Prediction of secondary structural content of proteins from their amino acid composition alone. II. The paradox with secondary structural class.

The predictive limits of the amino acid composition for the secondary structural content (percentage of residues in the secondary structural states helix, sheet, and coil) in proteins are assessed quantitatively. For the first time, techniques for prediction of secondary structural content are presented which rely on the amino acid composition as the only information on the query protein. In our first method, the amino acid composition of an unknown protein is represented by the best (in a least square sense) linear combination of the characteristic amino acid compositions of the three secondary structural types computed from a learning set of tertiary structures. The second technique is a generalization of the first one and takes into account also possible compositional couplings between any two sorts of amino acids. Its mathematical formulation results in an eigenvalue/eigenvector problem of the second moment matrix describing the amino acid compositional fluctuations of secondary structural types in various proteins of a learning set. Possible correlations of the principal directions of the eigenspaces with physical properties of the amino acids were also checked. For example, the first two eigenvectors of the helical eigenspace correlate with the size and hydrophobicity of the residue types respectively. As learning and test sets of tertiary structures, we utilized representative, automatically generated subsets of Protein Data Bank (PDB) consisting of non-homologous protein structures at the resolution thresholds < or = 1.8A, < or = 2.0A, < or = 2.5A, and < or = 3.0 A. We show that the consideration of compositional couplings improves prediction accuracy, albeit not dramatically. Whereas in the self-consistency test (learning with the protein to be predicted), a clear decrease of prediction accuracy with worsening resolution is observed, the jackknife test (leave the predicted protein out) yielded best results for the largest dataset (< or = 3.0A, almost no difference to the self-consistency test!), i.e., only this set, with more than 400 proteins, is sufficient for stable computation of the parameters in the prediction function of the second method. The average absolute error in predicting the fraction of helix, sheet, and coil from amino acid composition of the query protein are 13.7, 12.6, and 11.4%, respectively with r.m.s. deviations in the range of 8.6 divided by 11.8% for the 3.0 A dataset in a jackknife test. The absolute precision of the average absolute errors is in the range of 1 divided by 3% as measured for other representative subsets of the PDB. Secondary structural content prediction methods found in the literature have been clustered in accordance with their prediction accuracies. To our surprise, much more complex secondary structure prediction methods utilized for the same purpose of secondary structural content prediction achieve prediction accuracies very similar to those of the present analytic techniques, implying that all the information beyond the amino acid composition is, in fact, mainly utilized for positioning the secondary structural state in the sequence but not for determination of the overall number of residues in a secondary structural type. This result implies that higher prediction accuracies cannot be achieved relying solely on the amino acid composition of an unknown query protein as prediction input. Our prediction program SSCP has been made available as a World Wide Web and E-mail service.

Protein secondary structure prediction based on the GOR algorithm incorporating multiple sequence alignment information

Accurate protein secondary structure prediction from the amino acid sequence is essential for almost all theoretical and experimental studies on protein structure and function. After a brief discussion of application of data mining for optimization of crystallization conditions for target proteins we show that data mining of structural fragments of proteins from known structures in the protein data bank (PDB) significantly improves the accuracy of secondary structure predictions. The original method was proposed by us a few years ago and was termed fragment database mining (FDM) (Cheng H, Sen TZ, Kloczkowski A, Margaritis D, Jernigan RL (2005) Prediction of protein secondary structure by mining structural fragment database. Polymer 46:4314–4321). This method gives excellent accuracy for predictions if similar sequence fragments are available in our library of structural fragments, but is less successful if such fragments are absent in the fragments database. Recently we have improved secondary structure predictions further by combining FDM with classical GOR V (Kloczkowski A, Ting KL, Jernigan RL, Garnier J (2002a) Combining the GOR V algorithm with evolutionary information for protein secondary structure prediction from amino acid sequence. Proteins 49:154–66; Sen TZ, Jernigan RL, Garnier J, Kloczkowski A (2005) GOR V server for protein secondary structure prediction. Bioinformatics 21:2787–8) predictions to form a combined method, so-called consensus database mining (CDM) (Sen TZ, Cheng H, Kloczkowski A, Jernigan RL (2006) A Consensus Data Mining secondary structure prediction by combining GOR V and Fragment Database Mining. Protein Sci 15:2499–506). FDM mines the structural segments of PDB, and utilizes structural information from the matching sequence fragments for the prediction of protein secondary structures. By combining it with the GOR V secondary structure prediction method, which is based on information theory and Bayesian statistics, coupled with evolutionary information from multiple sequence alignments (MSA), our CDM method guarantees improved accuracies of prediction. Additionally, with the constant growth in the number of new protein structures and folds in the PDB, the accuracy of the CDM method is clearly expected to increase in future. We have developed a publicly available CDM server (Cheng H, Sen TZ, Jernigan RL, Kloczkowski A (2007) Consensus Data Mining (CDM) Protein Secondary Structure Prediction Server: combining GOR V and Fragment Database Mining (FDM). Bioinformatics 23:2628–30) (http://gor.bb.iastate.edu/cdm) for protein secondary structure prediction.

