Real-SPINE: An integrated system of neural networks for real-value prediction of protein structural properties

Predicting lysine methylation sites using a convolutional neural network

Protein lysine methylation is a particular type of post translational modification that plays an important role in both histone and non-histone function regulation in proteins. Deregulation caused by lysine methyltransferases has been identified as the cause of several diseases including cancer as well as both mental and developmental disorders. Identifying lysine methylation sites is a critical step in both early diagnosis and drug design. This study proposes a new Machine Learning method called CNN-Meth for predicting lysine methylation sites using a convolutional neural network (CNN). Our model is trained using evolutionary, structural, and physicochemical-based presentation along with binary encoding. Unlike previous studies, instead of extracting handcrafted features, we use CNN to automatically extract features from different presentations of amino acids to avoid information loss. Automated feature extraction from these representations of amino acids as well as CNN as a classifier have never been used for this problem. Our results demonstrate that CNN-Meth can significantly outperform previous methods for predicting methylation sites. It achieves 96.0%, 85.1%, 96.4%, and 0.65 in terms of Accuracy, Sensitivity, Specificity, and Matthew's Correlation Coefficient (MCC), respectively. CNN-Meth and its source code are publicly available at https://github.com/MLBC-lab/CNN-Meth.

Effective Local and Secondary Protein Structure Prediction by Combining a Neural Network-Based Approach with Extensive Feature Design and Selection without Reliance on Evolutionary Information

Protein structure prediction continues to pose multiple challenges despite outstanding progress that is largely attributable to the use of novel machine learning techniques. One of the widely used representations of local 3D structure-protein blocks (PBs)-can be treated in a similar way to secondary structure classes. Here, we present a new approach for predicting local conformation in terms of PB classes solely from amino acid sequences. We apply the RMSD metric to ensure unambiguous future 3D protein structure recovery. The selection of statistically assessed features is a key component of the proposed method. We suggest that ML input features should be created from the statistically significant predictors that are derived from the amino acids' physicochemical properties and the resolved structures' statistics. The statistical significance of the suggested features was assessed using a stepwise regression analysis that permitted the evaluation of the contribution and statistical significance of each predictor. We used the set of 380 statistically significant predictors as a learning model for the regression neural network that was trained using the PISCES30 dataset. When using the same dataset and metrics for benchmarking, our method outperformed all other methods reported in the literature for the CB513 nonredundant dataset (for the PBs, Q16 = 81.01%, and for the DSSP, Q3 = 85.99% and Q8 = 79.35%).

Machine learning approaches demonstrate that protein structures carry information about their genetic coding

Synonymous codons translate into the same amino acid. Although the identity of synonymous codons is often considered inconsequential to the final protein structure, there is mounting evidence for an association between the two. Our study examined this association using regression and classification models, finding that codon sequences predict protein backbone dihedral angles with a lower error than amino acid sequences, and that models trained with true dihedral angles have better classification of synonymous codons given structural information than models trained with random dihedral angles. Using this classification approach, we investigated local codon-codon dependencies and tested whether synonymous codon identity can be predicted more accurately from codon context than amino acid context alone, and most specifically which codon context position carries the most predictive power.

Accurate prediction of protein torsion angles using evolutionary signatures and recurrent neural network

The amino acid sequence of a protein contains all the necessary information to specify its shape, which dictates its biological activities. However, it is challenging and expensive to experimentally determine the three-dimensional structure of proteins. The backbone torsion angles play a critical role in protein structure prediction, and accurately predicting the angles can considerably advance the tertiary structure prediction by accelerating efficient sampling of the large conformational space for low energy structures. Here we first time propose evolutionary signatures computed from protein sequence profiles, and a novel recurrent architecture, termed ESIDEN, that adopts a straightforward architecture of recurrent neural networks with a small number of learnable parameters. The ESIDEN can capture efficient information from both the classic and new features benefiting from different recurrent architectures in processing information. On the other hand, compared to widely used classic features, the new features, especially the Ramachandran basin potential, provide statistical and evolutionary information to improve prediction accuracy. On four widely used benchmark datasets, the ESIDEN significantly improves the accuracy in predicting the torsion angles by comparison to the best-so-far methods. As demonstrated in the present study, the predicted angles can be used as structural constraints to accurately infer protein tertiary structures. Moreover, the proposed features would pave the way to improve machine learning-based methods in protein folding and structure prediction, as well as function prediction. The source code and data are available at the website https://kornmann.bioch.ox.ac.uk/leri/resources/download.html .

Single-sequence and profile-based prediction of RNA solvent accessibility using dilated convolutional neural network

MOTIVATION

RNA solvent accessibility, similar to protein solvent accessibility, reflects the structural regions that are accessible to solvents or other functional biomolecules, and plays an important role for structural and functional characterization. Unlike protein solvent accessibility, only a few tools are available for predicting RNA solvent accessibility despite the fact that millions of RNA transcripts have unknown structures and functions. Also, these tools have limited accuracy. Here, we have developed RNAsnap2 that uses a dilated convolutional neural network with a new feature, based on predicted base-pairing probabilities from LinearPartition.

RESULTS

Using the same training set from the recent predictor RNAsol, RNAsnap2 provides an 11% improvement in median Pearson Correlation Coefficient (PCC) and 9% improvement in mean absolute errors for the same test set of 45 RNA chains. A larger improvement (22% in median PCC) is observed for 31 newly deposited RNA chains that are non-redundant and independent from the training and the test sets. A single-sequence version of RNAsnap2 (i.e. without using sequence profiles generated from homology search by Infernal) has achieved comparable performance to the profile-based RNAsol. In addition, RNAsnap2 has achieved comparable performance for protein-bound and protein-free RNAs. Both RNAsnap2 and RNAsnap2 (SingleSeq) are expected to be useful for searching structural signatures and locating functional regions of non-coding RNAs.

