Machine Learning Techniques for Protein Secondary Structure Prediction:An Overview and Evaluation

MulStack: An ensemble learning prediction model of multilabel mRNA subcellular localization

Subcellular localization of mRNA is related to protein synthesis, cell polarity, cell movement and other biological regulation mechanisms. The distribution of mRNAs in subcellulars is similar to that of proteins, and most mRNAs are distributed in multiple subcellulars. Recently, some computational methods have been designed to predict the subcellular localization of mRNA. However, these methods only employed a sin-gle level of mRNA features and did not employ the position encoding of nucleotides in mRNA. In this paper, an ensemble learning prediction model is proposed, named MulStack, which is based on random forest and deep learning for multilabel mRNA subcellular localization. The proposed method employs two levels of mRNA features, including sequence-level and residue-level features, and position encoding is employed for the first time in the field of subcellular localization of mRNA. Random forest is employed to learn mRNA sequence-level feature, deep learning is employed to learn mRNA sequence-level feature and mRNA residue-level combined with position encoding. And the outputs of random forest and deep learning model will be weighted sum as the prediction probability. Compared with existing methods, the results show that MulStack is the best in the localization of the nucleus, cytosol and exosome. In addition, position weight matrices (PWMs) are extracted by convolutional neural networks (CNNs) that can be matched with known RNA binding protein motifs. Gene ontology (GO) enrichment analysis shows biological processes, molecular functions and cellular components of mRNA genes. The prediction web server of MulStack is freely accessible at http://bliulab.net/MulStack.

DLC-ac4C: A Prediction Model for N4-acetylcytidine Sites in Human mRNA Based on DenseNet and Bidirectional LSTM Methods

Introduction

N4 acetylcytidine (ac4C) is a highly conserved nucleoside modification that is essential for the regulation of immune functions in organisms. Currently, the identification of ac4C is primarily achieved using biological methods, which can be time-consuming and labor-intensive. In contrast, accurate identification of ac4C by computational methods has become a more effective method for classification and prediction.

Aim

To the best of our knowledge, although there are several computational methods for ac4C locus prediction, the performance of the models they constructed is poor, and the network structure they used is relatively simple and suffers from the disadvantage of network degradation. This study aims to improve these limitations by proposing a predictive model based on integrated deep learning to better help identify ac4C sites.

Methods

In this study, we propose a new integrated deep learning prediction framework, DLC-ac4C. First, we encode RNA sequences based on three feature encoding schemes, namely C2 encoding, nucleotide chemical property (NCP) encoding, and nucleotide density (ND) encoding. Second, one-dimensional convolutional layers and densely connected convolutional networks (DenseNet) are used to learn local features, and bi-directional long short-term memory networks (Bi-LSTM) are used to learn global features. Third, a channel attention mechanism is introduced to determine the importance of sequence characteristics. Finally, a homomorphic integration strategy is used to limit the generalization error of the model, which further improves the performance of the model.

Results

The DLC-ac4C model performed well in terms of sensitivity (Sn), specificity (Sp), accuracy (Acc), Mathews correlation coefficient (MCC), and area under the curve (AUC) for the independent test data with 86.23%, 79.71%, 82.97%, 66.08%, and 90.42%, respectively, which was significantly better than the prediction accuracy of the existing methods.

Conclusion

Our model not only combines DenseNet and Bi-LSTM, but also uses the channel attention mechanism to better capture hidden information features from a sequence perspective, and can identify ac4C sites more effectively.

Whole-Genome Sequencing of a Potential Ester-Synthesizing Bacterium Isolated from Fermented Golden Pomfret and Identification of Its Lipase Encoding Genes

