Improving the prediction accuracy of residue solvent accessibility and real-value backbone torsion angles of proteins by guided-learning through a two-layer neural network

IGPRED-MultiTask: A Deep Learning Model to Predict Protein Secondary Structure, Torsion Angles and Solvent Accessibility

Protein secondary structure, solvent accessibility and torsion angle predictions are preliminary steps to predict 3D structure of a protein. Deep learning approaches have achieved significant improvements in predicting various features of protein structure. In this study, IGPRED-Multitask, a deep learning model with multi task learning architecture based on deep inception network, graph convolutional network and a bidirectional long short-term memory is proposed. Moreover, hyper-parameters of the model are fine-tuned using Bayesian optimization, which is faster and more effective than grid search. The same benchmark test data sets as in the OPUS-TASS paper including TEST2016, TEST2018, CASP12, CASP13, CASPFM, HARD68, CAMEO93, CAMEO93_HARD, as well as the train and validation sets, are used for fair comparison with the literature. Statistically significant improvements are observed in secondary structure prediction on 4 datasets, in phi angle prediction on 2 datasets and in psi angel prediction on 3 datasets compared to the state-of-the-art methods. For solvent accessibility prediction, TEST2016 and TEST2018 datasets are used only to assess the performance of the proposed model.

Prediction of protein-protein interaction sites in intrinsically disordered proteins

Intrinsically disordered proteins (IDPs) participate in many biological processes by interacting with other proteins, including the regulation of transcription, translation, and the cell cycle. With the increasing amount of disorder sequence data available, it is thus crucial to identify the IDP binding sites for functional annotation of these proteins. Over the decades, many computational approaches have been developed to predict protein-protein binding sites of IDP (IDP-PPIS) based on protein sequence information. Moreover, there are new IDP-PPIS predictors developed every year with the rapid development of artificial intelligence. It is thus necessary to provide an up-to-date overview of these methods in this field. In this paper, we collected 30 representative predictors published recently and summarized the databases, features and algorithms. We described the procedure how the features were generated based on public data and used for the prediction of IDP-PPIS, along with the methods to generate the feature representations. All the predictors were divided into three categories: scoring functions, machine learning-based prediction, and consensus approaches. For each category, we described the details of algorithms and their performances. Hopefully, our manuscript will not only provide a full picture of the status quo of IDP binding prediction, but also a guide for selecting different methods. More importantly, it will shed light on the inspirations for future development trends and principles.

Predicting Protein Conformational Disorder and Disordered Binding Sites

In the last two decades it has become increasingly evident that a large number of proteins adopt either a fully or a partially disordered conformation. Intrinsically disordered proteins are ubiquitous proteins that fulfill essential biological functions while lacking a stable 3D structure. Their conformational heterogeneity is encoded by the amino acid sequence, thereby allowing intrinsically disordered proteins or regions to be recognized based on their sequence properties. The identification of disordered regions facilitates the functional annotation of proteins and is instrumental for delineating boundaries of protein domains amenable to crystallization. This chapter focuses on the methods currently employed for predicting protein disorder and identifying intrinsically disordered binding sites.

A Survey for Predicting ATP Binding Residues of Proteins Using Machine Learning Methods

Protein-ligand interactions are necessary for majority protein functions. Adenosine-5'-triphosphate (ATP) is one such ligand that plays vital role as a coenzyme in providing energy for cellular activities, catalyzing biological reaction and signaling. Knowing ATP binding residues of proteins is helpful for annotation of protein function and drug design. However, due to the huge amounts of protein sequences influx into databases in the post-genome era, experimentally identifying ATP binding residues is cost-ineffective and time-consuming. To address this problem, computational methods have been developed to predict ATP binding residues. In this review, we briefly summarized the application of machine learning methods in detecting ATP binding residues of proteins. We expect this review will be helpful for further research.

Prediction of MoRFs based on sequence properties and convolutional neural networks

Background

Intrinsically disordered proteins possess flexible 3-D structures, which makes them play an important role in a variety of biological functions. Molecular recognition features (MoRFs) act as an important type of functional regions, which are located within longer intrinsically disordered regions and undergo disorder-to-order transitions upon binding their interaction partners.

Results

We develop a method, MoRF_CNN, to predict MoRFs based on sequence properties and convolutional neural networks (CNNs). The sequence properties contain structural and physicochemical properties which are used to describe the differences between MoRFs and non-MoRFs. Especially, to highlight the correlation between the target residue and adjacent residues, three windows are selected to preprocess the selected properties. After that, these calculated properties are combined into the feature matrix to predict MoRFs through the constructed CNN. Comparing with other existing methods, MoRF_CNN obtains better performance.