AVAILABILITY AND IMPLEMENTATION

Standalone-versions of RNAsnap2 and RNAsnap2 (SingleSeq) are available at https://github.com/jaswindersingh2/RNAsnap2. Direct prediction can also be made at https://sparks-lab.org/server/rnasnap2. The datasets used in this research can also be downloaded from the GITHUB and the webserver mentioned above.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

PupStruct: Prediction of Pupylated Lysine Residues Using Structural Properties of Amino Acids

Post-translational modification (PTM) is a critical biological reaction which adds to the diversification of the proteome. With numerous known modifications being studied, pupylation has gained focus in the scientific community due to its significant role in regulating biological processes. The traditional experimental practice to detect pupylation sites proved to be expensive and requires a lot of time and resources. Thus, there have been many computational predictors developed to challenge this issue. However, performance is still limited. In this study, we propose another computational method, named PupStruct, which uses the structural information of amino acids with a radial basis kernel function Support Vector Machine (SVM) to predict pupylated lysine residues. We compared PupStruct with three state-of-the-art predictors from the literature where PupStruct has validated a significant improvement in performance over them with statistical metrics such as sensitivity (0.9234), specificity (0.9359), accuracy (0.9296), precision (0.9349), and Mathew’s correlation coefficient (0.8616) on a benchmark dataset.

Enhancing protein backbone angle prediction by using simpler models of deep neural networks

Protein structure prediction is a grand challenge. Prediction of protein structures via the representations using backbone dihedral angles has recently achieved significant progress along with the on-going surge of deep neural network (DNN) research in general. However, we observe that in the protein backbone angle prediction research, there is an overall trend to employ more and more complex neural networks and then to throw more and more features to the neural networks. While more features might add more predictive power to the neural network, we argue that redundant features could rather clutter the scenario and more complex neural networks then just could counterbalance the noise. From artificial intelligence and machine learning perspectives, problem representations and solution approaches do mutually interact and thus affect performance. We also argue that comparatively simpler predictors can more easily be reconstructed than the more complex ones. With these arguments in mind, we present a deep learning method named Simpler Angle Predictor (SAP) to train simpler DNN models that enhance protein backbone angle prediction. We then empirically show that SAP significantly outperforms existing state-of-the-art methods on well-known benchmark datasets: for some types of angles, the differences are above 3 in mean absolute error (MAE). The SAP program along with its data is available from the website https://gitlab.com/mahnewton/sap.

Investigation of machine learning techniques on proteomics: A comprehensive survey

Proteomics is the extensive investigation of proteins which has empowered the recognizable proof of consistently expanding quantities of protein. Proteins are necessary part of living life form, with numerous capacities. The proteome is the complete arrangement of proteins that are created or altered by a life form or framework of the organism. Proteome fluctuates with time and unambiguous prerequisites, or stresses, that a cell or organism experiences. Proteomics is an interdisciplinary area that has derived from the hereditary data of different genome ventures. Much proteomics information is gathered with the assistance of high throughput techniques, for example, mass spectrometry and microarray. It would regularly take weeks or months to analyze the information and perform examinations by hand. Therefore, scholars and scientific experts are teaming up with computer science researchers and mathematicians to make projects and pipeline to computationally examine the protein information. Utilizing bioinformatics procedures, scientists are prepared to do quicker investigation and protein information storing. The goal of this paper is to brief about the review of machine learning procedures and its application in the field of proteomics.

EvolStruct-Phogly: incorporating structural properties and evolutionary information from profile bigrams for the phosphoglycerylation prediction

Background

Post-translational modification (PTM), which is a biological process, tends to modify proteome that leads to changes in normal cell biology and pathogenesis. In the recent times, there has been many reported PTMs. Out of the many modifications, phosphoglycerylation has become particularly the subject of interest. The experimental procedure for identification of phosphoglycerylated residues continues to be an expensive, inefficient and time-consuming effort, even with a large number of proteins that are sequenced in the post-genomic period. Computational methods are therefore being anticipated in order to effectively predict phosphoglycerylated lysines. Even though there are predictors available, the ability to detect phosphoglycerylated lysine residues still remains inadequate.

Results

We have introduced a new predictor in this paper named EvolStruct-Phogly that uses structural and evolutionary information relating to amino acids to predict phosphoglycerylated lysine residues. Benchmarked data is employed containing experimentally identified phosphoglycerylated and non-phosphoglycerylated lysines. We have then extracted the three structural information which are accessible surface area of amino acids, backbone torsion angles, amino acid’s local structure conformations and profile bigrams of position-specific scoring matrices.

Conclusion

EvolStruct-Phogly showed a noteworthy improvement in regards to the performance when compared with the previous predictors. The performance metrics obtained are as follows: sensitivity 0.7744, specificity 0.8533, precision 0.7368, accuracy 0.8275, and Mathews correlation coefficient of 0.6242. The software package and data of this work can be obtained from https://github.com/abelavit/EvolStruct-Phogly or www.alok-ai-lab.com

GlyStruct: glycation prediction using structural properties of amino acid residues

Background

Glycation is a one of the post-translational modifications (PTM) where sugar molecules and residues in protein sequences are covalently bonded. It has become one of the clinically important PTM in recent times attributed to many chronic and age related complications. Being a non-enzymatic reaction, it is a great challenge when it comes to its prediction due to the lack of significant bias in the sequence motifs.

Results

We developed a classifier, GlyStruct based on support vector machine, to predict glycated and non-glycated lysine residues using structural properties of amino acid residues. The features used were secondary structure, accessible surface area and the local backbone torsion angles. For this work, a benchmark dataset was extracted containing 235 glycated and 303 non-glycated lysine residues. GlyStruct demonstrated improved performance of approximately 10% in comparison to benchmark method of Gly-PseAAC. The performance for GlyStruct on the metrics, sensitivity, specificity, accuracy and Mathew’s correlation coefficient were 0.7013, 0.7989, 0.7562, and 0.5065, respectively for 10-fold cross-validation.