An algorithm has been developed to improve the success rate in the prediction of the secondary structure of proteins by taking into account the predicted class of the proteins. This method has been called the 'double prediction method' and consists of a first prediction of the secondary structure from a new algorithm which uses parameters of the type described by Chou and Fasman, and the prediction of the class of the proteins from their amino acid composition. These two independent predictions allow one to optimize the parameters calculated over the secondary structure database to provide the final prediction of secondary structure. This method has been tested on 59 proteins in the database (i.e. 10,322 residues) and yields 72% success in class prediction, 61.3% of residues correctly predicted for three states (helix, sheet and coil) and a good agreement between observed and predicted contents in secondary structure.

Correct prediction of secondary and tertiary structure of proteins is one of the major challenges in bioinformatics/computational biological research. Predicting the correct secondary structure is the key to predict a good/satisfactory tertiary structure of the protein which not only helps in prediction of protein function but also in prediction of sub-cellular localization. This chapter aims to explain the different algorithms and methodologies, which are used in secondary structure prediction. Similarly, tertiary structure prediction has also emerged as one of developing areas of bioinformatics/computational biological research owing to the large gap between the available number of protein sequences and the known experimentally solved structures. Because of time and cost intensive experimental methods, experimentally determined structures are not available for vast majority of the available protein sequences present in public domain databases. The primary aim of this chapter is to offer a detailed conceptual insight to the algorithms used for protein secondary and tertiary structure prediction. This chapter systematically illustrates flowchart for selecting the most accurate prediction algorithm among different categories for the target sequence against three categories of tertiary structure prediction methods. Out of the three methods, homology modeling which is considered as most reliable method is discussed in detail followed by strengths and limitations for each of these categories. This chapter also explains different practical and conceptual problems, obstructing the high accuracy of the protein structure in each of the steps for all the three methods of tertiary structure prediction. The popular hybrid methodologies which further club together a number of features such as structural alignments, solvent accessibility and secondary structure information are also discussed. Moreover, this chapter elucidates about the Meta-servers that generate consensus result from many servers to build a protein model of high accuracy. Lastly, scope for further research in order to bridge existing gaps and for developing better secondary and tertiary structure prediction algorithms is also highlighted.

Chapter 5 - Protein Structure Prediction

Three different strategies to tackle mispredictions from incorrect secondary structure prediction are analysed using 21 small proteins (22-121 amino acids; 1-6 secondary structure elements) with known three dimensional structures: (1) Testing accuracy of different secondary structure predictions and improving them by combinations, (2) correcting mispredictions exploiting protein folding simulations with a genetic algorithm and (3) applying and combining experimental data to refine predictions both for secondary structure and tertiary fold. We demonstrate that predictions from secondary structure prediction programs can be efficiently combined to reduce prediction errors from missed secondary structure elements. Further, up to two secondary structure elements (helices, strands) missed by secondary structure prediction were corrected by the genetic algorithm simulation. Finally, we show how input from experimental data is exploited to refine the predictions obtained.

