Predicting disulfide connectivity from protein sequence using multiple sequence feature vectors and secondary structure

The Impact of Sodium Dodecyl Sulfate and 2-Mercaptoethanol on Antibody and Antigen Binding

OBJECTIVE

To evaluate the effect of sodium dodecyl sulfate (SDS) and 2-mercaptoethanol (2-ME) on antigen-antibody binding when incubated at 100°C, which is the pretreatment temperature required for western blots.

METHODS

Serum that tested positive for hepatitis B surface antigen (HBsAg) plus loading buffer were mixed at a ratio of 4:1 and incubated in a water bath. We then detected HBsAg using double immunodiffusion and ELISA.

RESULTS

The HBsAg titer was 1:512 in the control group when incubated at 37°C. Incubation with SDS at 100°C reduced the antigen titer to 1:32. The inhibitory effect on HBsAg titer reached 96.9% after incubation at 100°C with SDS and 2-ME.

CONCLUSION

We detected strong inhibition of antigens in western blots via SDS and 2-ME. It is likely that false-negative results will be obtained from western blots of antigens with weak resistance to these reagents.

diSBPred: A machine learning based approach for disulfide bond prediction

The protein disulfide bond is a covalent bond that forms during post-translational modification by the oxidation of a pair of cysteines. In protein, the disulfide bond is the most frequent covalent link between amino acids after the peptide bond. It plays a significant role in three-dimensional (3D) ab initio protein structure prediction (aiPSP), stabilizing protein conformation, post-translational modification, and protein folding. In aiPSP, the location of disulfide bonds can strongly reduce the conformational space searching by imposing geometrical constraints. Existing experimental techniques for the determination of disulfide bonds are time-consuming and expensive. Thus, developing sequence-based computational methods for disulfide bond prediction becomes indispensable. This study proposed a stacking-based machine learning approach for disulfide bond prediction (diSBPred). Various useful sequence and structure-based features are extracted for effective training, including conservation profile, residue solvent accessibility, torsion angle flexibility, disorder probability, a sequential distance between cysteines, and more. The prediction of disulfide bonds is carried out in two stages: first, individual cysteines are predicted as either bonding or non-bonding; second, the cysteine-pairs are predicted as either bonding or non-bonding by including the results from cysteine bonding prediction as a feature. The examination of the relevance of the features employed in this study and the features utilized in the existing nearest neighbor algorithm (NNA) method shows that the features used in this study improve about 7.39 % in jackknife validation balanced accuracy. Moreover, for individual cysteine bonding prediction and cysteine-pair bonding prediction, diSBPred provides a 10-fold cross-validation balanced accuracy of 82.29 % and 94.20 %, respectively. Altogether, our predictor achieves an improvement of 43.25 % based on balanced accuracy compared to the existing NNA based approach. Thus, diSBPred can be utilized to annotate the cysteine bonding residues of protein sequences whose structures are unknown as well as improve the accuracy of the aiPSP method, which can further aid in experimental studies of the disulfide bond and structure determination.

Local Similarity Matrix for Cysteine Disulfide Connectivity Prediction from Protein Sequences

Accurately predicting three dimensional protein structures from sequences would present us with targets for drugs via molecular dynamics that would treat cancer, viral infections, and neurological diseases. These treatments would have a far reaching impact to our economy, quality of life, and society. The goal of this research was to build a data mining framework to predict cysteine connectivity in proteins from the sequence and oxidation state of cysteines. Accurately predicting the cysteine bonding configuration improves the TM-Score, a quantitative measurement of protein structure prediction accuracy. We provided state of the art Q_p and Q_c on the PDBCYS and IVD-54 Datasets. Furthermore, we have produced a Local Similarity Matrix that compares favorably to the default PSSMs generated from PSI-Blast in a statistically significant way. Our Q_p for SP39, PDBCYS, and IVD-54 were 90.6, 80.6, and 68.5, respectively.

Optoplasmonic characterisation of reversible disulfide interactions at single thiol sites in the attomolar regime

Probing individual chemical reactions is key to mapping reaction pathways. Trace analysis of sub-kDa reactants and products is obfuscated by labels, however, as reaction kinetics are inevitably perturbed. The thiol-disulfide exchange reaction is of specific interest as it has many applications in nanotechnology and in nature. Redox cycling of single thiols and disulfides has been unresolvable due to a number of technological limitations, such as an inability to discriminate the leaving group. Here, we demonstrate detection of single-molecule thiol-disulfide exchange using a label-free optoplasmonic sensor. We quantify repeated reactions between sub-kDa thiolated species in real time and at concentrations down to 100’s of attomolar. A unique sensing modality is featured in our measurements, enabling the observation of single disulfide reaction kinetics and pathways on a plasmonic nanoparticle surface. Our technique paves the way towards characterising molecules in terms of their charge, oxidation state, and chirality via optoplasmonics.

