Improve Protein Secondary Structure Prediction Research Articles

Ensemble deep learning models for protein secondary structure prediction using bidirectional temporal convolution and bidirectional long short-term memory.

Protein secondary structure prediction (PSSP) is a challenging task in computational biology. However, existing models with deep architectures are not sufficient and comprehensive for deep long-range feature extraction of long sequences. This paper proposes a novel deep learning model to improve Protein secondary structure prediction. In the model, our proposed bidirectional temporal convolutional network (BTCN) can extract the bidirectional deep local dependencies in protein sequences segmented by the sliding window technique, the bidirectional long short-term memory (BLSTM) network can extract the global interactions between residues, and our proposed multi-scale bidirectional temporal convolutional network (MSBTCN) can further capture the bidirectional multi-scale long-range features of residues while preserving the hidden layer information more comprehensively. In particular, we also propose that fusing the features of 3-state and 8-state Protein secondary structure prediction can further improve the prediction accuracy. Moreover, we also propose and compare multiple novel deep models by combining bidirectional long short-term memory with temporal convolutional network (TCN), reverse temporal convolutional network (RTCN), multi-scale temporal convolutional network (multi-scale bidirectional temporal convolutional network), bidirectional temporal convolutional network and multi-scale bidirectional temporal convolutional network, respectively. Furthermore, we demonstrate that the reverse prediction of secondary structure outperforms the forward prediction, suggesting that amino acids at later positions have a greater impact on secondary structure recognition. Experimental results on benchmark datasets including CASP10, CASP11, CASP12, CASP13, CASP14, and CB513 show that our methods achieve better prediction performance compared to five state-of-the-art methods.

Improving protein secondary structure prediction: the evolutionary optimized classification algorithms

Determining protein structures plays an important role in the field of drug design. Currently, the machine learning methods including artificial neural network (ANN) and support vector machine (SVM) have replaced the experimental techniques to determine these structures. However, as these predictions are increasingly becoming the workhorse for numerous methods aimed at predicting protein structure and function, it still needs to be improved. In this study, evolutionary optimized neural network (EONN) and evolutionary optimized support vector machine (EOSVM) were applied to predict protein secondary structure using GA, DE, and PSO. Despite the simplicity of the applied methods, the results are found to be superior to those achieved through other techniques. The EONN and EOSVM modestly improved the accuracy by 6% and 5% on the same database, respectively.

Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction

Recently developed deep learning techniques have significantly improved the accuracy of various speech and image recognition systems. In this paper we show how to adapt some of these techniques to create a novel chained convolutional architecture with next-step conditioning for improving performance on protein sequence prediction problems. We explore its value by demonstrating its ability to improve performance on eight-class secondary structure prediction. We first establish a state-of-the-art baseline by adapting recent advances in convolutional neural networks which were developed for vision tasks. This model achieves 70.0% per amino acid accuracy on the CB513 benchmark dataset without use of standard performance-boosting techniques such as ensembling or multitask learning. We then improve upon this state-of-the-art result using a novel chained prediction approach which frames the secondary structure prediction as a next-step prediction problem. This sequential model achieves 70.3% Q8 accuracy on CB513 with a single model; an ensemble of these models produces 71.4% Q8 accuracy on the same test set, improving upon the previous overall state of the art for the eight-class secondary structure problem. Our models are implemented using TensorFlow, an open-source machine learning software library available at this http URL; we aim to release the code for these experiments as part of the TensorFlow repository.

SPINE X: improving protein secondary structure prediction by multistep learning coupled with prediction of solvent accessible surface area and backbone torsion angles.

Accurate prediction of protein secondary structure is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. The accuracy of ab initio secondary structure prediction from sequence, however, has only increased from around 77 to 80% over the past decade. Here, we developed a multistep neural-network algorithm by coupling secondary structure prediction with prediction of solvent accessibility and backbone torsion angles in an iterative manner. Our method called SPINE X was applied to a dataset of 2640 proteins (25% sequence identity cutoff) previously built for the first version of SPINE and achieved a 82.0% accuracy based on 10-fold cross validation (Q(3)). Surpassing 81% accuracy by SPINE X is further confirmed by employing an independently built test dataset of 1833 protein chains, a recently built dataset of 1975 proteins and 117 CASP 9 targets (critical assessment of structure prediction techniques) with an accuracy of 81.3%, 82.3% and 81.8%, respectively. The prediction accuracy is further improved to 83.8% for the dataset of 2640 proteins if the DSSP assignment used above is replaced by a more consistent consensus secondary structure assignment method. Comparison to the popular PSIPRED and CASP-winning structure-prediction techniques is made. SPINE X predicts number of helices and sheets correctly for 21.0% of 1833 proteins, compared to 17.6% by PSIPRED. It further shows that SPINE X consistently makes more accurate prediction in helical residues (6%) without over prediction while PSIPRED makes more accurate prediction in coil residues (3-5%) and over predicts them by 7%. SPINE X Server and its training/test datasets are available at http://sparks.informatics.iupui.edu/