Exponential growth in the number of available protein sequences is unmatched by the slower growth in the number of structures. As a result, the development of efficient and fast protein secondary structure prediction methods is essential for the broad comprehension of protein structures. Computational methods that can efficiently determine secondary structure can in turn facilitate protein tertiary structure prediction, since most methods rely initially on secondary structure predictions. Recently, we have developed a fast learning optimized prediction methodology (FLOPRED) for predicting protein secondary structure (Saraswathi et al. in JMM 18:4275, 2012). Data are generated by using knowledge-based potentials combined with structure information from the CATH database. A neural network-based extreme learning machine (ELM) and advanced particle swarm optimization (PSO) are used with this data to obtain better and faster convergence to more accurate secondary structure predicted results. A five-fold cross-validated testing accuracy of 83.8 % and a segment overlap (SOV) score of 78.3 % are obtained in this study. Secondary structure predictions and their accuracy are usually presented for three secondary structure elements: α-helix, β-strand and coil but rarely have the results been analyzed with respect to their constituent amino acids. In this paper, we use the results obtained with FLOPRED to provide detailed behaviors for different amino acid types in the secondary structure prediction. We investigate the influence of the composition, physico-chemical properties and position specific occurrence preferences of amino acids within secondary structure elements. In addition, we identify the correlation between these properties and prediction accuracy. The present detailed results suggest several important ways that secondary structure predictions can be improved in the future that might lead to improved protein design and engineering.

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 data-base individually).

A primary and a secondary neural network are applied to secondary structure and structural class prediction for a database of 681 non-homologous protein chains. A new method of decoding the outputs of the secondary structure prediction network is used to produce an estimate of the probability of finding each type of secondary structure at every position in the sequence. In addition to providing a reliable estimate of the accuracy of the predictions, this method gives a more accurate Q3 (74.6%) than the cutoff method which is commonly used. Use of these predictions in jury methods improves the Q3 to 74.8%, the best available at present. On a database of 126 proteins commonly used for comparison of prediction methods, the jury predictions are 76.6% accurate. An estimate of the overall Q3 for a given sequence is made by averaging the estimated accuracy of the prediction over all residues in the sequence. As an example, the analysis is applied to the target beta-cryptogein, which was a difficult target for ab initio predictions in the CASP2 study; it shows that the prediction made with the present method (62% of residues correct) is close to the expected accuracy (66%) for this protein. The larger database and use of a new network training protocol also improve structural class prediction accuracy to 86%, relative to 80% obtained previously. Secondary structure content is predicted with accuracy comparable to that obtained with spectroscopic methods, such as vibrational or electronic circular dichroism and Fourier transform infrared spectroscopy.

A primary and a secondary neural network are applied to secondary structure and structural class prediction for a database of 681 non-homologous protein chains. A new method of decoding the outputs of the secondary structure prediction network is used to produce an estimate of the probability of finding each type of secondary structure at every position in the sequence. In addition to providing a reliable estimate of the accuracy of the predictions, this method gives a more accurate Q3 (74.6%) than the cutoff method which is commonly used. Use of these predictions in jury methods improves the Q3 to 74.8%, the best available at present. On a database of 126 proteins commonly used for comparison of prediction methods, the jury predictions are 76.6% accurate. An estimate of the overall Q3 for a given sequence is made by averaging the estimated accuracy of the prediction over all residues in the sequence. As an example, the analysis is applied to the target β-cryptogein, which was a difficult target for ab initio predictions in the CASP2 study; it shows that the prediction made with the present method (62% of residues correct) is close to the expected accuracy (66%) for this protein. The larger database and use of a new network training protocol also improve structural class prediction accuracy to 86%, relative to 80% obtained previously. Secondary structure content is predicted with accuracy comparable to that obtained with spectroscopic methods, such as vibrational or electronic circular dichroism and Fourier transform infrared spectroscopy. Proteins 1999;35:293–306. © 1999 Wiley-Liss, Inc.

Prediction of the protein secondary structure is a key issue in protein science. Protein secondary structure prediction (PSSP) aims to construct a function that can map the amino acid sequence into the secondary structure so that the protein secondary structure can be obtained according to the amino acid sequence. Driven by deep learning, the prediction accuracy of the protein secondary structure has been greatly improved in recent years. To explore a new technique of PSSP, this study introduces the concept of an adversarial game into the prediction of the secondary structure, and a conditional generative adversarial network (GAN)-based prediction model is proposed. We introduce a new multiscale convolution module and an improved channel attention (ICA) module into the generator to generate the secondary structure, and then a discriminator is designed to conflict with the generator to learn the complicated features of proteins. Then, we propose a PSSP method based on the proposed multiscale convolution module and ICA module. The experimental results indicate that the conditional GAN-based protein secondary structure prediction (CGAN-PSSP) model is workable and worthy of further study because of the strong feature-learning ability of adversarial learning.