Visualising single-molecule reactions, to understand their mechanisms, is a challenging task. Here, the authors investigate disulfide exchange reactions with thiolates immobilised on a gold nanoparticle through a label-free optoplasmonic sensor, and detect individual disulfide interactions in solution

iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites

Regulation of proteolysis plays a critical role in a myriad of important cellular processes. The key to better understanding the mechanisms that control this process is to identify the specific substrates that each protease targets. To address this, we have developed iProt-Sub, a powerful bioinformatics tool for the accurate prediction of protease-specific substrates and their cleavage sites. Importantly, iProt-Sub represents a significantly advanced version of its successful predecessor, PROSPER. It provides optimized cleavage site prediction models with better prediction performance and coverage for more species-specific proteases (4 major protease families and 38 different proteases). iProt-Sub integrates heterogeneous sequence and structural features and uses a two-step feature selection procedure to further remove redundant and irrelevant features in an effort to improve the cleavage site prediction accuracy. Features used by iProt-Sub are encoded by 11 different sequence encoding schemes, including local amino acid sequence profile, secondary structure, solvent accessibility and native disorder, which will allow a more accurate representation of the protease specificity of approximately 38 proteases and training of the prediction models. Benchmarking experiments using cross-validation and independent tests showed that iProt-Sub is able to achieve a better performance than several existing generic tools. We anticipate that iProt-Sub will be a powerful tool for proteome-wide prediction of protease-specific substrates and their cleavage sites, and will facilitate hypothesis-driven functional interrogation of protease-specific substrate cleavage and proteolytic events.

Computational analysis and prediction of lysine malonylation sites by exploiting informative features in an integrative machine-learning framework

As a newly discovered post-translational modification (PTM), lysine malonylation (Kmal) regulates a myriad of cellular processes from prokaryotes to eukaryotes and has important implications in human diseases. Despite its functional significance, computational methods to accurately identify malonylation sites are still lacking and urgently needed. In particular, there is currently no comprehensive analysis and assessment of different features and machine learning (ML) methods that are required for constructing the necessary prediction models. Here, we review, analyze and compare 11 different feature encoding methods, with the goal of extracting key patterns and characteristics from residue sequences of Kmal sites. We identify optimized feature sets, with which four commonly used ML methods (random forest, support vector machines, K-nearest neighbor and logistic regression) and one recently proposed [Light Gradient Boosting Machine (LightGBM)] are trained on data from three species, namely, Escherichia coli, Mus musculus and Homo sapiens, and compared using randomized 10-fold cross-validation tests. We show that integration of the single method-based models through ensemble learning further improves the prediction performance and model robustness on the independent test. When compared to the existing state-of-the-art predictor, MaloPred, the optimal ensemble models were more accurate for all three species (AUC: 0.930, 0.923 and 0.944 for E. coli, M. musculus and H. sapiens, respectively). Using the ensemble models, we developed an accessible online predictor, kmal-sp, available at http://kmalsp.erc.monash.edu/. We hope that this comprehensive survey and the proposed strategy for building more accurate models can serve as a useful guide for inspiring future developments of computational methods for PTM site prediction, expedite the discovery of new malonylation and other PTM types and facilitate hypothesis-driven experimental validation of novel malonylated substrates and malonylation sites.

A transfer learning approach via procrustes analysis and mean shift for cancer drug sensitivity prediction

Transfer learning (TL) algorithms aim to improve the prediction performance in a target task (e.g. the prediction of cisplatin sensitivity in triple-negative breast cancer patients) via transferring knowledge from auxiliary data of a related task (e.g. the prediction of docetaxel sensitivity in breast cancer patients), where the distribution and even the feature space of the data pertaining to the tasks can be different. In real-world applications, we sometimes have a limited training set in a target task while we have auxiliary data from a related task. To obtain a better prediction performance in the target task, supervised learning requires a sufficiently large training set in the target task to perform well in predicting future test examples of the target task. In this paper, we propose a TL approach for cancer drug sensitivity prediction, where our approach combines three techniques. First, we shift the representation of a subset of examples from auxiliary data of a related task to a representation closer to a target training set of a target task. Second, we align the shifted representation of the selected examples of the auxiliary data to the target training set to obtain examples with representation aligned to the target training set. Third, we train machine learning algorithms using both the target training set and the aligned examples. We evaluate the performance of our approach against baseline approaches using the Area Under the receiver operating characteristic (ROC) Curve (AUC) on real clinical trial datasets pertaining to multiple myeloma, nonsmall cell lung cancer, triple-negative breast cancer, and breast cancer. Experimental results show that our approach is better than the baseline approaches in terms of performance and statistical significance.

Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches

In the course of infecting their hosts, pathogenic bacteria secrete numerous effectors, namely, bacterial proteins that pervert host cell biology. Many Gram-negative bacteria, including context-dependent human pathogens, use a type IV secretion system (T4SS) to translocate effectors directly into the cytosol of host cells. Various type IV secreted effectors (T4SEs) have been experimentally validated to play crucial roles in virulence by manipulating host cell gene expression and other processes. Consequently, the identification of novel effector proteins is an important step in increasing our understanding of host-pathogen interactions and bacterial pathogenesis. Here, we train and compare six machine learning models, namely, Naïve Bayes (NB), K-nearest neighbor (KNN), logistic regression (LR), random forest (RF), support vector machines (SVMs) and multilayer perceptron (MLP), for the identification of T4SEs using 10 types of selected features and 5-fold cross-validation. Our study shows that: (1) including different but complementary features generally enhance the predictive performance of T4SEs; (2) ensemble models, obtained by integrating individual single-feature models, exhibit a significantly improved predictive performance and (3) the 'majority voting strategy' led to a more stable and accurate classification performance when applied to predicting an ensemble learning model with distinct single features. We further developed a new method to effectively predict T4SEs, Bastion4 (Bacterial secretion effector predictor for T4SS), and we show our ensemble classifier clearly outperforms two recent prediction tools. In summary, we developed a state-of-the-art T4SE predictor by conducting a comprehensive performance evaluation of different machine learning algorithms along with a detailed analysis of single- and multi-feature selections.

Periscope: quantitative prediction of soluble protein expression in the periplasm of Escherichia coli

Periplasmic expression of soluble proteins in Escherichia coli not only offers a much-simplified downstream purification process, but also enhances the probability of obtaining correctly folded and biologically active proteins. Different combinations of signal peptides and target proteins lead to different soluble protein expression levels, ranging from negligible to several grams per litre. Accurate algorithms for rational selection of promising candidates can serve as a powerful tool to complement with current trial-and-error approaches. Accordingly, proteomics studies can be conducted with greater efficiency and cost-effectiveness. Here, we developed a predictor with a two-stage architecture, to predict the real-valued expression level of target protein in the periplasm. The output of the first-stage support vector machine (SVM) classifier determines which second-stage support vector regression (SVR) classifier to be used. When tested on an independent test dataset, the predictor achieved an overall prediction accuracy of 78% and a Pearson's correlation coefficient (PCC) of 0.77. We further illustrate the relative importance of various features with respect to different models. The results indicate that the occurrence of dipeptide glutamine and aspartic acid is the most important feature for the classification model. Finally, we provide access to the implemented predictor through the Periscope webserver, freely accessible at http://lightning.med.monash.edu/periscope/.

Soft Computing Methods for Disulfide Connectivity Prediction

The problem of protein structure prediction (PSP) is one of the main challenges in structural bioinformatics. To tackle this problem, PSP can be divided into several subproblems. One of these subproblems is the prediction of disulfide bonds. The disulfide connectivity prediction problem consists in identifying which nonadjacent cysteines would be cross-linked from all possible candidates. Determining the disulfide bond connectivity between the cysteines of a protein is desirable as a previous step of the 3D PSP, as the protein conformational search space is highly reduced. The most representative soft computing approaches for the disulfide bonds connectivity prediction problem of the last decade are summarized in this paper. Certain aspects, such as the different methodologies based on soft computing approaches (artificial neural network or support vector machine) or features of the algorithms, are used for the classification of these methods.

Accurate disulfide-bonding network predictions improve ab initio structure prediction of cysteine-rich proteins

MOTIVATION

Cysteine-rich proteins cover many important families in nature but there are currently no methods specifically designed for modeling the structure of these proteins. The accuracy of disulfide connectivity pattern prediction, particularly for the proteins of higher-order connections, e.g., >3 bonds, is too low to effectively assist structure assembly simulations.

RESULTS

We propose a new hierarchical order reduction protocol called Cyscon for disulfide-bonding prediction. The most confident disulfide bonds are first identified and bonding prediction is then focused on the remaining cysteine residues based on SVR training. Compared with purely machine learning-based approaches, Cyscon improved the average accuracy of connectivity pattern prediction by 21.9%. For proteins with more than 5 disulfide bonds, Cyscon improved the accuracy by 585% on the benchmark set of PDBCYS. When applied to 158 non-redundant cysteine-rich proteins, Cyscon predictions helped increase (or decrease) the TM-score (or RMSD) of the ab initio QUARK modeling by 12.1% (or 14.4%). This result demonstrates a new avenue to improve the ab initio structure modeling for cysteine-rich proteins.