Improving protein secondary structure prediction using a multi-modal BP method

Methods for predicting protein secondary structures provide information that is useful both in ab initio structure prediction and as additional restraints for fold recognition algorithms. Secondary structure predictions may also be used to guide the design of site directed mutagenesis studies, and to locate potential functionally important residues. In this article, we propose a multi-modal back propagation neural network (MMBP) method for predicting protein secondary structures. Using a Knowledge Discovery Theory based on Inner Cognitive Mechanism (KDTICM) method, we have constructed a compound pyramid model (CPM), which is composed of three layers of intelligent interface that integrate multi-modal back propagation neural network (MMBP), mixed-modal SVM (MMS), modified Knowledge Discovery in Databases (KDD ⁎) process and so on. The CPM method is both an integrated web server and a standalone application that exploits recent advancements in knowledge discovery and machine learning to perform very accurate protein secondary structure predictions. Using a non-redundant test dataset of 256 proteins from RCASP256, the CPM method achieves an average Q 3 score of 86.13% (SOV99=84.66%). Extensive testing indicates that this is significantly better than any other method currently available. Assessments using RS126 and CB513 datasets indicate that the CPM method can achieve average Q 3 score approaching 83.99% (SOV99=80.25%) and 85.58% (SOV99=81.15%). By using both sequence and structure databases and by exploiting the latest techniques in machine learning it is possible to routinely predict protein secondary structure with an accuracy well above 80%. A program and web server, called CPM, which performs these secondary structure predictions, is accessible at http://kdd.ustb.edu.cn/protein_Web/.

Improved Protein Secondary Structure Prediction Using a Intelligent HSVM Method with a New Encoding Scheme

Prediction of protein secondary structures is an important problem in bioinformatics and has many applications. Successful secondary structure predictions provide a starting point for direct tertiary structure modelling, and also can significantly improve sequence analysis and sequence-structure threading for aiding in structure and function determination. Now many secondary structure prediction methods routinely achieve accuracy (Q3) of about 70%. We believe this accuracy could be further improved by using a hybrid method as essential part of the prediction process. In this article, a hybrid SVM(HSVM) has been used to predict protein secondary structure based on the method of combining physicochemical properties of amino acid residues with position-specific scoring matrices (PSSM) containing evolutionary information. Secondary structure can be predicted at significantly increased accuracy. Using a knowledge discovery theory based on inner cognitive mechanism (KDTICM) method, we have developed a gradually enhanced, multi-layered prediction system to predict protein secondary structure, compound pyramid model (CPM). The results are found to be superior to those produced by other methods with blind test dataset from the CASP9 meeting, including the popular psipred method according to Q3 and SOV99 accuracy. The results show that our method has strong generalization ability. The CPM website is accessible at http://kdd.ustb.edu.cn/protein _Web/.

Improving protein secondary structure prediction based on short subsequences with local structure similarity

BackgroundWhen characterizing the structural topology of proteins, protein secondary structure (PSS) plays an important role in analyzing and modeling protein structures because it represents the local conformation of amino acids into regular structures. Although PSS prediction has been studied for decades, the prediction accuracy reaches a bottleneck at around 80%, and further improvement is very difficult.ResultsIn this paper, we present an improved dictionary-based PSS prediction method called SymPred, and a meta-predictor called SymPsiPred. We adopt the concept behind natural language processing techniques and propose synonymous words to capture local sequence similarities in a group of similar proteins. A synonymous word is an n-gram pattern of amino acids that reflects the sequence variation in a protein’s evolution. We generate a protein-dependent synonymous dictionary from a set of protein sequences for PSS prediction.On a large non-redundant dataset of 8,297 protein chains (DsspNr-25), the average Q3 of SymPred and SymPsiPred are 81.0% and 83.9% respectively. On the two latest independent test sets (EVA Set_1 and EVA_Set2), the average Q3 of SymPred is 78.8% and 79.2% respectively. SymPred outperforms other existing methods by 1.4% to 5.4%. We study two factors that may affect the performance of SymPred and find that it is very sensitive to the number of proteins of both known and unknown structures. This finding implies that SymPred and SymPsiPred have the potential to achieve higher accuracy as the number of protein sequences in the NCBInr and PDB databases increases.ConclusionsOur experiment results show that local similarities in protein sequences typically exhibit conserved structures, which can be used to improve the accuracy of secondary structure prediction. For the application of synonymous words, we demonstrate an example of a sequence alignment which is generated by the distribution of shared synonymous words of a pair of protein sequences. We can align the two sequences nearly perfectly which are very dissimilar at the sequence level but very similar at the structural level. The SymPred and SymPsiPred prediction servers are available at http://bio-cluster.iis.sinica.edu.tw/SymPred/.