Conclusions

MoRF_CNN is a new individual MoRFs prediction method which just uses protein sequence properties without evolutionary information. The simulation results show that MoRF_CNN is effective and competitive.

A Hybrid Levenberg-Marquardt Algorithm on a Recursive Neural Network for Scoring Protein Models

We have studied the ability of three types of neural networks to predict the closeness of a given protein model to the native structure associated with its sequence. We show that a partial combination of the Levenberg-Marquardt algorithm and the back-propagation algorithm produced the best results, giving the lowest error and largest Pearson correlation coefficient. We also find, as previous studies, that adding associative memory to a neural network improves its performance. Additionally, we find that the hybrid method we propose was the most robust in the sense that other configurations of it experienced less decline in comparison to the other methods. We find that the hybrid networks also undergo more fluctuations on the path to convergence. We propose that these fluctuations allow for better sampling. Overall we find it may be beneficial to treat different parts of a neural network with varied computational approaches during optimization.

Relevance of Machine Learning Techniques and Various Protein Features in Protein Fold Classification: A Review

Background:

Protein fold prediction is a fundamental step in Structural Bioinformatics. The tertiary structure of a protein determines its function and to predict its tertiary structure, fold prediction serves an important role. Protein fold is simply the arrangement of the secondary structure elements relative to each other in space. A number of studies have been carried out till date by different research groups working worldwide in this field by using the combination of different benchmark datasets, different types of descriptors, features and classification techniques.

Objective:

In this study, we have tried to put all these contributions together, analyze their study and to compare different techniques used by them.

Methods:

Different features are derived from protein sequence, its secondary structure, different physicochemical properties of amino acids, domain composition, Position Specific Scoring Matrix, profile and threading techniques.

Conclusion:

Combination of these different features can improve classification accuracy to a large extent. With the help of this survey, one can know the most suitable feature/attribute set and classification technique for this multi-class protein fold classification problem.

Predicting FAD Interacting Residues with Feature Selection and Comprehensive Sequence Descriptors

The function of a flavoprotein is determined to a great extent by the binding sites on its surface that interacts with flavin adenine dinucleotide (FAD). Malfunction or dysregulation of FAD binding leads to a series of diseases. Therefore, accurately identifying FAD interacting residues (FIRs) provides insights into the molecular mechanisms of flavoprotein-related biological processes and disease progression. In this paper, a new computational method is proposed for identifying FIRs from protein sequences. Various sequence-derived discriminative features are explored. We analyze the distinctions of these features between FIRs and non-FIRs. We also investigate the predictive capabilities of both individual features and combinations of features. A relief algorithm followed by incremental feature selection (relief-IFS) is then adopted to search the optimal features. Finally, a random forest (RF) module is used to predict FIRs based on the optimal features. Using a 5-fold cross-validation test, the proposed method performs well, with a sensitivity of 0.847, a specificity of 0.933, an accuracy of 0.890, and a Matthews correlation coefficient (MCC) of 0.782, thereby outperforming previous methods. These results indicate that our method is relatively successful at predicting FIRs.

Computational prediction of MoRFs based on protein sequences and minimax probability machine

Background

Molecular recognition features (MoRFs) are one important type of disordered segments that can promote specific protein-protein interactions. They are located within longer intrinsically disordered regions (IDRs), and undergo disorder-to-order transitions upon binding to their interaction partners. The functional importance of MoRFs and the limitation of experimental identification make it necessary to predict MoRFs accurately with computational methods.

Results

In this study, a new sequence-based method, named as MoRF_MPM, is proposed for predicting MoRFs. MoRF_MPM uses minimax probability machine (MPM) to predict MoRFs based on 16 features and 3 different windows, which neither relying on other predictors nor calculating the properties of the surrounding regions of MoRFs separately. Comparing with ANCHOR, MoRFpred and MoRF_CHiBi on the same test sets, MoRF_MPM not only obtains higher AUC, but also obtains higher TPR at low FPR.

Conclusions

The features used in MoRF_MPM can effectively predict MoRFs, especially after preprocessing. Besides, MoRF_MPM uses a linear classification algorithm and does not rely on results of other predictors which makes it accessible and repeatable.

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.