AVAILABILITY AND IMPLEMENTATION

http://www.csbio.sjtu.edu.cn/bioinf/Cyscon/

CONTACT

zhng@umich.edu or hbshen@sjtu.edu.cn.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Disulfide Connectivity Prediction Based on Modelled Protein 3D Structural Information and Random Forest Regression

Disulfide connectivity is an important protein structural characteristic. Accurately predicting disulfide connectivity solely from protein sequence helps to improve the intrinsic understanding of protein structure and function, especially in the post-genome era where large volume of sequenced proteins without being functional annotated is quickly accumulated. In this study, a new feature extracted from the predicted protein 3D structural information is proposed and integrated with traditional features to form discriminative features. Based on the extracted features, a random forest regression model is performed to predict protein disulfide connectivity. We compare the proposed method with popular existing predictors by performing both cross-validation and independent validation tests on benchmark datasets. The experimental results demonstrate the superiority of the proposed method over existing predictors. We believe the superiority of the proposed method benefits from both the good discriminative capability of the newly developed features and the powerful modelling capability of the random forest. The web server implementation, called TargetDisulfide, and the benchmark datasets are freely available at: http://csbio.njust.edu.cn/bioinf/TargetDisulfide for academic use.

Prediction of hot regions in protein-protein interaction by combining density-based incremental clustering with feature-based classification

Discovering hot regions in protein-protein interaction is important for drug and protein design, while experimental identification of hot regions is a time-consuming and labor-intensive effort; thus, the development of predictive models can be very helpful. In hot region prediction research, some models are based on structure information, and others are based on a protein interaction network. However, the prediction accuracy of these methods can still be improved. In this paper, a new method is proposed for hot region prediction, which combines density-based incremental clustering with feature-based classification. The method uses density-based incremental clustering to obtain rough hot regions, and uses feature-based classification to remove the non-hot spot residues from the rough hot regions. Experimental results show that the proposed method significantly improves the prediction performance of hot regions.

Prediction of protein solvent accessibility using PSO-SVR with multiple sequence-derived features and weighted sliding window scheme

BACKGROUND

The prediction of solvent accessibility could provide valuable clues for analyzing protein structure and functions, such as protein 3-Dimensional structure and B-cell epitope prediction. To fully decipher the protein-protein interaction process, an initial but crucial step is to calculate the protein solvent accessibility, especially when the tertiary structure of the protein is unknown. Although some efforts have been put into the protein solvent accessibility prediction, the performance of existing methods is far from satisfaction.

METHODS

In order to develop the high-accuracy model, we focus on some possible aspects concerning the prediction performance, including several sequence-derived features, a weighted sliding window scheme and the parameters optimization of machine learning approach. To address above issues, we take following strategies. Firstly, we explore various features which have been observed to be associated with the residue solvent accessibility. These discriminative features include protein evolutionary information, predicted protein secondary structure, native disorder, physicochemical propensities and several sequence-based structural descriptors of residues. Secondly, the different contributions of adjacent residues in sliding window are observed, thus a weighted sliding window scheme is proposed to differentiate the contributions of adjacent residues on the central residue. Thirdly, particle swarm optimization (PSO) is employed to search the global best parameters for the proposed predictor.

RESULTS

Evaluated by 3-fold cross-validation, our method achieves the mean absolute error (MAE) of 14.1% and the person correlation coefficient (PCC) of 0.75 for our new-compiled dataset. When compared with the state-of-the-art prediction models in the two benchmark datasets, our method demonstrates better performance. Experimental results demonstrate that our PSAP achieves high performances and outperforms many existing predictors. A web server called PSAP is built and freely available at http://59.73.198.144:8088/SolventAccessibility/.

PGluS: prediction of protein S-glutathionylation sites with multiple features and analysis

S-Glutathionylation is a reversible protein post-translational modification, which generates mixed disulfides between glutathione (GSH) and cysteine residues, playing an important role in regulating protein stability, activity, and redox regulation. To fully understand S-glutathionylation mechanisms, identification of substrates and specific S-glutathionylated sites is crucial. Compared with the labor-intensive and time-consuming experimental approaches, computational predictions of S-glutathionylated sites are very desirable due to their convenience and high speed. Therefore, in this study, a new bioinformatics tool named PGluS was developed to predict S-glutathionylated sites based on multiple features and support vector machines. The performance of PGluS was measured with an accuracy of 71.41% and a MCC of 0.431 using the 5-fold cross-validation on the training dataset. Additionally, PGluS was evaluated using an independent testing dataset resulting in an accuracy of 71.25%, which demonstrated that PGluS was very promising for predicting S-glutathionylated sites. Furthermore, feature analysis was performed and it was shown that all features adopted in this method contributed to the S-glutathionylation process. A site-specific analysis showed that S-glutathionylation was intimately correlated with the features derived from its surrounding sites. The conclusions derived from this study might help to understand more of the S-glutathionylation mechanism and guide the related experimental validation. For public access, PGluS is freely accessible at .