Conclusion

Glycation has emerged to be one of the clinically important PTM of proteins in recent times. Therefore, the development of computational tools become necessary to predict glycation, which could help medical professionals administer drugs and manage patients more effectively. The proposed predictor manages to classify glycated and non-glycated lysine residues with promising results consistently on various cross-validation schemes and outperforms other state of the art methods.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2547-x) contains supplementary material, which is available to authorized users.

PhoglyStruct: Prediction of phosphoglycerylated lysine residues using structural properties of amino acids

The biological process known as post-translational modification (PTM) contributes to diversifying the proteome hence affecting many aspects of normal cell biology and pathogenesis. There have been many recently reported PTMs, but lysine phosphoglycerylation has emerged as the most recent subject of interest. Despite a large number of proteins being sequenced, the experimental method for detection of phosphoglycerylated residues remains an expensive, time-consuming and inefficient endeavor in the post-genomic era. Instead, the computational methods are being proposed for accurately predicting phosphoglycerylated lysines. Though a number of predictors are available, performance in detecting phosphoglycerylated lysine residues is still limited. In this paper, we propose a new predictor called PhoglyStruct that utilizes structural information of amino acids alongside a multilayer perceptron classifier for predicting phosphoglycerylated and non-phosphoglycerylated lysine residues. For the experiment, we located phosphoglycerylated and non-phosphoglycerylated lysines in our employed benchmark. We then derived and integrated properties such as accessible surface area, backbone torsion angles, and local structure conformations. PhoglyStruct showed significant improvement in the ability to detect phosphoglycerylated residues from non-phosphoglycerylated ones when compared to previous predictors. The sensitivity, specificity, accuracy, Mathews correlation coefficient and AUC were 0.8542, 0.7597, 0.7834, 0.5468 and 0.8077, respectively. The data and Matlab/Octave software packages are available at https://github.com/abelavit/PhoglyStruct .

Molecular characterization of the apoptosis-related SH3RF1 and SH3RF2 genes and their association with exercise performance in Arabian horses

BACKGROUND

Apoptosis plays an important role in the regulation of healthy tissue growth and development as well as in controlling the maintenance of homeostasis in exercising muscles. During an intensive physical effort, the regulation of cell death by apoptosis results in the replacement of unaccustomed muscle cells by new cells that are better suited to exercise. The aim of this study was to determine the expression of two genes (SH3FR1 and SH3RF2) that control apoptosis in muscle tissues during training periods characterized by different intensities. The gene expression levels were estimated using real-time PCR method in skeletal muscle biopsies collected from 15 Arabian horses (untrained, after an intense gallop phase, and at the end of the racing season). An association study was performed on 250 Arabian horses to assess the effect of the SH3RF2:c.796 T > C (p.Ser266Pro) variant on race performance traits in flat gallop-racing.

RESULTS

A gene expression analysis confirmed a significant decrease (p < 0.01) in the anti-apoptotic SH3RF2 (POSHER) gene during training periods that differed in intensity. The highest SH3RF2 expression level was detected in the muscles of untrained horses, whereas the lowest expression was identified at the end of the racing season in horses that were fully adapted to the exercise. A non-significant decrease in SH3RF1 gene expression following the training periods was observed. Moreover, a serine substitution by proline at amino acid position 266 (CC genotype) was negatively associated with the probability of winning races, the number of races in which a horse occurred and the financial value of the prizes. Horses with the TT genotype achieved the highest financial benefits, both for total winnings and for winnings per race in which the horses participated.

CONCLUSIONS

The present study showed the supposed regulation mechanism of exercise-induced apoptosis in horses at the molecular level. The identified SH3RF2: c.796 T > C missense variant was associated with selected racing performance traits, which is important information during the evaluation of horses' exercise predisposition. The association results and frequencies of the CT and TT genotypes suggest the possibility of using SH3RF2 variant in selection to improve the racing performance of Arabian horses.

Protein Solvent-Accessibility Prediction by a Stacked Deep Bidirectional Recurrent Neural Network

Residue solvent accessibility is closely related to the spatial arrangement and packing of residues. Predicting the solvent accessibility of a protein is an important step to understand its structure and function. In this work, we present a deep learning method to predict residue solvent accessibility, which is based on a stacked deep bidirectional recurrent neural network applied to sequence profiles. To capture more long-range sequence information, a merging operator was proposed when bidirectional information from hidden nodes was merged for outputs. Three types of merging operators were used in our improved model, with a long short-term memory network performing as a hidden computing node. The trained database was constructed from 7361 proteins extracted from the PISCES server using a cut-off of 25% sequence identity. Sequence-derived features including position-specific scoring matrix, physical properties, physicochemical characteristics, conservation score and protein coding were used to represent a residue. Using this method, predictive values of continuous relative solvent-accessible area were obtained, and then, these values were transformed into binary states with predefined thresholds. Our experimental results showed that our deep learning method improved prediction quality relative to current methods, with mean absolute error and Pearson’s correlation coefficient values of 8.8% and 74.8%, respectively, on the CB502 dataset and 8.2% and 78%, respectively, on the Manesh215 dataset.

Prediction of Protein Backbone Torsion Angles Using Deep Residual Inception Neural Networks

Prediction of protein backbone torsion angles (Psi and Phi) can provide important information for protein structure prediction and sequence alignment. Existing methods for Psi-Phi angle prediction have significant room for improvement. In this paper, a new deep residual inception network architecture, called DeepRIN, is proposed for the prediction of Psi-Phi angles. The input to DeepRIN is a feature matrix representing a composition of physico-chemical properties of amino acids, a 20-dimensional position-specific substitution matrix (PSSM) generated by PSI-BLAST, a 30-dimensional hidden Markov Model sequence profile generated by HHBlits, and predicted eight-state secondary structure features. DeepRIN is designed based on inception networks and residual networks that have performed well on image classification and text recognition. The architecture of DeepRIN enables effective encoding of local and global interatcions between amino acids in a protein sequence to achieve accruacte prediction. Extensive experimental results show that DeepRIN outperformed the best existing tools significantly. Compared to the recently released state-of-the-art tool, SPIDER3, DeepRIN reduced the Psi angle prediction error by more than 5 degrees and the Phi angle prediction error by more than 2 degrees on average. The executable tool of DeepRIN is available for download at http://dslsrv8.cs.missouri.edu/~cf797/MUFoldAngle/.