Entropy, Fluctuations, and Disordered Proteins

Entropy should directly reflect the extent of disorder in proteins. By clustering structurally related proteins and studying the multiple-sequence-alignment of the sequences of these clusters, we were able to link between sequence, structure, and disorder information. We introduced several parameters as measures of fluctuations at a given MSA site and used these as representative of the sequence and structure entropy at that site. In general, we found a tendency for negative correlations between disorder and structure, and significant positive correlations between disorder and the fluctuations in the system. We also found evidence for residue-type conservation for those residues proximate to potentially disordered sites. Mutation at the disorder site itself appear to be allowed. In addition, we found positive correlation for disorder and accessible surface area, validating that disordered residues occur in exposed regions of proteins. Finally, we also found that fluctuations in the dihedral angles at the original mutated residue and disorder are positively correlated while dihedral angle fluctuations in spatially proximal residues are negatively correlated with disorder. Our results seem to indicate permissible variability in the disordered site, but greater rigidity in the parts of the protein with which the disordered site interacts. This is another indication that disordered residues are involved in protein function.

Prediction of MoRFs in Protein Sequences with MLPs Based on Sequence Properties and Evolution Information

Molecular recognition features (MoRFs) are one important type of intrinsically disordered proteins functional regions that can undergo a disorder-to-order transition through binding to their interaction partners. Prediction of MoRFs is crucial, as the functions of MoRFs are associated with many diseases and can therefore become the potential drug targets. In this paper, a method of predicting MoRFs is developed based on the sequence properties and evolutionary information. To this end, we design two distinct multi-layer perceptron (MLP) neural networks and present a procedure to train them. We develop a preprocessing process which exploits different sizes of sliding windows to capture various properties related to MoRFs. We then use the Bayes rule together with the outputs of two trained MLP neural networks to predict MoRFs. In comparison to several state-of-the-art methods, the simulation results show that our method is competitive.

ANDIS: an atomic angle- and distance-dependent statistical potential for protein structure quality assessment

Background

The knowledge-based statistical potential has been widely used in protein structure modeling and model quality assessment. They are commonly evaluated based on their abilities of native recognition as well as decoy discrimination. However, these two aspects are found to be mutually exclusive in many statistical potentials.

Results

We developed an atomic ANgle- and DIStance-dependent (ANDIS) statistical potential for protein structure quality assessment with distance cutoff being a tunable parameter. When distance cutoff is ≤9.0 Å, “effective atomic interaction” is employed to enhance the ability of native recognition. For a distance cutoff of ≥10 Å, the distance-dependent atom-pair potential with random-walk reference state is combined to strengthen the ability of decoy discrimination. Benchmark tests on 632 structural decoy sets from diverse sources demonstrate that ANDIS outperforms other state-of-the-art potentials in both native recognition and decoy discrimination.

Conclusions

Distance cutoff is a crucial parameter for distance-dependent statistical potentials. A lower distance cutoff is better for native recognition, while a higher one is favorable for decoy discrimination. The ANDIS potential is freely available as a standalone application at http://qbp.hzau.edu.cn/ANDIS/.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-2898-y) contains supplementary material, which is available to authorized users.

Predicting Functions of Disordered Proteins with MoRFpred

Intrinsically disordered proteins and regions are involved in a wide range of cellular functions, and they often facilitate protein-protein interactions. Molecular recognition features (MoRFs) are segments of intrinsically disordered regions that bind to partner proteins, where binding is concomitant with a transition to a structured conformation. MoRFs facilitate translation, transport, signaling, and regulatory processes and are found across all domains of life. A popular computational tool, MoRFpred, accurately predicts MoRFs in protein sequences. MoRFpred is implemented as a user-friendly web server that is freely available at http://biomine.cs.vcu.edu/servers/MoRFpred/ . We describe this predictor, explain how to run the web server, and show how to interpret the results it generates. We also demonstrate the utility of this web server based on two case studies, focusing on the relevance of evolutionary conservation of MoRF regions.

Dimensionality reduction for protein secondary structure and solvent accesibility prediction

Secondary structure and solvent accessibility prediction provide valuable information for estimating the three dimensional structure of a protein. As new feature extraction methods are developed the dimensionality of the input feature space increases steadily. Reducing the number of dimensions provides several advantages such as faster model training, faster prediction and noise elimination. In this work, several dimensionality reduction techniques have been employed including various feature selection methods, autoencoders and PCA for protein secondary structure and solvent accessibility prediction. The reduced feature set is used to train a support vector machine at the second stage of a hybrid classifier. Cross-validation experiments on two difficult benchmarks demonstrate that the dimension of the input space can be reduced substantially while maintaining the prediction accuracy. This will enable the incorporation of additional informative features derived for predicting the structural properties of proteins without reducing the accuracy due to overfitting.