A neural network algorithm is applied to secondary structure and structural class prediction for a database of 318 nonhomologous protein chains. Significant improvement in accuracy is obtained as compared with performance on smaller databases. A systematic study of the effects of network topology shows that, for the larger database, better results are obtained with more units in the hidden layer. In a 32-fold cross validated test, secondary structure prediction accuracy is 67.0%, relative to 62.6% obtained previously, without any evolutionary information on the sequence. Introduction of sequence profiles increases this value to 72.9%, suggesting that the two types of information are essentially independent. Tertiary structural class is predicted with 80.2% accuracy, relative to 73.9% obtained previously. The use of a larger database is facilitated by the introduction of a scaled conjugate gradient algorithm for optimizing the neural network. This algorithm is about 10-20 times as fast as the standard steepest descent algorithm.

BackgroundCatalase (EC 1.11.1.6) is a heme-containing tetrameric enzyme that plays a critical role in signaling and hydrogen peroxide metabolism. It was the first enzyme to be crystallized and isolated. Catalase is a well-known industrial enzyme used in diagnostic and analytical methods in the form of biomarkers and biosensors, as well as in the textile, paper, food, and pharmaceutical industries. In silico analysis of CAT genes and proteins has gained increased interest, emphasizing the development of biomarkers and drug designs. The present work aims to understand the catalase evolutionary relationship of plant species and analyze its physicochemical characteristics, homology, phylogenetic tree construction, secondary structure prediction, and 3D modeling of protein sequences and its validation using a variety of conventional computational methods to assist researchers in better understanding the structure of proteins. ResultsAround 65 plant catalase sequences were computationally evaluated and subjected to bioinformatics assessment for physicochemical characterization, multiple sequence alignment, phylogenetic construction, motif and domain identification, and secondary and tertiary structure prediction. The phylogenetic tree revealed six unique clusters where diversity of plant catalases was found to be the largest for Oryza sativa. The thermostability and hydrophilic nature of these proteins were primarily observed, as evidenced by a relatively high aliphatic index and negative GRAVY value. The distribution of 5 sequence motifs was uniformly distributed with a width length of 50 with the best possible amino residue sequences that resemble the plant catalase PLN02609 superfamily. Using SOPMA, the predicted secondary structure of the protein sequences revealed the predominance of the random coil. The predicted 3D CAT model from Arabidopsis thaliana was a homotetramer, thermostable protein with 59-KDa weight, and its structural validation was confirmed by PROCHECK, ERRAT, Verify3D, and Ramachandran plot. The functional relationships of our query sequence revealed the glutathione reductase as the closest interacting protein of query protein. ConclusionsThis theoretical plant catalases in silico analysis provide insight into its physiochemical characteristics and functional and structural understanding and its evolutionary behavior and exploring protein structure-function relationships when crystal structures are unavailable.

BackgroundProtein secondary structure prediction provides insight into protein function and is a valuable preliminary step for predicting the 3D structure of a protein. Dynamic Bayesian networks (DBNs) and support vector machines (SVMs) have been shown to provide state-of-the-art performance in secondary structure prediction. As the size of the protein database grows, it becomes feasible to use a richer model in an effort to capture subtle correlations among the amino acids and the predicted labels. In this context, it is beneficial to derive sparse models that discourage over-fitting and provide biological insight.ResultsIn this paper, we first show that we are able to obtain accurate secondary structure predictions. Our per-residue accuracy on a well established and difficult benchmark (CB513) is 80.3%, which is comparable to the state-of-the-art evaluated on this dataset. We then introduce an algorithm for sparsifying the parameters of a DBN. Using this algorithm, we can automatically remove up to 70-95% of the parameters of a DBN while maintaining the same level of predictive accuracy on the SD576 set. At 90% sparsity, we are able to compute predictions three times faster than a fully dense model evaluated on the SD576 set. We also demonstrate, using simulated data, that the algorithm is able to recover true sparse structures with high accuracy, and using real data, that the sparse model identifies known correlation structure (local and non-local) related to different classes of secondary structure elements.ConclusionsWe present a secondary structure prediction method that employs dynamic Bayesian networks and support vector machines. We also introduce an algorithm for sparsifying the parameters of the dynamic Bayesian network. The sparsification approach yields a significant speed-up in generating predictions, and we demonstrate that the amino acid correlations identified by the algorithm correspond to several known features of protein secondary structure. Datasets and source code used in this study are available at http://noble.gs.washington.edu/proj/pssp.