the prediction quality for identifying linear B-cell epitopes on proteins. Our approach combines several parameters previously associated with antigenicity, and includes novel parameters based on frequencies of amino acids and amino acid neighborhood propensities. We utilized machine learning algorithms for deriving antigenicity classification functions assigning antigenic propensities to each amino acid of a given protein sequence. We compared the prediction quality of the novel classifiers with respect to established routines for epitope scoring, and tested prediction accuracy on experimental data available for HIV proteins. The major finding is that machine learning classifiers clearly outperform the reference classification systems on the HIV epitope validation set.     

Classifier ensembles for protein structural class prediction with varying homology

Structural class characterizes the overall folding type of a protein or its domain. A number of computational methods have been proposed to predict structural class based on primary sequences; however, the accuracy of these methods is strongly affected by sequence homology. This paper proposes, an ensemble classification method and a compact feature-based sequence representation. This method improves prediction accuracy for the four main structural classes compared to competing methods, and provides highly accurate predictions for sequences of widely varying homologies. The experimental evaluation of the proposed method shows superior results across sequences that are characterized by entire homology spectrum, ranging from 25% to 90% homology. The error rates were reduced by over 20% when compared with using individual prediction methods and most commonly used composition vector representation of protein sequences. Comparisons with competing methods on three large benchmark datasets consistently show the superiority of the proposed method.     

Learning protein multi-view features in complex space

Protein attribute prediction from primary sequences is an important task and how to extract discriminative features is one of the most crucial aspects. Because single-view feature cannot reflect all the information of a protein, fusing multi-view features is considered as a promising route to improve prediction accuracy. In this paper, we propose a novel framework for protein multi-view feature fusion: first, features from different views are parallely combined to form complex feature vectors; Then, we extend the classic principal component analysis to the generalized principle component analysis for further feature extraction from the parallely combined complex features, which lie in a complex space. Finally, the extracted features are used for prediction. Experimental results on different benchmark datasets and machine learning algorithms demonstrate that parallel strategy outperforms the traditional serial approach and is particularly helpful for extracting the core information buried among multi-view feature sets. A web server for protein structural class prediction based on the proposed method (COMSPA) is freely available for academic use at: http://www.csbio.sjtu.edu.cn/bioinf/COMSPA/.     

Sampling Bottlenecks in De novo Protein Structure Prediction

The primary obstacle to de novo protein structure prediction is conformational sampling: the native state generally has lower free energy than nonnative structures but is exceedingly difficult to locate. Structure predictions with atomic level accuracy have been made for small proteins using the Rosetta structure prediction method, but for larger and more complex proteins, the native state is virtually never sampled, and it has been unclear how much of an increase in computing power would be required to successfully predict the structures of such proteins. In this paper, we develop an approach to determining how much computer power is required to accurately predict the structure of a protein, based on a reformulation of the conformational search problem as a combinatorial sampling problem in a discrete feature space. We find that conformational sampling for many proteins is limited by critical “linchpin” features, often the backbone torsion angles of individual residues, which are sampled very rarely in unbiased trajectories and, when constrained, dramatically increase the sampling of the native state. These critical features frequently occur in less regular and likely strained regions of proteins that contribute to protein function. In a number of proteins, the linchpin features are in regions found experimentally to form late in folding, suggesting a correspondence between folding in silico and in reality.     

Environmental features are important in determining protein secondary structure

We have investigated amino acid features that determine secondary structure: (1) the solvent accessibility of each side chain, and (2) the interaction of each side chain with others one to four residues apart. Solvent accessibility is a simple model that distinguishes residue environment. The pairwise interactions represent a simple model of local side chain to side chain interactions. To test the importance of these features we developed an algorithm to separate alpha-helices, beta-strands, and "other" structure. Single residue and pairwise probabilities were determined for 25,141 samples from proteins with <30% homology. Combining the features of solvent accessibility with pairwise probabilities allows us to distinguish the three structures after cross validation at the 82.0% level. We gain 1.4% to 2.0% accuracy by optimizing the propensities, demonstrating that probabilities do not necessarily reflect propensities. Optimization of residue exposures, weights of all probabilities, and propensities increased accuracy to 84.0%.