Chemical shift-based methods in NMR structure determination

Chemical shifts are highly sensitive probes harnessed by NMR spectroscopists and structural biologists as conformational parameters to characterize a range of biological molecules. Traditionally, assignment of chemical shifts has been a labor-intensive process requiring numerous samples and a suite of multidimensional experiments. Over the past two decades, the development of complementary computational approaches has bolstered the analysis, interpretation and utilization of chemical shifts for elucidation of high resolution protein and nucleic acid structures. Here, we review the development and application of chemical shift-based methods for structure determination with a focus on ab initio fragment assembly, comparative modeling, oligomeric systems, and automated assignment methods. Throughout our discussion, we point out practical uses, as well as advantages and caveats, of using chemical shifts in structure modeling. We additionally highlight (i) hybrid methods that employ chemical shifts with other types of NMR restraints (residual dipolar couplings, paramagnetic relaxation enhancements and pseudocontact shifts) that allow for improved accuracy and resolution of generated 3D structures, (ii) the utilization of chemical shifts to model the structures of sparsely populated excited states, and (iii) modeling of sidechain conformations. Finally, we briefly discuss the advantages of contemporary methods that employ sparse NMR data recorded using site-specific isotope labeling schemes for chemical shift-driven structure determination of larger molecules. With this review, we aim to emphasize the accessibility and versatility of chemical shifts for structure determination of challenging biological systems, and to point out emerging areas of development that lead us towards the next generation of tools.

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.

RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning

Background

Protein dihedral angles provide a detailed description of protein local conformation. Predicted dihedral angles can be used to narrow down the conformational space of the whole polypeptide chain significantly, thus aiding protein tertiary structure prediction. However, direct angle prediction from sequence alone is challenging.

Results

In this article, we present a novel method (named RaptorX-Angle) to predict real-valued angles by combining clustering and deep learning. Tested on a subset of PDB25 and the targets in the latest two Critical Assessment of protein Structure Prediction (CASP), our method outperforms the existing state-of-art method SPIDER2 in terms of Pearson Correlation Coefficient (PCC) and Mean Absolute Error (MAE). Our result also shows approximately linear relationship between the real prediction errors and our estimated bounds. That is, the real prediction error can be well approximated by our estimated bounds.

Conclusions

Our study provides an alternative and more accurate prediction of dihedral angles, which may facilitate protein structure prediction and functional study.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2065-x) contains supplementary material, which is available to authorized users.

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.

A Novel Method for Drug Screen to Regulate G Protein-Coupled Receptors in the Metabolic Network of Alzheimer's Disease

Alzheimer's disease (AD) is a chronic and progressive neurodegenerative disorder and the pathogenesis of AD is poorly understood. G protein-coupled receptors (GPCRs) are involved in numerous key AD pathways and play a key role in the pathology of AD. To fully understand the pathogenesis of AD and design novel drug therapeutics, analyzing the connection between AD and GPCRs is of great importance. In this paper, we firstly build and analyze the AD-related pathway by consulting the KEGG pathway of AD and a mass of literature and collect 25 AD-related GPCRs for drug discovery. Then the ILbind and AutoDock Vina tools are integrated to find out potential drugs related to AD. According to the analysis of DUD-E dataset, we select five drugs, that is, Acarbose (ACR), Carvedilol (CVD), Digoxin (DGX), NADH (NAI), and Telmisartan (TLS), by sorting the ILbind scores (≥0.73). Then depending on their AutoDock Vina scores and pocket position information, the binding patterns of these five drugs are obtained. We analyze the regulation function of GPCRs in the metabolic network of AD based on the drug screen results, which may be helpful for the study of the off-target effect and the side effect of drugs.

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/.

Molecular Characterization of Pneumococcal Surface Protein A (PspA), Serotype Distribution and Antibiotic Susceptibility of Streptococcus pneumoniae Strains Isolated from Pakistan

INTRODUCTION

Pakistan has one of the highest burdens of pneumococcal diseases in the world, but unfortunately studies in this demanding research area are limited in the region. Pneumococcal surface protein A (PspA) is the next generation pneumococcal vaccine candidate as the protein locates on the Streptococcus pneumoniae surface. Its gene, pspA, might be encoded by all pneumococci, and the protein has proven immunogenicity. The molecular characterization of PspA, pneumococcal serotype distribution and antibiotic susceptibility are important for regional diversity studies.