Microbial ester synthases are regarded as valuable catalysts in the food industry. Here, one strain of Acinetobacter venetianus with ester synthase-production capacity, SCSMX-3, was isolated from traditional fermented golden pomfret. It exhibited good growth in mesophilic, low salt, and slightly alkaline environments. The ester synthase produced by SCSMX-3 displayed maximum activity at pH 8.0 and 35 °C. Genome sequencing revealed that the strain contains one circular chromosome of 336313 bp and two circular plasmids (plasmid A-14424 bp and plasmid B-11249 bp). Six CRISPR structures enhance the genomic stability of SCSMX-3 and provide the opportunity to create new functional strains. Gene function analysis indicated that SCSMX-3 produces the necessary enzymes for survival under different conditions and for flavor substance synthesis. Furthermore, 49 genes encoding enzymes associated with lipid metabolism, including three triacylglycerol lipases and two esterases, were identified through the NCBI Non-Redundant Protein Database. The lipase encoded by gene0302 belongs to the GX group and the abH15.02 (Burkholderia cepacia lipase) homolog of the abH15 superfamily. Our results shed light on the genomic diversity of and lipid metabolism in A. venetianus isolated from fermented golden pomfret, laying a foundation for the exploration of new ester synthases to improve the flavor of fermented fish products.

CNNLSTMac4CPred: A Hybrid Model for N4-Acetylcytidine Prediction

N4-Acetylcytidine (ac4C) is a highly conserved post-transcriptional and an extensively existing RNA modification, playing versatile roles in the cellular processes. Due to the limitation of techniques and knowledge, large-scale identification of ac4C is still a challenging task. RNA sequences are like sentences containing semantics in the natural language. Inspired by the semantics of language, we proposed a hybrid model for ac4C prediction. The model used long short-term memory and convolution neural network to extract the semantic features hidden in the sequences. The semantic and the two traditional features (k-nucleotide frequencies and pseudo tri-tuple nucleotide composition) were combined to represent ac4C or non-ac4C sequences. The eXtreme Gradient Boosting was used as the learning algorithm. Five-fold cross-validation over the training set consisting of 1160 ac4C and 10,855 non-ac4C sequences obtained the area under the receiver operating characteristic curve (AUROC) of 0.9004, and the independent test over 469 ac4C and 4343 non-ac4C sequences reached an AUROC of 0.8825. The model obtained a sensitivity of 0.6474 in the five-fold cross-validation and 0.6290 in the independent test, outperforming two state-of-the-art methods. The performance of semantic features alone was better than those of k-nucleotide frequencies and pseudo tri-tuple nucleotide composition, implying that ac4C sequences are of semantics. The proposed hybrid model was implemented into a user-friendly web-server which is freely available to scientific communities: http://47.113.117.61/ac4c/ . The presented model and tool are beneficial to identify ac4C on large scale.

Variable Length Character N-Gram Embedding of Protein Sequences for Secondary Structure Prediction

BACKGROUND

The prediction of a protein's secondary structure from its amino acid sequence is an essential step towards predicting its 3-D structure. The prediction performance improves by incorporating homologous multiple sequence alignment information. Since homologous details not available for all proteins. Therefore, it is necessary to predict the protein secondary structure from single sequences.

OBJECTIVE AND METHODS

Protein secondary structure predicted from their primary sequences using n-gram word embedding and deep recurrent neural network. Protein secondary structure depends on local and long-range neighbor residues in primary sequences. In the proposed work, the local contextual information of amino acid residues captures variable-length character n-gram words. An embedding vector represents these variable-length character n-gram words. Further, the bidirectional long short-term memory (Bi-LSTM) model is used to capture the long-range contexts by extracting the past and future residues information in primary sequences.

RESULTS

The proposed model evaluates on three public datasets ss.txt, RS126, and CASP9. The model shows the Q3 accuracy of 92.57%, 86.48%, and 89.66% for ss.txt, RS126, and CASP9.

CONCLUSION

The proposed model performance compares with state-of-the-art methods available in the literature. After a comparative analysis, it observed that the proposed model performs better than state-of-the-art methods.

Protein secondary structure prediction (PSSP) using different machine algorithms

Background

The computational biology approach has advanced exponentially in protein secondary structure prediction (PSSP), which is vital for the pharmaceutical industry. Extracting protein structure from the laboratory has insufficient information for PSSP that is used in bioinformatics studies. In this paper, the support vector machine (SVM) model and decision tree are presented on the RS126 dataset to address the problem of PSSP. A decision tree is applied for the SVM outcome to obtain the relevant guidelines possible for PSSP. Furthermore, the number of produced rules was fairly small, and they show a greater degree of comprehensibility compared to other rules. Several of the proposed principles have compelling and relevant biological clarification.