Success: evolutionary and structural properties of amino acids prove effective for succinylation site prediction

BACKGROUND

Post-translational modification is considered an important biological mechanism with critical impact on the diversification of the proteome. Although a long list of such modifications has been studied, succinylation of lysine residues has recently attracted the interest of the scientific community. The experimental detection of succinylation sites is an expensive process, which consumes a lot of time and resources. Therefore, computational predictors of this covalent modification have emerged as a last resort to tackling lysine succinylation.

RESULTS

In this paper, we propose a novel computational predictor called 'Success', which efficiently uses the structural and evolutionary information of amino acids for predicting succinylation sites. To do this, each lysine was described as a vector that combined the above information of surrounding amino acids. We then designed a support vector machine with a radial basis function kernel for discriminating between succinylated and non-succinylated residues. We finally compared the Success predictor with three state-of-the-art predictors in the literature. As a result, our proposed predictor showed a significant improvement over the compared predictors in statistical metrics, such as sensitivity (0.866), accuracy (0.838) and Matthews correlation coefficient (0.677) on a benchmark dataset.

CONCLUSIONS

The proposed predictor effectively uses the structural and evolutionary information of the amino acids surrounding a lysine. The bigram feature extraction approach, while retaining the same number of features, facilitates a better description of lysines. A support vector machine with a radial basis function kernel was used to discriminate between modified and unmodified lysines. The aforementioned aspects make the Success predictor outperform three state-of-the-art predictors in succinylation detection.

Gaussian network model can be enhanced by combining solvent accessibility in proteins

Gaussian network model (GNM), regarded as the simplest and most representative coarse-grained model, has been widely adopted to analyze and reveal protein dynamics and functions. Designing a variation of the classical GNM, by defining a new Kirchhoff matrix, is the way to improve the residue flexibility modeling. We combined information arising from local relative solvent accessibility (RSA) between two residues into the Kirchhoff matrix of the parameter-free GNM. The undetermined parameters in the new Kirchhoff matrix were estimated by using particle swarm optimization. The usage of RSA was motivated by the fact that our previous work using RSA based linear regression model resulted out higher prediction quality of the residue flexibility when compared with the classical GNM and the parameter free GNM. Computational experiments, conducted based on one training dataset, two independent datasets and one additional small set derived by molecular dynamics simulations, demonstrated that the average correlation coefficients of the proposed RSA based parameter-free GNM, called RpfGNM, were significantly increased when compared with the parameter-free GNM. Our empirical results indicated that a variation of the classical GNMs by combining other protein structural properties is an attractive way to improve the quality of flexibility modeling.

SucStruct: Prediction of succinylated lysine residues by using structural properties of amino acids

Post-Translational Modification (PTM) is a biological reaction which contributes to diversify the proteome. Despite many modifications with important roles in cellular activity, lysine succinylation has recently emerged as an important PTM mark. It alters the chemical structure of lysines, leading to remarkable changes in the structure and function of proteins. In contrast to the huge amount of proteins being sequenced in the post-genome era, the experimental detection of succinylated residues remains expensive, inefficient and time-consuming. Therefore, the development of computational tools for accurately predicting succinylated lysines is an urgent necessity. To date, several approaches have been proposed but their sensitivity has been reportedly poor. In this paper, we propose an approach that utilizes structural features of amino acids to improve lysine succinylation prediction. Succinylated and non-succinylated lysines were first retrieved from 670 proteins and characteristics such as accessible surface area, backbone torsion angles and local structure conformations were incorporated. We used the k-nearest neighbors cleaning treatment for dealing with class imbalance and designed a pruned decision tree for classification. Our predictor, referred to as SucStruct (Succinylation using Structural features), proved to significantly improve performance when compared to previous predictors, with sensitivity, accuracy and Mathew's correlation coefficient equal to 0.7334-0.7946, 0.7444-0.7608 and 0.4884-0.5240, respectively.

Improving prediction of burial state of residues by exploiting correlation among residues

Background

Residues in a protein might be buried inside or exposed to the solvent surrounding the protein. The buried residues usually form hydrophobic cores to maintain the structural integrity of proteins while the exposed residues are tightly related to protein functions. Thus, the accurate prediction of solvent accessibility of residues will greatly facilitate our understanding of both structure and functionalities of proteins. Most of the state-of-the-art prediction approaches consider the burial state of each residue independently, thus neglecting the correlations among residues.

Results

In this study, we present a high-order conditional random field model that considers burial states of all residues in a protein simultaneously. Our approach exploits not only the correlation among adjacent residues but also the correlation among long-range residues. Experimental results showed that by exploiting the correlation among residues, our approach outperformed the state-of-the-art approaches in prediction accuracy. In-depth case studies also showed that by using the high-order statistical model, the errors committed by the bidirectional recurrent neural network and chain conditional random field models were successfully corrected.

Conclusions

Our methods enable the accurate prediction of residue burial states, which should greatly facilitate protein structure prediction and evaluation.

Fast and Accurate Accessible Surface Area Prediction Without a Sequence Profile

A fast accessible surface area (ASA) predictor is presented. In this new approach no residue mutation profiles generated by multiple sequence alignments are used as inputs. Instead, we use only single sequence information and global features such as single-residue and two-residue compositions of the chain. The resulting predictor is both highly more efficient than sequence alignment based predictors and of comparable accuracy to them. Introduction of the global inputs significantly helps achieve this comparable accuracy. The predictor, termed ASAquick, is found to perform similarly well for so-called easy and hard cases indicating generalizability and possible usability for de-novo protein structure prediction. The source code and a Linux executables for ASAquick are available from Research and Information Systems at http://mamiris.com and from the Battelle Center for Mathematical Medicine at http://mathmed.org .