Improving protein secondary structure prediction by using the residue conformational classes

In this paper, based on the 340 protein sequences and their corresponding secondary structures retrieved from the protein data bank (PDB), we group the 20 different amino acid residues into 3 conformational categories: f (Former), b (Breaker) and n (Neutral), which reflect the intrinsic preference of the residue for a given type of secondary structure (α-helix, β-sheets and Coil). Then, based on radial basis function neural network (RBFNN) technique, we use this information to reconstruct the input vectors and try to improve globulin protein secondary structure prediction (SSP) accuracy. The experimental results indicate that our approach outperforms the previous conventional methods.

Improved Protein Secondary Structure Prediction Using Support Vector Machine With a New Encoding Scheme and an Advanced Tertiary Classifier

Prediction of protein secondary structures is an important problem in bioinformatics and has many applications. The recent trend of secondary structure prediction studies is mostly based on the neural network or the support vector machine (SVM). The SVM method is a comparatively new learning system which has mostly been used in pattern recognition problems. In this study, SVM is used as a machine learning tool for the prediction of secondary structure and several encoding schemes, including orthogonal matrix, hydrophobicity matrix, BLOSUM62 substitution matrix, and combined matrix of these, are applied and optimized to improve the prediction accuracy. Also, the optimal window length for six SVM binary classifiers is established by testing different window sizes and our new encoding scheme is tested based on this optimal window size via sevenfold cross validation tests. The results show 2% increase in the accuracy of the binary classifiers when compared with the instances in which the classical orthogonal matrix is used. Finally, to combine the results of the six SVM binary classifiers, a new tertiary classifier which combines the results of one-versus-one binary classifiers is introduced and the performance is compared with those of existing tertiary classifiers. According to the results, the Q3 prediction accuracy of new tertiary classifier reaches 78.8% and this is better than the best result reported in the literature.

Using artificially generated spectral data to improve protein secondary structure prediction from Fourier transform infrared spectra of proteins

Secondary structures of proteins have been predicted using neural networks from their Fourier transform infrared spectra. To improve the generalization ability of the neural networks, the training data set has been artificially increased by linear interpolation. The leave-one-out approach has been used to demonstrate the applicability of the method. Bayesian regularization has been used to train the neural networks and the predictions have been further improved by the maximum-likelihood estimation method. The networks have been tested and standard error of prediction (SEP) of 4.19% for α helix, 3.49% for β sheet, and 3.15% for turns have been achieved. The results indicate that there is a significant decrease in the SEP for each type of structure parameter compared to previous works.

Improved prediction for N-termini of alpha-helices using empirical information.

The prediction of the secondary structure of proteins from their amino acid sequences remains a key component of many approaches to the protein folding problem. The most abundant form of regular secondary structure in proteins is the alpha-helix, in which specific residue preferences exist at the N-terminal locations. Propensities derived from these observed amino acid frequencies in the Protein Data Bank (PDB) database correlate well with experimental free energies measured for residues at different N-terminal positions in alanine-based peptides. We report a novel method to exploit this data to improve protein secondary structure prediction through identification of the correct N-terminal sequences in alpha-helices, based on existing popular methods for secondary structure prediction. With this algorithm, the number of correctly predicted alpha-helix start positions was improved from 30% to 38%, while the overall prediction accuracy (Q3) remained the same, using cross-validated testing. Although the algorithm was developed and tested on multiple sequence alignment-based secondary structure predictions, it was also able to improve the predictions of start locations by methods that use single sequences to make their predictions. Furthermore, the residue frequencies at N-terminal positions of the improved predictions better reflect those seen at the N-terminal positions of alpha-helices in proteins. This has implications for areas such as comparative modeling, where a more accurate prediction of the N-terminal regions of alpha-helices should benefit attempts to model adjacent loop regions. The algorithm is available as a Web tool, located at http://rocky.bms.umist.ac.uk/elephant.