METHODS

In this study, we examined 38 pneumococcal isolates from pneumococcal diseased (pneumonia/meningitis) patients blood or cerebrospinal fluid. There were no specific inclusion or exclusion criteria, but all the individuals [ages 1 month to 12 years (male/female)] had undergone no antibiotic treatment in at least the past 3 months and had no vaccination history. We investigated the serotype distribution, antibiotic susceptibility, prevalence of the PspA family and its active domain's fusion, expression and antigenicity.

RESULTS

Our finding shows that serotype 19F is the most prevalent (23.6%) followed by 18B (15.78%) (non-vaccine type) in all isolated pneumococcal strains. All strains were susceptible to chloramphenicol and linezolid, while 80% were resistant to gentamycin. Genotyping revealed that ~ 80% (N = 31/38) of pneumococcal strains produce PspA belonging to family 2 and clade 3. We further selected three active domains of PspA (family 2 and clade 3) by in silico analysis, merged together into a fusion gene for expression study, and its antigenicity was analyzed by Western blotting.

CONCLUSION

Serotypes 19F and 18B (non-vaccine type) are the most prevalent in the Pakistani pneumococcal isolates. The PspA family 2 proteins produced by Pakistani pneumococcal isolates have high sequence homologies with each other and differ from those produced by strains isolated in the rest of the world. The PspA fusion peptide had a proven antigenic response in western blotting, with no considerable correlation among pneumococcal serotypes, antibiotic susceptibility and PspA family/clade distribution.

RBSURFpred: Modeling protein accessible surface area in real and binary space using regularized and optimized regression

Accessible surface area (ASA) of a protein residue is an effective feature for protein structure prediction, binding region identification, fold recognition problems etc. Improving the prediction of ASA by the application of effective feature variables is a challenging but explorable task to consider, specially in the field of machine learning. Among the existing predictors of ASA, REGAd³p is a highly accurate ASA predictor which is based on regularized exact regression with polynomial kernel of degree 3. In this work, we present a new predictor RBSURFpred, which extends REGAd³p on several dimensions by incorporating 58 physicochemical, evolutionary and structural properties into 9-tuple peptides via Chou's general PseAAC, which allowed us to obtain higher accuracies in predicting both real-valued and binary ASA. We have compared RBSURFpred for both real and binary space predictions with state-of-the-art predictors, such as REGAd³p and SPIDER2. We also have carried out a rigorous analysis of the performance of RBSURFpred in terms of different amino acids and their properties, and also with biologically relevant case-studies. The performance of RBSURFpred establishes itself as a useful tool for the community.

A sparse autoencoder-based deep neural network for protein solvent accessibility and contact number prediction

BACKGROUND

Direct prediction of the three-dimensional (3D) structures of proteins from one-dimensional (1D) sequences is a challenging problem. Significant structural characteristics such as solvent accessibility and contact number are essential for deriving restrains in modeling protein folding and protein 3D structure. Thus, accurately predicting these features is a critical step for 3D protein structure building.

RESULTS

In this study, we present DeepSacon, a computational method that can effectively predict protein solvent accessibility and contact number by using a deep neural network, which is built based on stacked autoencoder and a dropout method. The results demonstrate that our proposed DeepSacon achieves a significant improvement in the prediction quality compared with the state-of-the-art methods. We obtain 0.70 three-state accuracy for solvent accessibility, 0.33 15-state accuracy and 0.74 Pearson Correlation Coefficient (PCC) for the contact number on the 5729 monomeric soluble globular protein dataset. We also evaluate the performance on the CASP11 benchmark dataset, DeepSacon achieves 0.68 three-state accuracy and 0.69 PCC for solvent accessibility and contact number, respectively.

CONCLUSIONS

We have shown that DeepSacon can reliably predict solvent accessibility and contact number with stacked sparse autoencoder and a dropout approach.

Protein Crystallizability

Obtaining diffracting quality crystals remains a major challenge in protein structure research. We summarize and compare methods for selecting the best protein targets for crystallization, construct optimization and crystallization condition design. Target selection methods are divided into algorithms predicting the chance of successful progression through all stages of structural determination (from cloning to solving the structure) and those focusing only on the crystallization step. We tried to highlight pros and cons of different approaches examining the following aspects: data size, redundancy and representativeness, overfitting during model construction, and results evaluation. In summary, although in recent years progress was made and several sequence properties were reported to be relevant for crystallization, the successful prediction of protein crystallization behavior and selection of corresponding crystallization conditions continue to challenge structural researchers.