SPIDER2: A Package to Predict Secondary Structure, Accessible Surface Area, and Main-Chain Torsional Angles by Deep Neural Networks

Predicting one-dimensional structure properties has played an important role to improve prediction of protein three-dimensional structures and functions. The most commonly predicted properties are secondary structure and accessible surface area (ASA) representing local and nonlocal structural characteristics, respectively. Secondary structure prediction is further complemented by prediction of continuous main-chain torsional angles. Here we describe a newly developed method SPIDER2 that utilizes three iterations of deep learning neural networks to improve the prediction accuracy of several structural properties simultaneously. For an independent test set of 1199 proteins SPIDER2 achieves 82 % accuracy for secondary structure prediction, 0.76 for the correlation coefficient between predicted and actual solvent accessible surface area, 19° and 30° for mean absolute errors of backbone φ and ψ angles, respectively, and 8° and 32° for mean absolute errors of Cα-based θ and τ angles, respectively. The method provides state-of-the-art, all-in-one accurate prediction of local structure and solvent accessible surface area. The method is implemented, as a webserver along with a standalone package that are available in our website: http://sparks-lab.org .

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 .

Backbone Dihedral Angle Prediction

More than two decades of research have enabled dihedral angle predictions at an accuracy that makes them an interesting alternative or supplement to secondary structure prediction that provides detailed local structure information for every residue of a protein. The evolution of dihedral angle prediction methods is closely linked to advancements in machine learning and other relevant technologies. Consequently recent improvements in large-scale training of deep neural networks have led to the best method currently available, which achieves a mean absolute error of 19° for phi, and 30° for psi. This performance opens interesting perspectives for the application of dihedral angle prediction in the comparison, prediction, and design of protein structures.

Molecular Dynamics Driven Design of pH-Stabilized Mutants of MNEI, a Sweet Protein

MNEI is a single chain derivative of monellin, a plant protein that can interact with the human sweet taste receptor, being therefore perceived as sweet. This unusual physiological activity makes MNEI a potential template for the design of new sugar replacers for the food and beverage industry. Unfortunately, applications of MNEI have been so far limited by its intrinsic sensitivity to some pH and temperature conditions, which could occur in industrial processes. Changes in physical parameters can, in fact, lead to irreversible protein denaturation, as well as aggregation and precipitation. It has been previously shown that the correlation between pH and stability in MNEI derives from the presence of a single glutamic residue in a hydrophobic pocket of the protein. We have used molecular dynamics to study the consequences, at the atomic level, of the protonation state of such residue and have identified the network of intramolecular interactions responsible for MNEI stability at acidic pH. Based on this information, we have designed a pH-independent, stabilized mutant of MNEI and confirmed its increased stability by both molecular modeling and experimental techniques.

Highly accurate sequence-based prediction of half-sphere exposures of amino acid residues in proteins

Motivation: Solvent exposure of amino acid residues of proteins plays an important role in understanding and predicting protein structure, function and interactions. Solvent exposure can be characterized by several measures including solvent accessible surface area (ASA), residue depth (RD) and contact numbers (CN). More recently, an orientation-dependent contact number called half-sphere exposure (HSE) was introduced by separating the contacts within upper and down half spheres defined according to the Cα-Cβ (HSEβ) vector or neighboring Cα-Cα vectors (HSEα). HSEα calculated from protein structures was found to better describe the solvent exposure over ASA, CN and RD in many applications. Thus, a sequence-based prediction is desirable, as most proteins do not have experimentally determined structures. To our best knowledge, there is no method to predict HSEα and only one method to predict HSEβ.

Results: This study developed a novel method for predicting both HSEα and HSEβ (SPIDER-HSE) that achieved a consistent performance for 10-fold cross validation and two independent tests. The correlation coefficients between predicted and measured HSEβ (0.73 for upper sphere, 0.69 for down sphere and 0.76 for contact numbers) for the independent test set of 1199 proteins are significantly higher than existing methods. Moreover, predicted HSEα has a higher correlation coefficient (0.46) to the stability change by residue mutants than predicted HSEβ (0.37) and ASA (0.43). The results, together with its easy Cα-atom-based calculation, highlight the potential usefulness of predicted HSEα for protein structure prediction and refinement as well as function prediction.

Availability and implementation: The method is available at http://sparks-lab.org.

Contact: yuedong.yang@griffith.edu.au or yaoqi.zhou@griffith.edu.au

Supplementary information: Supplementary data are available at Bioinformatics online.

Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning

Direct prediction of protein structure from sequence is a challenging problem. An effective approach is to break it up into independent sub-problems. These sub-problems such as prediction of protein secondary structure can then be solved independently. In a previous study, we found that an iterative use of predicted secondary structure and backbone torsion angles can further improve secondary structure and torsion angle prediction. In this study, we expand the iterative features to include solvent accessible surface area and backbone angles and dihedrals based on Cα atoms. By using a deep learning neural network in three iterations, we achieved 82% accuracy for secondary structure prediction, 0.76 for the correlation coefficient between predicted and actual solvent accessible surface area, 19° and 30° for mean absolute errors of backbone φ and ψ angles, respectively, and 8° and 32° for mean absolute errors of Cα-based θ and τ angles, respectively, for an independent test dataset of 1199 proteins. The accuracy of the method is slightly lower for 72 CASP 11 targets but much higher than those of model structures from current state-of-the-art techniques. This suggests the potentially beneficial use of these predicted properties for model assessment and ranking.