Large-scale protein-protein interactions detection by integrating big biosensing data with computational model

Protein-protein interactions are the basis of biological functions, and studying these interactions on a molecular level is of crucial importance for understanding the functionality of a living cell. During the past decade, biosensors have emerged as an important tool for the high-throughput identification of proteins and their interactions. However, the high-throughput experimental methods for identifying PPIs are both time-consuming and expensive. On the other hand, high-throughput PPI data are often associated with high false-positive and high false-negative rates. Targeting at these problems, we propose a method for PPI detection by integrating biosensor-based PPI data with a novel computational model. This method was developed based on the algorithm of extreme learning machine combined with a novel representation of protein sequence descriptor. When performed on the large-scale human protein interaction dataset, the proposed method achieved 84.8% prediction accuracy with 84.08% sensitivity at the specificity of 85.53%. We conducted more extensive experiments to compare the proposed method with the state-of-the-art techniques, support vector machine. The achieved results demonstrate that our approach is very promising for detecting new PPIs, and it can be a helpful supplement for biosensor-based PPI data detection.

Cascleave 2.0, a new approach for predicting caspase and granzyme cleavage targets

MOTIVATION

Caspases and granzyme B (GrB) are important proteases involved in fundamental cellular processes and play essential roles in programmed cell death, necrosis and inflammation. Although a number of substrates for both types have been experimentally identified, the complete repertoire of caspases and granzyme B substrates remained to be fully characterized. Accordingly, systematic bioinformatics studies of known cleavage sites may provide important insights into their substrate specificity and facilitate the discovery of novel substrates.

RESULTS

We develop a new bioinformatics tool, termed Cascleave 2.0, which builds on previous success of the Cascleave tool for predicting generic caspase cleavage sites. It can be efficiently used to predict potential caspase-specific cleavage sites for the human caspase-1, 3, 6, 7, 8 and GrB. In particular, we integrate heterogeneous sequence and protein functional information from various sources to improve the prediction accuracy of Cascleave 2.0. During classification, we use both maximum relevance minimum redundancy and forward feature selection techniques to quantify the relative contribution of each feature to prediction and thus remove redundant as well as irrelevant features. A systematic evaluation of Cascleave 2.0 using the benchmark data and comparison with other state-of-the-art tools using independent test data indicate that Cascleave 2.0 outperforms other tools on protease-specific cleavage site prediction of caspase-1, 3, 6, 7 and GrB. Cascleave 2.0 is anticipated to be used as a powerful tool for identifying novel substrates and cleavage sites of caspases and GrB and help understand the functional roles of these important proteases in human proteolytic cascades.

AVAILABILITY AND IMPLEMENTATION

http://www.structbioinfor.org/cascleave2/.

Disulfide connectivity prediction based on structural information without a prior knowledge of the bonding state of cysteines

Previous studies predicted the disulfide bonding patterns of cysteines using a prior knowledge of their bonding states. In this study, we propose a method that is based on the ensemble support vector machine (SVM), with the structural features of cysteines extracted without any prior knowledge of their bonding states. This method is useful for improving the predictive performance of disulfide bonding patterns. For comparison, the proposed method was tested with the same dataset SPX that was adopted in previous studies. The experimental results demonstrate that bridge classification and disulfide connectivity predictions achieve 96.5% and 89.2% accuracy, respectively, using the ensemble SVM model, which outperforms the traditional method (51.5% and 51.0%, respectively) and the model that is based on a single-kernel SVM classifier (94.6% and 84.4%, respectively). For protein chain and residue classifications, the sensitivity, specificity, and accuracy of ensemble and single-kernel SVM approaches are better than those of the traditional methods. The predictive performances of the ensemble SVM and single-kernel models are identical, indicating that the ensemble model can converge to the single-kernel model for some applications.

On the relevance of sophisticated structural annotations for disulfide connectivity pattern prediction

Disulfide bridges strongly constrain the native structure of many proteins and predicting their formation is therefore a key sub-problem of protein structure and function inference. Most recently proposed approaches for this prediction problem adopt the following pipeline: first they enrich the primary sequence with structural annotations, second they apply a binary classifier to each candidate pair of cysteines to predict disulfide bonding probabilities and finally, they use a maximum weight graph matching algorithm to derive the predicted disulfide connectivity pattern of a protein. In this paper, we adopt this three step pipeline and propose an extensive study of the relevance of various structural annotations and feature encodings. In particular, we consider five kinds of structural annotations, among which three are novel in the context of disulfide bridge prediction. So as to be usable by machine learning algorithms, these annotations must be encoded into features. For this purpose, we propose four different feature encodings based on local windows and on different kinds of histograms. The combination of structural annotations with these possible encodings leads to a large number of possible feature functions. In order to identify a minimal subset of relevant feature functions among those, we propose an efficient and interpretable feature function selection scheme, designed so as to avoid any form of overfitting. We apply this scheme on top of three supervised learning algorithms: k-nearest neighbors, support vector machines and extremely randomized trees. Our results indicate that the use of only the PSSM (position-specific scoring matrix) together with the CSP (cysteine separation profile) are sufficient to construct a high performance disulfide pattern predictor and that extremely randomized trees reach a disulfide pattern prediction accuracy of on the benchmark dataset SPX, which corresponds to improvement over the state of the art. A web-application is available at http://m24.giga.ulg.ac.be:81/x3CysBridges.