Results

The results confirmed that the existence of a particular amino acid in a protein sequence increases the stability for the forecast of protein secondary structure. The suggested algorithm achieved 85% accuracy for the E|~E classifier.

Conclusions

The proposed rules can be very important in managing wet laboratory experiments intended at determining protein secondary structure. Lastly, future work will focus mainly on large protein datasets without overfitting and expand the amount of extracted regulations for PSSP.

Protein Secondary Structure Prediction Using Character Bi-gram Embedding and Bi-LSTM

Background:

Protein secondary structure is vital to predicting the tertiary structure, which is essential in deciding protein function and drug designing. Therefore, there is a high requirement of computational methods to predict secondary structure from their primary sequence. Protein primary sequences represented as a linear combination of twenty amino acid characters and contain the contextual information for secondary structure prediction.

Objective and Methods:

Protein secondary structure predicted from their primary sequences using a deep recurrent neural network. Protein secondary structure depends on local and long-range residues in primary sequences. In the proposed work, the local contextual information of amino acid residues captures with character n-gram. A dense embedding vector represents this local contextual information. Furthermore, the bidirectional long short-term memory (Bi-LSTM) model is used to capture the long-range contexts by extracting the past and future residues information in primary sequences.

Results:

The proposed deep recurrent architecture is evaluated for its efficacy for datasets, namely ss.txt, RS126, and CASP9. The model shows the Q3 accuracies of 88.45%, 83.48%, and 86.69% for ss.txt, RS126, and CASP9, respectively. The performance of the proposed model is also compared with other state-of-the-art methods available in the literature.

Conclusion:

After a comparative analysis, it was observed that the proposed model is performing better in comparison to state-of-art methods.

Machine learning for phytopathology: from the molecular scale towards the network scale

With the increasing volume of high-throughput sequencing data from a variety of omics techniques in the field of plant-pathogen interactions, sorting, retrieving, processing and visualizing biological information have become a great challenge. Within the explosion of data, machine learning offers powerful tools to process these complex omics data by various algorithms, such as Bayesian reasoning, support vector machine and random forest. Here, we introduce the basic frameworks of machine learning in dissecting plant-pathogen interactions and discuss the applications and advances of machine learning in plant-pathogen interactions from molecular to network biology, including the prediction of pathogen effectors, plant disease resistance protein monitoring and the discovery of protein-protein networks. The aim of this review is to provide a summary of advances in plant defense and pathogen infection and to indicate the important developments of machine learning in phytopathology.

A Deep Convolutional Neural Network to Improve the Prediction of Protein Secondary Structure

Background:

Protein secondary structure prediction (PSSP) is a fundamental task in bioinformatics that is helpful for understanding the three-dimensional structure and biological function of proteins. Many neural network-based prediction methods have been developed for protein secondary structures. Deep learning and multiple features are two obvious means to improve prediction accuracy.

Objective:

To promote the development of PSSP, a deep convolutional neural network-based method is proposed to predict both the eight-state and three-state of protein secondary structure.

Methods:

In this model, sequence and evolutionary information of proteins are combined as multiple input features after preprocessing. A deep convolutional neural network with no pooling layer and connection layer is then constructed to predict the secondary structure of proteins. L2 regularization, batch normalization, and dropout techniques are employed to avoid over-fitting and obtain better prediction performance, and an improved cross-entropy is used as the loss function.

Results:

Our proposed model can obtain Q3 prediction results of 86.2%, 84.5%, 87.8%, and 84.7%, respectively, on CullPDB, CB513, CASP10 and CASP11 datasets, with corresponding Q8 prediction results of 74.1%, 70.5%, 74.9%, and 71.3%.

Conclusion:

We have proposed the DCNN-SS deep convolutional-network-based PSSP method, and experimental results show that DCNN-SS performs competitively with other methods.