Deep learning methods for protein torsion angle prediction

Background

Deep learning is one of the most powerful machine learning methods that has achieved the state-of-the-art performance in many domains. Since deep learning was introduced to the field of bioinformatics in 2012, it has achieved success in a number of areas such as protein residue-residue contact prediction, secondary structure prediction, and fold recognition. In this work, we developed deep learning methods to improve the prediction of torsion (dihedral) angles of proteins.

Results

We design four different deep learning architectures to predict protein torsion angles. The architectures including deep neural network (DNN) and deep restricted Boltzmann machine (DRBN), deep recurrent neural network (DRNN) and deep recurrent restricted Boltzmann machine (DReRBM) since the protein torsion angle prediction is a sequence related problem. In addition to existing protein features, two new features (predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments) are used as input to each of the four deep learning architectures to predict phi and psi angles of protein backbone. The mean absolute error (MAE) of phi and psi angles predicted by DRNN, DReRBM, DRBM and DNN is about 20–21° and 29–30° on an independent dataset. The MAE of phi angle is comparable to the existing methods, but the MAE of psi angle is 29°, 2° lower than the existing methods. On the latest CASP12 targets, our methods also achieved the performance better than or comparable to a state-of-the art method.

Conclusions

Our experiment demonstrates that deep learning is a valuable method for predicting protein torsion angles. The deep recurrent network architecture performs slightly better than deep feed-forward architecture, and the predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments are useful features for improving prediction accuracy.

Electronic supplementary material

The online version of this article (10.1186/s12859-017-1834-2) contains supplementary material, which is available to authorized users.

Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions

Computational prediction of intrinsic disorder in protein sequences dates back to late 1970 and has flourished in the last two decades. We provide a brief historical overview, and we review over 30 recent predictors of disorder. We are the first to also cover predictors of molecular functions of disorder, including 13 methods that focus on disordered linkers and disordered protein-protein, protein-RNA, and protein-DNA binding regions. We overview their predictive models, usability, and predictive performance. We highlight newest methods and predictors that offer strong predictive performance measured based on recent comparative assessments. We conclude that the modern predictors are relatively accurate, enjoy widespread use, and many of them are fast. Their predictions are conveniently accessible to the end users, via web servers and databases that store pre-computed predictions for millions of proteins. However, research into methods that predict many not yet addressed functions of intrinsic disorder remains an outstanding challenge.

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 .

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 .

Intrinsic Disorder and Semi-disorder Prediction by SPINE-D

Over the past decade, it has become evident that a large proportion of proteins contain intrinsically disordered regions, which play important roles in pivotal cellular functions. Many computational tools have been developed with the aim of identifying the level and location of disorder within a protein. In this chapter, we describe a neural network based technique called SPINE-D that employs a unique three-state design and can accurately capture disordered residues in both short and long disordered regions. SPINE-D was trained on a large database of 4229 non-redundant proteins, and yielded an AUC of 0.86 on a cross-validation test and 0.89 on an independent test. SPINE-D can also detect a semi-disordered state that is associated with induced folders and aggregation-prone regions in disordered proteins and weakly stable or locally unfolded regions in structured proteins. We implement an online web service and an offline stand-alone program for SPINE-D, they are freely available at http://sparks-lab.org/SPINE-D/ . We then walk you through how to use the online and offline SPINE-D in making disorder predictions, and examine the disorder and semi-disorder prediction in a case study on the p53 protein.

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.

Predicting MoRFs in protein sequences using HMM profiles

BACKGROUND

Intrinsically Disordered Proteins (IDPs) lack an ordered three-dimensional structure and are enriched in various biological processes. The Molecular Recognition Features (MoRFs) are functional regions within IDPs that undergo a disorder-to-order transition on binding to a partner protein. Identifying MoRFs in IDPs using computational methods is a challenging task.

METHODS

In this study, we introduce hidden Markov model (HMM) profiles to accurately identify the location of MoRFs in disordered protein sequences. Using windowing technique, HMM profiles are utilised to extract features from protein sequences and support vector machines (SVM) are used to calculate a propensity score for each residue. Two different SVM kernels with high noise tolerance are evaluated with a varying window size and the scores of the SVM models are combined to generate the final propensity score to predict MoRF residues. The SVM models are designed to extract maximal information between MoRF residues, its neighboring regions (Flanks) and the remainder of the sequence (Others).

RESULTS

To evaluate the proposed method, its performance was compared to that of other MoRF predictors; MoRFpred and ANCHOR. The results show that the proposed method outperforms these two predictors.