Prediction of S-glutathionylation sites based on protein sequences

S-glutathionylation, the reversible formation of mixed disulfides between glutathione(GSH) and cysteine residues in proteins, is a specific form of post-translational modification that plays important roles in various biological processes, including signal transduction, redox homeostasis, and metabolism inside cells. Experimentally identifying S-glutathionylation sites is labor-intensive and time consuming, whereas bioinformatics methods provide an alternative way to this problem by predicting S-glutathionylation sites in silico. The bioinformatics approaches give not only candidate sites for further experimental verification but also bio-chemical insights into the mechanism of S-glutathionylation. In this paper, we firstly collect experimentally determined S-glutathionylated proteins and their corresponding modification sites from the literature, and then propose a new method for predicting S-glutathionylation sites by employing machine learning methods based on protein sequence data. Promising results are obtained by our method with an AUC (area under ROC curve) score of 0.879 in 5-fold cross-validation, which demonstrates the predictive power of our proposed method. The datasets used in this work are available at http://csb.shu.edu.cn/SGDB.

Prediction of disulfide connectivity in proteins with machine-learning methods and correlated mutations

Background

Recently, information derived by correlated mutations in proteins has regained relevance for predicting protein contacts. This is due to new forms of mutual information analysis that have been proven to be more suitable to highlight direct coupling between pairs of residues in protein structures and to the large number of protein chains that are currently available for statistical validation. It was previously discussed that disulfide bond topology in proteins is also constrained by correlated mutations.

Results

In this paper we exploit information derived from a corrected mutual information analysis and from the inverse of the covariance matrix to address the problem of the prediction of the topology of disulfide bonds in Eukaryotes. Recently, we have shown that Support Vector Regression (SVR) can improve the prediction for the disulfide connectivity patterns. Here we show that the inclusion of the correlated mutation information increases of 5 percentage points the SVR performance (from 54% to 59%). When this approach is used in combination with a method previously developed by us and scoring at the state of art in predicting both location and topology of disulfide bonds in Eukaryotes (DisLocate), the per-protein accuracy is 38%, 2 percentage points higher than that previously obtained.

Conclusions

In this paper we show that the inclusion of information derived from correlated mutations can improve the performance of the state of the art methods for predicting disulfide connectivity patterns in Eukaryotic proteins. Our analysis also provides support to the notion that improving methods to extract evolutionary information from multiple sequence alignments greatly contributes to the scoring performance of predictors suited to detect relevant features from protein chains.

PROSPER: an integrated feature-based tool for predicting protease substrate cleavage sites

The ability to catalytically cleave protein substrates after synthesis is fundamental for all forms of life. Accordingly, site-specific proteolysis is one of the most important post-translational modifications. The key to understanding the physiological role of a protease is to identify its natural substrate(s). Knowledge of the substrate specificity of a protease can dramatically improve our ability to predict its target protein substrates, but this information must be utilized in an effective manner in order to efficiently identify protein substrates by in silico approaches. To address this problem, we present PROSPER, an integrated feature-based server for in silico identification of protease substrates and their cleavage sites for twenty-four different proteases. PROSPER utilizes established specificity information for these proteases (derived from the MEROPS database) with a machine learning approach to predict protease cleavage sites by using different, but complementary sequence and structure characteristics. Features used by PROSPER include local amino acid sequence profile, predicted secondary structure, solvent accessibility and predicted native disorder. Thus, for proteases with known amino acid specificity, PROSPER provides a convenient, pre-prepared tool for use in identifying protein substrates for the enzymes. Systematic prediction analysis for the twenty-four proteases thus far included in the database revealed that the features we have included in the tool strongly improve performance in terms of cleavage site prediction, as evidenced by their contribution to performance improvement in terms of identifying known cleavage sites in substrates for these enzymes. In comparison with two state-of-the-art prediction tools, PoPS and SitePrediction, PROSPER achieves greater accuracy and coverage. To our knowledge, PROSPER is the first comprehensive server capable of predicting cleavage sites of multiple proteases within a single substrate sequence using machine learning techniques. It is freely available at http://lightning.med.monash.edu.au/PROSPER/.