GENN: a GEneral Neural Network for learning tabulated data with examples from protein structure prediction

We present a GEneral Neural Network (GENN) for learning trends from existing data and making predictions of unknown information. The main novelty of GENN is in its generality, simplicity of use, and its specific handling of windowed input/output. Its main strength is its efficient handling of the input data, enabling learning from large datasets. GENN is built on a two-layered neural network and has the option to use separate inputs-output pairs or window-based data using data structures to efficiently represent input-output pairs. The program was tested on predicting the accessible surface area of globular proteins, scoring proteins according to similarity to native, predicting protein disorder, and has performed remarkably well. In this paper we describe the program and its use. Specifically, we give as an example the construction of a similarity to native protein scoring function that was constructed using GENN. The source code and Linux executables for GENN are available from Research and Information Systems at http://mamiris.com and from the Battelle Center for Mathematical Medicine at http://mathmed.org. Bugs and problems with the GENN program should be reported to EF.

Computational peptide vaccinology

Immunoinformatics focuses on modeling immune responses for better understanding of the immune system and in many cases for proposing agents able to modify the immune system. The most classical of these agents are vaccines derived from living organisms such as smallpox or polio. More modern vaccines comprise recombinant proteins, protein domains, and in some cases peptides. Generating a vaccine from peptides however requires technologies and concepts very different from classical vaccinology. Immunoinformatics therefore provides the computational tools to propose peptides suitable for formulation into vaccines. This chapter introduces the essential biological concepts affecting design and efficacy of peptide vaccines and discusses current methods and workflows applied to design successful peptide vaccines using computers.

Accurate single-sequence prediction of solvent accessible surface area using local and global features

We present a new approach for predicting the Accessible Surface Area (ASA) using a General Neural Network (GENN). The novelty of the new approach lies in not using residue mutation profiles generated by multiple sequence alignments as descriptive inputs. Instead we use solely sequential window information and global features such as single-residue and two-residue compositions of the chain. The resulting predictor is both highly more efficient than sequence alignment-based predictors and of comparable accuracy to them. Introduction of the global inputs significantly helps achieve this comparable accuracy. The predictor, termed ASAquick, is tested on predicting the ASA of globular proteins and found to perform similarly well for so-called easy and hard cases indicating generalizability and possible usability for de-novo protein structure prediction. The source code and a Linux executables for GENN and ASAquick are available from Research and Information Systems at http://mamiris.com, from the SPARKS Lab at http://sparks-lab.org, and from the Battelle Center for Mathematical Medicine at http://mathmed.org.

Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network

Because a nearly constant distance between two neighbouring Cα atoms, local backbone structure of proteins can be represented accurately by the angle between C(αi-1)-C(αi)-C(αi+1) (θ) and a dihedral angle rotated about the C(αi)-C(αi+1) bond (τ). θ and τ angles, as the representative of structural properties of three to four amino-acid residues, offer a description of backbone conformations that is complementary to φ and ψ angles (single residue) and secondary structures (>3 residues). Here, we report the first machine-learning technique for sequence-based prediction of θ and τ angles. Predicted angles based on an independent test have a mean absolute error of 9° for θ and 34° for τ with a distribution on the θ-τ plane close to that of native values. The average root-mean-square distance of 10-residue fragment structures constructed from predicted θ and τ angles is only 1.9Å from their corresponding native structures. Predicted θ and τ angles are expected to be complementary to predicted ϕ and ψ angles and secondary structures for using in model validation and template-based as well as template-free structure prediction. The deep neural network learning technique is available as an on-line server called Structural Property prediction with Integrated DEep neuRal network (SPIDER) at http://sparks-lab.org.

Evaluation of protein dihedral angle prediction methods

Tertiary structure prediction of a protein from its amino acid sequence is one of the major challenges in the field of bioinformatics. Hierarchical approach is one of the persuasive techniques used for predicting protein tertiary structure, especially in the absence of homologous protein structures. In hierarchical approach, intermediate states are predicted like secondary structure, dihedral angles, C^α-C^α distance bounds, etc. These intermediate states are used to restraint the protein backbone and assist its correct folding. In the recent years, several methods have been developed for predicting dihedral angles of a protein, but it is difficult to conclude which method is better than others. In this study, we benchmarked the performance of dihedral prediction methods ANGLOR and SPINE X on various datasets, including independent datasets. TANGLE dihedral prediction method was not benchmarked (due to unavailability of its standalone) and was compared with SPINE X and ANGLOR on only ANGLOR dataset on which TANGLE has reported its results. It was observed that SPINE X performed better than ANGLOR and TANGLE, especially in case of prediction of dihedral angles of glycine and proline residues. The analysis suggested that angle shifting was the foremost reason of better performance of SPINE X. We further evaluated the performance of the methods on independent ccPDB30 dataset and observed that SPINE X performed better than ANGLOR.

QA-RecombineIt: a server for quality assessment and recombination of protein models

QA-RecombineIt provides a web interface to assess the quality of protein 3D structure models and to improve the accuracy of models by merging fragments of multiple input models. QA-RecombineIt has been developed for protein modelers who are working on difficult problems, have a set of different homology models and/or de novo models (from methods such as I-TASSER or ROSETTA) and would like to obtain one consensus model that incorporates the best parts into one structure that is internally coherent. An advanced mode is also available, in which one can modify the operation of the fragment recombination algorithm by manually identifying individual fragments or entire models to recombine. Our method produces up to 100 models that are expected to be on the average more accurate than the starting models. Therefore, our server may be useful for crystallographic protein structure determination, where protein models are used for Molecular Replacement to solve the phase problem. To address the latter possibility, a special feature was added to the QA-RecombineIt server. The QA-RecombineIt server can be freely accessed at http://iimcb.genesilico.pl/qarecombineit/.

DomHR: accurately identifying domain boundaries in proteins using a hinge region strategy

Motivation

The precise prediction of protein domains, which are the structural, functional and evolutionary units of proteins, has been a research focus in recent years. Although many methods have been presented for predicting protein domains and boundaries, the accuracy of predictions could be improved.