CONCLUSIONS

Using HMM profile as a source of feature extraction, the proposed method indicates improvement in predicting MoRFs in disordered protein sequences.

Estimation of Position Specific Energy as a Feature of Protein Residues from Sequence Alone for Structural Classification

A set of features computed from the primary amino acid sequence of proteins, is crucial in the process of inducing a machine learning model that is capable of accurately predicting three-dimensional protein structures. Solutions for existing protein structure prediction problems are in need of features that can capture the complexity of molecular level interactions. With a view to this, we propose a novel approach to estimate position specific estimated energy (PSEE) of a residue using contact energy and predicted relative solvent accessibility (RSA). Furthermore, we demonstrate PSEE can be reasonably estimated based on sequence information alone. PSEE is useful in identifying the structured as well as unstructured or, intrinsically disordered region of a protein by computing favorable and unfavorable energy respectively, characterized by appropriate threshold. The most intriguing finding, verified empirically, is the indication that the PSEE feature can effectively classify disorder versus ordered residues and can segregate different secondary structure type residues by computing the constituent energies. PSEE values for each amino acid strongly correlate with the hydrophobicity value of the corresponding amino acid. Further, PSEE can be used to detect the existence of critical binding regions that essentially undergo disorder-to-order transitions to perform crucial biological functions. Towards an application of disorder prediction using the PSEE feature, we have rigorously tested and found that a support vector machine model informed by a set of features including PSEE consistently outperforms a model with an identical set of features with PSEE removed. In addition, the new disorder predictor, DisPredict2, shows competitive performance in predicting protein disorder when compared with six existing disordered protein predictors.

AUC-Maximized Deep Convolutional Neural Fields for Protein Sequence Labeling

Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This paper presents Deep Convolutional Neural Fields (DeepCNF), an integration of DCNN with Conditional Random Field (CRF), for sequence labeling with an imbalanced label distribution. The widely-used training methods, such as maximum-likelihood and maximum labelwise accuracy, do not work well on imbalanced data. To handle this, we present a new training algorithm called maximum-AUC for DeepCNF. That is, we train DeepCNF by directly maximizing the empirical Area Under the ROC Curve (AUC), which is an unbiased measurement for imbalanced data. To fulfill this, we formulate AUC in a pairwise ranking framework, approximate it by a polynomial function and then apply a gradient-based procedure to optimize it. Our experimental results confirm that maximum-AUC greatly outperforms the other two training methods on 8-state secondary structure prediction and disorder prediction since their label distributions are highly imbalanced and also has similar performance as the other two training methods on solvent accessibility prediction, which has three equally-distributed labels. Furthermore, our experimental results show that our AUC-trained DeepCNF models greatly outperform existing popular predictors of these three tasks. The data and software related to this paper are available at https://github.com/realbigws/DeepCNF_AUC.

Inadequate Reference Datasets Biased toward Short Non-epitopes Confound B-cell Epitope Prediction

X-ray crystallography has shown that an antibody paratope typically binds 15-22 amino acids (aa) of an epitope, of which 2-5 randomly distributed amino acids contribute most of the binding energy. In contrast, researchers typically choose for B-cell epitope mapping short peptide antigens in antibody binding assays. Furthermore, short 6-11-aa epitopes, and in particular non-epitopes, are over-represented in published B-cell epitope datasets that are commonly used for development of B-cell epitope prediction approaches from protein antigen sequences. We hypothesized that such suboptimal length peptides result in weak antibody binding and cause false-negative results. We tested the influence of peptide antigen length on antibody binding by analyzing data on more than 900 peptides used for B-cell epitope mapping of immunodominant proteins of Chlamydia spp. We demonstrate that short 7-12-aa peptides of B-cell epitopes bind antibodies poorly; thus, epitope mapping with short peptide antigens falsely classifies many B-cell epitopes as non-epitopes. We also show in published datasets of confirmed epitopes and non-epitopes a direct correlation between length of peptide antigens and antibody binding. Elimination of short, ≤11-aa epitope/non-epitope sequences improved datasets for evaluation of in silico B-cell epitope prediction. Achieving up to 86% accuracy, protein disorder tendency is the best indicator of B-cell epitope regions for chlamydial and published datasets. For B-cell epitope prediction, the most effective approach is plotting disorder of protein sequences with the IUPred-L scale, followed by antibody reactivity testing of 16-30-aa peptides from peak regions. This strategy overcomes the well known inaccuracy of in silico B-cell epitope prediction from primary protein sequences.