An integrative computational framework based on a two-step random forest algorithm improves prediction of zinc-binding sites in proteins

Zinc-binding proteins are the most abundant metalloproteins in the Protein Data Bank where the zinc ions usually have catalytic, regulatory or structural roles critical for the function of the protein. Accurate prediction of zinc-binding sites is not only useful for the inference of protein function but also important for the prediction of 3D structure. Here, we present a new integrative framework that combines multiple sequence and structural properties and graph-theoretic network features, followed by an efficient feature selection to improve prediction of zinc-binding sites. We investigate what information can be retrieved from the sequence, structure and network levels that is relevant to zinc-binding site prediction. We perform a two-step feature selection using random forest to remove redundant features and quantify the relative importance of the retrieved features. Benchmarking on a high-quality structural dataset containing 1,103 protein chains and 484 zinc-binding residues, our method achieved >80% recall at a precision of 75% for the zinc-binding residues Cys, His, Glu and Asp on 5-fold cross-validation tests, which is a 10%-28% higher recall at the 75% equal precision compared to SitePredict and zincfinder at residue level using the same dataset. The independent test also indicates that our method has achieved recall of 0.790 and 0.759 at residue and protein levels, respectively, which is a performance better than the other two methods. Moreover, AUC (the Area Under the Curve) and AURPC (the Area Under the Recall-Precision Curve) by our method are also respectively better than those of the other two methods. Our method can not only be applied to large-scale identification of zinc-binding sites when structural information of the target is available, but also give valuable insights into important features arising from different levels that collectively characterize the zinc-binding sites. The scripts and datasets are available at http://protein.cau.edu.cn/zincidentifier/.

CMD: A Database to Store the Bonding States of Cysteine Motifs with Secondary Structures

Computational approaches to the disulphide bonding state and its connectivity pattern prediction are based on various descriptors. One descriptor is the amino acid sequence motifs flanking the cysteine residue motifs. Despite the existence of disulphide bonding information in many databases and applications, there is no complete reference and motif query available at the moment. Cysteine motif database (CMD) is the first online resource that stores all cysteine residues, their flanking motifs with their secondary structure, and propensity values assignment derived from the laboratory data. We extracted more than 3 million cysteine motifs from PDB and UniProt data, annotated with secondary structure assignment, propensity value assignment, and frequency of occurrence and coefficiency of their bonding status. Removal of redundancies generated 15875 unique flanking motifs that are always bonded and 41577 unique patterns that are always nonbonded. Queries are based on the protein ID, FASTA sequence, sequence motif, and secondary structure individually or in batch format using the provided APIs that allow remote users to query our database via third party software and/or high throughput screening/querying. The CMD offers extensive information about the bonded, free cysteine residues, and their motifs that allows in-depth characterization of the sequence motif composition.

FunSAV: predicting the functional effect of single amino acid variants using a two-stage random forest model

Single amino acid variants (SAVs) are the most abundant form of known genetic variations associated with human disease. Successful prediction of the functional impact of SAVs from sequences can thus lead to an improved understanding of the underlying mechanisms of why a SAV may be associated with certain disease. In this work, we constructed a high-quality structural dataset that contained 679 high-quality protein structures with 2,048 SAVs by collecting the human genetic variant data from multiple resources and dividing them into two categories, i.e., disease-associated and neutral variants. We built a two-stage random forest (RF) model, termed as FunSAV, to predict the functional effect of SAVs by combining sequence, structure and residue-contact network features with other additional features that were not explored in previous studies. Importantly, a two-step feature selection procedure was proposed to select the most important and informative features that contribute to the prediction of disease association of SAVs. In cross-validation experiments on the benchmark dataset, FunSAV achieved a good prediction performance with the area under the curve (AUC) of 0.882, which is competitive with and in some cases better than other existing tools including SIFT, SNAP, Polyphen2, PANTHER, nsSNPAnalyzer and PhD-SNP. The sourcecodes of FunSAV and the datasets can be downloaded at http://sunflower.kuicr.kyoto-u.ac.jp/sjn/FunSAV.

Prediction of bioluminescent proteins using auto covariance transformation of evolutional profiles

Bioluminescent proteins are important for various cellular processes, such as gene expression analysis, drug discovery, bioluminescent imaging, toxicity determination, and DNA sequencing studies. Hence, the correct identification of bioluminescent proteins is of great importance both for helping genome annotation and providing a supplementary role to experimental research to obtain insight into bioluminescent proteins' functions. However, few computational methods are available for identifying bioluminescent proteins. Therefore, in this paper we develop a new method to predict bioluminescent proteins using a model based on position specific scoring matrix and auto covariance. Tested by 10-fold cross-validation and independent test, the accuracy of the proposed model reaches 85.17% for the training dataset and 90.71% for the testing dataset respectively. These results indicate that our predictor is a useful tool to predict bioluminescent proteins. This is the first study in which evolutionary information and local sequence environment information have been successfully integrated for predicting bioluminescent proteins. A web server (BLPre) that implements the proposed predictor is freely available.