Results

In this study we present a novel approach, DomHR, which is an accurate predictor of protein domain boundaries based on a creative hinge region strategy. A hinge region was defined as a segment of amino acids that covers part of a domain region and a boundary region. We developed a strategy to construct profiles of domain-hinge-boundary (DHB) features generated by sequence-domain/hinge/boundary alignment against a database of known domain structures. The DHB features had three elements: normalized domain, hinge, and boundary probabilities. The DHB features were used as input to identify domain boundaries in a sequence. DomHR used a nonredundant dataset as the training set, the DHB and predicted shape string as features, and a conditional random field as the classification algorithm. In predicted hinge regions, a residue was determined to be a domain or a boundary according to a decision threshold. After decision thresholds were optimized, DomHR was evaluated by cross-validation, large-scale prediction, independent test and CASP (Critical Assessment of Techniques for Protein Structure Prediction) tests. All results confirmed that DomHR outperformed other well-established, publicly available domain boundary predictors for prediction accuracy.

Availability

The DomHR is available at http://cal.tongji.edu.cn/domain/.

TANGLE: two-level support vector regression approach for protein backbone torsion angle prediction from primary sequences

Protein backbone torsion angles (Phi) and (Psi) involve two rotation angles rotating around the C_α-N bond (Phi) and the C_α-C bond (Psi). Due to the planarity of the linked rigid peptide bonds, these two angles can essentially determine the backbone geometry of proteins. Accordingly, the accurate prediction of protein backbone torsion angle from sequence information can assist the prediction of protein structures. In this study, we develop a new approach called TANGLE (Torsion ANGLE predictor) to predict the protein backbone torsion angles from amino acid sequences. TANGLE uses a two-level support vector regression approach to perform real-value torsion angle prediction using a variety of features derived from amino acid sequences, including the evolutionary profiles in the form of position-specific scoring matrices, predicted secondary structure, solvent accessibility and natively disordered region as well as other global sequence features. When evaluated based on a large benchmark dataset of 1,526 non-homologous proteins, the mean absolute errors (MAEs) of the Phi and Psi angle prediction are 27.8° and 44.6°, respectively, which are 1% and 3% respectively lower than that using one of the state-of-the-art prediction tools ANGLOR. Moreover, the prediction of TANGLE is significantly better than a random predictor that was built on the amino acid-specific basis, with the p-value<1.46e-147 and 7.97e-150, respectively by the Wilcoxon signed rank test. As a complementary approach to the current torsion angle prediction algorithms, TANGLE should prove useful in predicting protein structural properties and assisting protein fold recognition by applying the predicted torsion angles as useful restraints. TANGLE is freely accessible at http://sunflower.kuicr.kyoto-u.ac.jp/~sjn/TANGLE/.

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/

A sampling-based method for ranking protein structural models by integrating multiple scores and features

One of the major challenges in protein tertiary structure prediction is structure quality assessment. In many cases, protein structure prediction tools generate good structural models, but fail to select the best models from a huge number of candidates as the final output. In this study, we developed a sampling-based machine-learning method to rank protein structural models by integrating multiple scores and features. First, features such as predicted secondary structure, solvent accessibility and residue-residue contact information are integrated by two Radial Basis Function (RBF) models trained from different datasets. Then, the two RBF scores and five selected scoring functions developed by others, i.e., Opus-CA, Opus-PSP, DFIRE, RAPDF, and Cheng Score are synthesized by a sampling method. At last, another integrated RBF model ranks the structural models according to the features of sampling distribution. We tested the proposed method by using two different datasets, including the CASP server prediction models of all CASP8 targets and a set of models generated by our in-house software MUFOLD. The test result shows that our method outperforms any individual scoring function on both best model selection, and overall correlation between the predicted ranking and the actual ranking of structural quality.

In-silico prediction of disorder content using hybrid sequence representation

Background

Intrinsically disordered proteins play important roles in various cellular activities and their prevalence was implicated in a number of human diseases. The knowledge of the content of the intrinsic disorder in proteins is useful for a variety of studies including estimation of the abundance of disorder in protein families, classes, and complete proteomes, and for the analysis of disorder-related protein functions. The above investigations currently utilize the disorder content derived from the per-residue disorder predictions. We show that these predictions may over-or under-predict the overall amount of disorder, which motivates development of novel tools for direct and accurate sequence-based prediction of the disorder content.

Results

We hypothesize that sequence-level aggregation of input information may provide more accurate content prediction when compared with the content extracted from the local window-based residue-level disorder predictors. We propose a novel predictor, DisCon, that takes advantage of a small set of 29 custom-designed descriptors that aggregate and hybridize information concerning sequence, evolutionary profiles, and predicted secondary structure, solvent accessibility, flexibility, and annotation of globular domains. Using these descriptors and a ridge regression model, DisCon predicts the content with low, 0.05, mean squared error and high, 0.68, Pearson correlation. This is a statistically significant improvement over the content computed from outputs of ten modern disorder predictors on a test dataset with proteins that share low sequence identity with the training sequences. The proposed predictive model is analyzed to discuss factors related to the prediction of the disorder content.

Conclusions

DisCon is a high-quality alternative for high-throughput annotation of the disorder content. We also empirically demonstrate that the DisCon's predictions can be used to improve binary annotations of the disordered residues from the real-value disorder propensities generated by current residue-level disorder predictors. The web server that implements the DisCon is available at http://biomine.ece.ualberta.ca/DisCon/.

Fluctuations of backbone torsion angles obtained from NMR-determined structures and their prediction

Protein molecules exhibit varying degrees of flexibility throughout their three-dimensional structures. Protein structural flexibility is often characterized by fluctuations in the Cartesian coordinate space. On the other hand, the protein backbone can be mostly defined by two torsion angles ϕ and ψ only. We introduce a new flexibility descriptor, backbone torsion-angle fluctuation derived from the variation of backbone torsion angles from different NMR models. The torsion-angle fluctuations correlate with mean-squared spatial fluctuations derived from the same collection of NMR models. We developed a neural-network based real-value predictor based on sequence information only. The predictor achieved ten-fold cross-validated correlation coefficients of 0.59 and 0.60, and mean absolute errors of 22.7° and 24.3° for the angle fluctuation of ϕ and ψ, respectively. This predictor is expected to be useful for function prediction and protein structure prediction when predicted torsion angles are used as restraints. Both sequence- and structure-based prediction of torsion-angle fluctuation will be available at http://sparks.informatics.iupui.edu within the SPINE-X package.