Improved de novo structure prediction in CASP11 by incorporating coevolution information into Rosetta

We describe CASP11 de novo blind structure predictions made using the Rosetta structure prediction methodology with both automatic and human assisted protocols. Model accuracy was generally improved using coevolution derived residue-residue contact information as restraints during Rosetta conformational sampling and refinement, particularly when the number of sequences in the family was more than three times the length of the protein. The highlight was the human assisted prediction of T0806, a large and topologically complex target with no homologs of known structure, which had unprecedented accuracy-<3.0 Å root-mean-square deviation (RMSD) from the crystal structure over 223 residues. For this target, we increased the amount of conformational sampling over our fully automated method by employing an iterative hybridization protocol. Our results clearly demonstrate, in a blind prediction scenario, that coevolution derived contacts can considerably increase the accuracy of template-free structure modeling. Proteins 2016; 84(Suppl 1):67-75. © 2015 Wiley Periodicals, Inc.

PredRSA: a gradient boosted regression trees approach for predicting protein solvent accessibility

Background

Protein solvent accessibility prediction is a pivotal intermediate step towards modeling protein tertiary structures directly from one-dimensional sequences. It also plays an important part in identifying protein folds and domains. Although some methods have been presented to the protein solvent accessibility prediction in recent years, the performance is far from satisfactory. In this work, we propose PredRSA, a computational method that can accurately predict relative solvent accessible surface area (RSA) of residues by exploring various local and global sequence features which have been observed to be associated with solvent accessibility. Based on these features, a novel and efficient approach, Gradient Boosted Regression Trees (GBRT), is first adopted to predict RSA.

Results

Experimental results obtained from 5-fold cross-validation based on the Manesh-215 dataset show that the mean absolute error (MAE) and the Pearson correlation coefficient (PCC) of PredRSA are 9.0 % and 0.75, respectively, which are better than that of the existing methods. Moreover, we evaluate the performance of PredRSA using an independent test set of 68 proteins. Compared with the state-of-the-art approaches (SPINE-X and ASAquick), PredRSA achieves a significant improvement on the prediction quality.

Conclusions

Our experimental results show that the Gradient Boosted Regression Trees algorithm and the novel feature combination are quite effective in relative solvent accessibility prediction. The proposed PredRSA method could be useful in assisting the prediction of protein structures by applying the predicted RSA as useful restraints.

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.

DisPredict: A Predictor of Disordered Protein Using Optimized RBF Kernel

Intrinsically disordered proteins or, regions perform important biological functions through their dynamic conformations during binding. Thus accurate identification of these disordered regions have significant implications in proper annotation of function, induced fold prediction and drug design to combat critical diseases. We introduce DisPredict, a disorder predictor that employs a single support vector machine with RBF kernel and novel features for reliable characterization of protein structure. DisPredict yields effective performance. In addition to 10-fold cross validation, training and testing of DisPredict was conducted with independent test datasets. The results were consistent with both the training and test error minimal. The use of multiple data sources, makes the predictor generic. The datasets used in developing the model include disordered regions of various length which are categorized as short and long having different compositions, different types of disorder, ranging from fully to partially disordered regions as well as completely ordered regions. Through comparison with other state of the art approaches and case studies, DisPredict is found to be a useful tool with competitive performance. DisPredict is available at https://github.com/tamjidul/DisPredict_v1.0.

AcconPred: Predicting Solvent Accessibility and Contact Number Simultaneously by a Multitask Learning Framework under the Conditional Neural Fields Model

Motivation. The solvent accessibility of protein residues is one of the driving forces of protein folding, while the contact number of protein residues limits the possibilities of protein conformations. The de novo prediction of these properties from protein sequence is important for the study of protein structure and function. Although these two properties are certainly related with each other, it is challenging to exploit this dependency for the prediction. Method. We present a method AcconPred for predicting solvent accessibility and contact number simultaneously, which is based on a shared weight multitask learning framework under the CNF (conditional neural fields) model. The multitask learning framework on a collection of related tasks provides more accurate prediction than the framework trained only on a single task. The CNF method not only models the complex relationship between the input features and the predicted labels, but also exploits the interdependency among adjacent labels. Results. Trained on 5729 monomeric soluble globular protein datasets, AcconPred could reach 0.68 three-state accuracy for solvent accessibility and 0.75 correlation for contact number. Tested on the 105 CASP11 domain datasets for solvent accessibility, AcconPred could reach 0.64 accuracy, which outperforms existing methods.