Neuro‐fuzzy structural classification of proteins for improved protein secondary structure prediction

Fourier transform infrared (FTIR) spectroscopy is a very flexible technique for characterization of protein secondary structure. Measurements can be carried out rapidly in a number of different environments based on only small quantities of proteins. For this technique to become more widely used for protein secondary structure characterization, however, further developments in methods to accurately quantify protein secondary structure are necessary. Here we propose a structural classification of proteins (SCOP) class specialized neural networks architecture combining an adaptive neuro-fuzzy inference system (ANFIS) with SCOP class specialized backpropagation neural networks for improved protein secondary structure prediction. Our study shows that proteins can be accurately classified into two main classes "all alpha proteins" and "all beta proteins" merely based on the amide I band maximum position of their FTIR spectra. ANFIS is employed to perform the classification task to demonstrate the potential of this architecture with moderately complex problems. Based on studies using a reference set of 17 proteins and an evaluation set of 4 proteins, improved predictions were achieved compared to a conventional neural network approach, where structure specialized neural networks are trained based on protein spectra of both "all alpha" and "all beta" proteins. The standard errors of prediction (SEPs) in % structure were improved by 4.05% for helix structure, by 5.91% for sheet structure, by 2.68% for turn structure, and by 2.15% for bend structure. For other structure, an increase of SEP by 2.43% was observed. Those results were confirmed by a "leave-one-out" run with the combined set of 21 FTIR spectra of proteins.

Improving Protein Secondary Structure Prediction Methods Using Empirical and Evolutionary Data

Improving Protein Secondary Structure Prediction Methods Using Empirical and Evolutionary Data

Application of multiple sequence alignment profiles to improve protein secondary structure prediction.

The effect of training a neural network secondary structure prediction algorithm with different types of multiple sequence alignment profiles derived from the same sequences, is shown to provide a range of accuracy from 70.5% to 76.4%. The best accuracy of 76.4% (standard deviation 8.4%), is 3.1% (Q(3)) and 4.4% (SOV2) better than the PHD algorithm run on the same set of 406 sequence non-redundant proteins that were not used to train either method. Residues predicted by the new method with a confidence value of 5 or greater, have an average Q(3) accuracy of 84%, and cover 68% of the residues. Relative solvent accessibility based on a two state model, for 25, 5, and 0% accessibility are predicted at 76.2, 79.8, and 86. 6% accuracy respectively. The source of the improvements obtained from training with different representations of the same alignment data are described in detail. The new Jnet prediction method resulting from this study is available in the Jpred secondary structure prediction server, and as a stand-alone computer program from: http://barton.ebi.ac.uk/. Proteins 2000;40:502-511.

Information Theory and Molecular Biology

Literature contains over fifty years of accumulated methods proposed by researchers for predicting the secondary structures of proteins in silico. A large part of this collection is comprised of artificial neural network-based approaches, a field of artificial intelligence and machine learning that is gaining increasing popularity in various application areas. The primary objective of this paper is to put together the summary of works that are important but sparse in time, to help new researchers have a clear view of the domain in a single place. An informative introduction to protein secondary structure and artificial neural networks is also included for context. This review will be valuable in designing future methods to improve protein secondary structure prediction accuracy. The various neural network methods found in this problem domain employ varying architectures and feature spaces, and a handful stand out due to significant improvements in prediction. Neural networks with larger feature scope and higher architecture complexity have been found to produce better protein secondary structure prediction. The current prediction accuracy lies around the 84% marks, leaving much room for further improvement in the prediction of secondary structures in silico. It was found that the estimated limit of 88% prediction accuracy has not been reached yet, hence further research is a timely demand.

Improving protein secondary structure prediction with aligned homologous sequences.

Most recent protein secondary structure prediction methods use sequence alignments to improve the prediction quality. We investigate the relationship between the location of secondary structural elements, gaps, and variable residue positions in multiple sequence alignments. We further investigate how these relationships compare with those found in structurally aligned protein families. We show how such associations may be used to improve the quality of prediction of the secondary structure elements, using the Quadratic-Logistic method with profiles. Furthermore, we analyze the extent to which the number of homologous sequences influences the quality of prediction. The analysis of variable residue positions shows that surprisingly, helical regions exhibit greater variability than do coil regions, which are generally thought to be the most common secondary structure elements in loops. However, the correlation between variability and the presence of helices does not significantly improve prediction quality. Gaps are a distinct signal for coil regions. Increasing the coil propensity for those residues occurring in gap regions enhances the overall prediction quality. Prediction accuracy increases initially with the number of homologues, but changes negligibly as the number of homologues exceeds about 14. The alignment quality affects the prediction more than other factors, hence a careful selection and alignment of even a small number of homologues can lead to significant improvements in prediction accuracy.