Trends in template/fragment-free protein structure prediction

Predicting the structure of a protein from its amino acid sequence is a long-standing unsolved problem in computational biology. Its solution would be of both fundamental and practical importance as the gap between the number of known sequences and the number of experimentally solved structures widens rapidly. Currently, the most successful approaches are based on fragment/template reassembly. Lacking progress in template-free structure prediction calls for novel ideas and approaches. This article reviews trends in the development of physical and specific knowledge-based energy functions as well as sampling techniques for fragment-free structure prediction. Recent physical- and knowledge-based studies demonstrated that it is possible to sample and predict highly accurate protein structures without borrowing native fragments from known protein structures. These emerging approaches with fully flexible sampling have the potential to move the field forward.

Phospho.ELM: a database of phosphorylation sites--update 2011

The Phospho.ELM resource (http://phospho.elm.eu.org) is a relational database designed to store in vivo and in vitro phosphorylation data extracted from the scientific literature and phosphoproteomic analyses. The resource has been actively developed for more than 7 years and currently comprises 42 574 serine, threonine and tyrosine non-redundant phosphorylation sites. Several new features have been implemented, such as structural disorder/order and accessibility information and a conservation score. Additionally, the conservation of the phosphosites can now be visualized directly on the multiple sequence alignment used for the score calculation. Finally, special emphasis has been put on linking to external resources such as interaction networks and other databases.

Accurate prediction of protein folding rates from sequence and sequence-derived residue flexibility and solvent accessibility

Protein folding rates vary by several orders of magnitude and they depend on the topology of the fold and the size and composition of the sequence. Although recent works show that the rates can be predicted from the sequence, allowing for high-throughput annotations, they consider only the sequence and its predicted secondary structure. We propose a novel sequence-based predictor, PFR-AF, which utilizes solvent accessibility and residue flexibility predicted from the sequence, to improve predictions and provide insights into the folding process. The predictor includes three linear regressions for proteins with two-state, multistate, and unknown (mixed-state) folding kinetics. PFR-AF on average outperforms current methods when tested on three datasets. The proposed approach provides high-quality predictions in the absence of similarity between the predicted and the training sequences. The PFR-AF's predictions are characterized by high (between 0.71 and 0.95, depending on the dataset) correlation and the lowest (between 0.75 and 0.9) mean absolute errors with respect to the experimental rates, as measured using out-of-sample tests. Our models reveal that for the two-state chains inclusion of solvent-exposed Ala may accelerate the folding, while increased content of Ile may reduce the folding speed. We also demonstrate that increased flexibility of coils facilitates faster folding and that proteins with larger content of solvent-exposed strands may fold at a slower pace. The increased flexibility of the solvent-exposed residues is shown to elongate folding, which also holds, with a lower correlation, for buried residues. Two case studies are included to support our findings.

In silico functional profiling of human disease-associated and polymorphic amino acid substitutions

An important challenge in translational bioinformatics is to understand how genetic variation gives rise to molecular changes at the protein level that can precipitate both monogenic and complex disease. To this end, we compiled datasets of human disease-associated amino acid substitutions (AAS) in the contexts of inherited monogenic disease, complex disease, functional polymorphisms with no known disease association, and somatic mutations in cancer, and compared them with respect to predicted functional sites in proteins. Using the sequence homology-based tool SIFT to estimate the proportion of deleterious AAS in each dataset, only complex disease AAS were found to be indistinguishable from neutral polymorphic AAS. Investigation of monogenic disease AAS predicted to be nondeleterious by SIFT were characterized by a significant enrichment for inherited AAS within solvent accessible residues, regions of intrinsic protein disorder, and an association with the loss or gain of various posttranslational modifications. Sites of structural and/or functional interest were therefore surmised to constitute useful additional features with which to identify the molecular disruptions caused by deleterious AAS. A range of bioinformatic tools, designed to predict structural and functional sites in protein sequences, were then employed to demonstrate that intrinsic biases exist in terms of the distribution of different types of human AAS with respect to specific structural, functional and pathological features. Our Web tool, designed to potentiate the functional profiling of novel AAS, has been made available at http://profile.mutdb.org/.

iFC²: an integrated web-server for improved prediction of protein structural class, fold type, and secondary structure content

Several descriptors of protein structure at the sequence and residue levels have been recently proposed. They are widely adopted in the analysis and prediction of structural and functional characteristics of proteins. Numerous in silico methods have been developed for sequence-based prediction of these descriptors. However, many of them do not have a public web-server and only a few integrate multiple descriptors to improve the predictions. We introduce iFC² (integrated prediction of fold, class, and content) server that is the first to integrate three modern predictors of sequence-level descriptors. They concern fold type (PFRES), structural class (SCEC), and secondary structure content (PSSC-core). The server exploits relations between the three descriptors to implement a cross-evaluation procedure that improves over the predictions of the individual methods. The iFC² annotates fold and class predictions as potentially correct/incorrect. When tested on datasets with low-similarity chains, for the fold prediction iFC² labels 82% of the PFRES predictions as correct and the accuracy of these predictions equals 72%. The accuracy of the remaining 28% of the PFRES predictions equals 38%. Similarly, our server assigns correct labels for over 79% of SCEC predictions, which are shown to be 98% accurate, while the remaining SCEC predictions are only 15% accurate. These results are shown to be competitive when contrasted against recent relevant web-servers. Predictions on CASP8 targets show that the content predicted by iFC² is competitive when compared with the content computed from the tertiary structures predicted by three best-performing methods in CASP8. The iFC² server is available at http://biomine.ece.ualberta.ca/1D/1D.html .