Amino Acid Encoding Methods for Protein Sequences: A Comprehensive Review and Assessment

As the first step of machine-learning based protein structure and function prediction, the amino acid encoding play a fundamental role in the final success of those methods. Different from the protein sequence encoding, the amino acid encoding can be used in both residue-level and sequence-level prediction of protein properties by combining them with different algorithms. However, it has not attracted enough attention in the past decades, and there are no comprehensive reviews and assessments about encoding methods so far. In this article, we make a systematic classification and propose a comprehensive review and assessment for various amino acid encoding methods. Those methods are grouped into five categories according to their information sources and information extraction methodologies, including binary encoding, physicochemical properties encoding, evolution-based encoding, structure-based encoding, and machine-learning encoding. Then, 16 representative methods from five categories are selected and compared on protein secondary structure prediction and protein fold recognition tasks by using large-scale benchmark datasets. The results show that the evolution-based position-dependent encoding method PSSM achieved the best performance, and the structure-based and machine-learning encoding methods also show some potential for further application, the neural network based distributed representation of amino acids in particular may bring new light to this area. We hope that the review and assessment are useful for future studies in amino acid encoding.

A Systematic Review on Popularity, Application and Characteristics of Protein Secondary Structure Prediction Tools

BACKGROUND

Prediction of proteins' secondary structure is one of the major steps in the generation of homology models. These models provide structural information which is used to design suitable ligands for potential medicinal targets. However, selecting a proper tool between multiple Secondary Structure Prediction (SSP) options is challenging. The current study is an insight into currently favored methods and tools, within various contexts.

OBJECTIVE

A systematic review was performed for a comprehensive access to recent (2013-2016) studies which used or recommended protein SSP tools.

METHODS

Three databases, Web of Science, PubMed and Scopus were systematically searched and 99 out of the 209 studies were finally found eligible to extract data.

RESULTS

Four categories of applications for 59 retrieved SSP tools were: (I) prediction of structural features of a given sequence, (II) evaluation of a method, (III) providing input for a new SSP method and (IV) integrating an SSP tool as a component for a program. PSIPRED was found to be the most popular tool in all four categories. JPred and tools utilizing PHD (Profile network from HeiDelberg) method occupied second and third places of popularity in categories I and II. JPred was only found in the two first categories, while PHD was present in three fields.

CONCLUSION

This study provides a comprehensive insight into the recent usage of SSP tools which could be helpful for selecting a proper tool.

BioSeq-Analysis2.0: an updated platform for analyzing DNA, RNA and protein sequences at sequence level and residue level based on machine learning approaches

As the first web server to analyze various biological sequences at sequence level based on machine learning approaches, many powerful predictors in the field of computational biology have been developed with the assistance of the BioSeq-Analysis. However, the BioSeq-Analysis can be only applied to the sequence-level analysis tasks, preventing its applications to the residue-level analysis tasks, and an intelligent tool that is able to automatically generate various predictors for biological sequence analysis at both residue level and sequence level is highly desired. In this regard, we decided to publish an important updated server covering a total of 26 features at the residue level and 90 features at the sequence level called BioSeq-Analysis2.0 (http://bliulab.net/BioSeq-Analysis2.0/), by which the users only need to upload the benchmark dataset, and the BioSeq-Analysis2.0 can generate the predictors for both residue-level analysis and sequence-level analysis tasks. Furthermore, the corresponding stand-alone tool was also provided, which can be downloaded from http://bliulab.net/BioSeq-Analysis2.0/download/. To the best of our knowledge, the BioSeq-Analysis2.0 is the first tool for generating predictors for biological sequence analysis tasks at residue level. Specifically, the experimental results indicated that the predictors developed by BioSeq-Analysis2.0 can achieve comparable or even better performance than the existing state-of-the-art predictors.

Multifaceted analysis of training and testing convolutional neural networks for protein secondary structure prediction

Protein secondary structure prediction remains a vital topic with broad applications. Due to lack of a widely accepted standard in secondary structure predictor evaluation, a fair comparison of predictors is challenging. A detailed examination of factors that contribute to higher accuracy is also lacking. In this paper, we present: (1) new test sets, Test2018, Test2019, and Test2018-2019, consisting of proteins from structures released in 2018 and 2019 with less than 25% identity to any protein published before 2018; (2) a 4-layer convolutional neural network, SecNet, with an input window of ±14 amino acids which was trained on proteins ≤25% identical to proteins in Test2018 and the commonly used CB513 test set; (3) an additional test set that shares no homologous domains with the training set proteins, according to the Evolutionary Classification of Proteins (ECOD) database; (4) a detailed ablation study where we reverse one algorithmic choice at a time in SecNet and evaluate the effect on the prediction accuracy; (5) new 4- and 5-label prediction alphabets that may be more practical for tertiary structure prediction methods. The 3-label accuracy (helix, sheet, coil) of the leading predictors on both Test2018 and CB513 is 81-82%, while SecNet's accuracy is 84% for both sets. Accuracy on the non-homologous ECOD set is only 0.6 points (83.9%) lower than the results on the Test2018-2019 set (84.5%). The ablation study of features, neural network architecture, and training hyper-parameters suggests the best accuracy results are achieved with good choices for each of them while the neural network architecture is not as critical as long as it is not too simple. Protocols for generating and using unbiased test, validation, and training sets are provided. Our data sets, including input features and assigned labels, and SecNet software including third-party dependencies and databases, are downloadable from dunbrack.fccc.edu/ss and github.com/sh-maxim/ss.

Probing the effect of a plus 1bp frameshift mutation in protein-DNA interface of domestication gene, NAMB1, in wheat

Transcription factor NAM-B1 has a major role in the process of senescence, which results in higher Fe and Zn concentrations in grains of wild wheat (T. durum; Td). The absence of the wild type NAMB1 in T. aestivum (Ta), one of the cardinal crops essential for more than 1/3^rd of the global population, affects Fe and Zn remobilisation to the maturing grain from the flag leaf resulting in lesser micronutrient bioavailability. The cardinal difference in the NAMB1 gene between the two species is the absence of +1 bp allele in Ta. Insilico studies using NAMB1 from Td and Ta was performed to explore the variation in the interaction with the conserved cis-element DNA motif (CATGTG) as both the proteins share the same domain, but there are no in silico studies reported of these proteins. The secondary structure, 3D-modelling of the proteins, DNA-protein docking and dynamics have computed by Schrodinger Prime Suite. Predicted secondary structures were energy minimised using Macromodel and docking was performed based on binding energy and hydrogen bonds. Molecular dynamics simulation of NAMB1-Ta and NAMB1-Td individually and with the cis-element motif, performed for 100 ns, revealed significant variations in the protein-DNA interaction in Ta. This work provides the modelled 3D-interaction profile caused by a single bp frameshift mutation in understanding the difference in function between NAMB1 orthologs due to lack of NAC domain. The overall computational analysis reveals that NAMB1-Ta and NAMB1-Td proteins display a good amount of dissimilarity in their structure, dynamics and DNA-binding characteristics.Communicated by Ramaswamy H. Sarma.

Protein Secondary Structure Prediction Based on Data Partition and Semi-Random Subspace Method

Protein secondary structure prediction is one of the most important and challenging problems in bioinformatics. Machine learning techniques have been applied to solve the problem and have gained substantial success in this research area. However there is still room for improvement toward the theoretical limit. In this paper, we present a novel method for protein secondary structure prediction based on a data partition and semi-random subspace method (PSRSM). Data partitioning is an important strategy for our method. First, the protein training dataset was partitioned into several subsets based on the length of the protein sequence. Then we trained base classifiers on the subspace data generated by the semi-random subspace method, and combined base classifiers by majority vote rule into ensemble classifiers on each subset. Multiple classifiers were trained on different subsets. These different classifiers were used to predict the secondary structures of different proteins according to the protein sequence length. Experiments are performed on 25PDB, CB513, CASP10, CASP11, CASP12, and T100 datasets, and the good performance of 86.38%, 84.53%, 85.51%, 85.89%, 85.55%, and 85.09% is achieved respectively. Experimental results showed that our method outperforms other state-of-the-art methods.

Sixty-five years of the long march in protein secondary structure prediction: the final stretch?

Protein secondary structure prediction began in 1951 when Pauling and Corey predicted helical and sheet conformations for protein polypeptide backbone even before the first protein structure was determined. Sixty-five years later, powerful new methods breathe new life into this field. The highest three-state accuracy without relying on structure templates is now at 82-84%, a number unthinkable just a few years ago. These improvements came from increasingly larger databases of protein sequences and structures for training, the use of template secondary structure information and more powerful deep learning techniques. As we are approaching to the theoretical limit of three-state prediction (88-90%), alternative to secondary structure prediction (prediction of backbone torsion angles and Cα-atom-based angles and torsion angles) not only has more room for further improvement but also allows direct prediction of three-dimensional fragment structures with constantly improved accuracy. About 20% of all 40-residue fragments in a database of 1199 non-redundant proteins have <6 Å root-mean-squared distance from the native conformations by SPIDER2. More powerful deep learning methods with improved capability of capturing long-range interactions begin to emerge as the next generation of techniques for secondary structure prediction. The time has come to finish off the final stretch of the long march towards protein secondary structure prediction.

Accurate Prediction of One-Dimensional Protein Structure Features Using SPINE-X

Accurate prediction of protein secondary structure and other one-dimensional structure features is essential for accurate sequence alignment, three-dimensional structure modeling, and function prediction. SPINE-X is a software package to predict secondary structure as well as accessible surface area and dihedral angles ϕ and ψ. For secondary structure SPINE-X achieves an accuracy of between 81 and 84 % depending on the dataset and choice of tests. The Pearson correlation coefficient for accessible surface area prediction is 0.75 and the mean absolute error from the ϕ and ψ dihedral angles are 20^∘ and 33^∘, respectively. The source code and a Linux executables for SPINE-X are available from Research and Information Systems at http://mamiris.com .

Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields

Protein secondary structure (SS) prediction is important for studying protein structure and function. When only the sequence (profile) information is used as input feature, currently the best predictors can obtain ~80% Q3 accuracy, which has not been improved in the past decade. Here we present DeepCNF (Deep Convolutional Neural Fields) for protein SS prediction. DeepCNF is a Deep Learning extension of Conditional Neural Fields (CNF), which is an integration of Conditional Random Fields (CRF) and shallow neural networks. DeepCNF can model not only complex sequence-structure relationship by a deep hierarchical architecture, but also interdependency between adjacent SS labels, so it is much more powerful than CNF. Experimental results show that DeepCNF can obtain ~84% Q3 accuracy, ~85% SOV score, and ~72% Q8 accuracy, respectively, on the CASP and CAMEO test proteins, greatly outperforming currently popular predictors. As a general framework, DeepCNF can be used to predict other protein structure properties such as contact number, disorder regions, and solvent accessibility.

Randomized Subspace Learning for Proline Cis-Trans Isomerization Prediction

Proline residues are common source of kinetic complications during folding. The X-Pro peptide bond is the only peptide bond for which the stability of the cis and trans conformations is comparable. The cis-trans isomerization (CTI) of X-Pro peptide bonds is a widely recognized rate-limiting factor, which can not only induces additional slow phases in protein folding but also modifies the millisecond and sub-millisecond dynamics of the protein. An accurate computational prediction of proline CTI is of great importance for the understanding of protein folding, splicing, cell signaling, and transmembrane active transport in both the human body and animals. In our earlier work, we successfully developed a biophysically motivated proline CTI predictor utilizing a novel tree-based consensus model with a powerful metalearning technique and achieved 86.58 percent Q2 accuracy and 0.74 Mcc, which is a better result than the results (70-73 percent Q2 accuracies) reported in the literature on the well-referenced benchmark dataset. In this paper, we describe experiments with novel randomized subspace learning and bootstrap seeding techniques as an extension to our earlier work, the consensus models as well as entropy-based learning methods, to obtain better accuracy through a precise and robust learning scheme for proline CTI prediction.

Intelligent Consensus Modeling for Proline Cis-Trans Isomerization Prediction

Proline cis-trans isomerization (CTI) plays a key role in the rate-determining steps of protein folding. Accurate prediction of proline CTI is of great importance for the understanding of protein folding, splicing, cell signaling, and transmembrane active transport in both the human body and animals. Our goal is to develop a state-of-the-art proline CTI predictor based on a biophysically motivated intelligent consensus modeling through the use of sequence information only (i.e., position specific scores generated by PSI-BLAST). The current computational proline CTI predictors reach about 70-73 percent Q2 accuracies and about 0.40 Matthew correlation coefficient (Mcc) through the use of sequence-based evolutionary information as well as predicted protein secondary structure information. However, our approach that utilizes a novel decision tree-based consensus model with a powerful randomized-metal earning technique has achieved 86.58 percent Q2 accuracy and 0.74 Mcc, on the same proline CTI data set, which is a better result than those of any existing computational proline CTI predictors reported in the literature.

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/