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/.

Is there evidence of optimisation for carbon efficiency in plant proteomes?

Flowering plants, angiosperms, can be divided into two major clades, monocots and dicots, and while differences in amino acid composition in different species from the two clades have been reported, a systematic analysis of amino acid content and distribution remains outstanding. Here, we show that monocot and dicot proteins have developed distinct amino acid content. In Arabidopsis thaliana and poplar, as in the ancestral moss Physcomitrella patens, the average mass per amino acid appears to be independent of protein length, while in the monocots rice, maize and sorghum, shorter proteins tend to be made of lighter amino acids. An examination of the elemental content of these proteomes reveals that the difference between monocot and dicot proteins can be largely attributed to their different carbon signatures. In monocots, the shorter proteins, which comprise the majority of all proteins, are made of amino acids with less carbon, while the nitrogen content is unchanged in both monocots and dicots. We hypothesise that this signature could be the result of carbon use and energy optimisation in fast-growing annual Poaceae (grasses).

Improving the prediction of disulfide bonds in Eukaryotes with machine learning methods and protein subcellular localization

MOTIVATION

Disulfide bonds stabilize protein structures and play relevant roles in their functions. Their formation requires an oxidizing environment and their stability is consequently depending on the redox ambient potential, which may differ according to the subcellular compartment. Several methods are available to predict cysteine-bonding state and connectivity patterns. However, none of them takes into consideration the relevance of protein subcellular localization.

RESULTS

Here we develop DISLOCATE, a two-step method based on machine learning models for predicting both the bonding state and the connectivity patterns of cysteine residues in a protein chain. We find that the inclusion of protein subcellular localization improves the performance of these predictive steps by 3 and 2 percentage points, respectively. When compared with previously developed methods for predicting disulfide bonds from sequence, DISLOCATE improves the overall performance by more than 10 percentage points.

AVAILABILITY

The method and the dataset are available at the Web page http://www.biocomp.unibo.it/savojard/Dislocate.html. GRHCRF code is available at http://www.biocomp.unibo.it/savojard/biocrf.html.

CONTACT

piero.fariselli@unibo.it.

SOMPNN: an efficient non-parametric model for predicting transmembrane helices

Accurately predicting the transmembrane helices (TMH) in a helical membrane protein is an important but challenging task. Recent researches have demonstrated that statistics-based methods are promising routes to improve the TMH prediction accuracy. However, most of existing TMH predictors are parametric models and they have to make assumptions of several or even hundreds of adjustable parameters based on the underlying probability distribution, which is difficult when no a priori knowledge is available. Besides the performances of these parametric predictors significantly depend on the estimated parameters, some of them need to exploit the entire training dataset in the prediction stage, which will lead to low prediction efficiency and this problem will become even worse when dealing with large-scale dataset. In this paper, we propose a novel SOMPNN model for prediction of TMH that features by minimal parameter assumptions requirement and high computational efficiency. In the SOMPNN model, a self-organizing map (SOM) is used to adaptively learn the helices distribution knowledge hidden in the training data, and then a probabilistic neural network (PNN) is adopted to predict TMH segments based on the knowledge learned by SOM. Experimental results on two benchmark datasets show that the proposed SOMPNN outperforms most existing popular TMH predictors and is promising to be extended to deal with other complicated biological problems. The datasets and the source codes of SOMPNN are available at http://www.csbio.sjtu.edu.cn/bioinf/SOMPNN/.

Bioinformatic approaches for predicting substrates of proteases

Proteases have central roles in "life and death" processes due to their important ability to catalytically hydrolyze protein substrates, usually altering the function and/or activity of the target in the process. Knowledge of the substrate specificity of a protease should, in theory, dramatically improve the ability to predict target protein substrates. However, experimental identification and characterization of protease substrates is often difficult and time-consuming. Thus solving the "substrate identification" problem is fundamental to both understanding protease biology and the development of therapeutics that target specific protease-regulated pathways. In this context, bioinformatic prediction of protease substrates may provide useful and experimentally testable information about novel potential cleavage sites in candidate substrates. In this article, we provide an overview of recent advances in developing bioinformatic approaches for predicting protease substrate cleavage sites and identifying novel putative substrates. We discuss the advantages and drawbacks of the current methods and detail how more accurate models can be built by deriving multiple sequence and structural features of substrates. We also provide some suggestions about how future studies might further improve the accuracy of protease substrate specificity prediction.

Improving the accuracy of predicting disulfide connectivity by feature selection

Disulfide bonds are primary covalent cross-links formed between two cysteine residues in the same or different protein polypeptide chains, which play important roles in the folding and stability of proteins. However, computational prediction of disulfide connectivity directly from protein primary sequences is challenging due to the nonlocal nature of disulfide bonds in the context of sequences, and the number of possible disulfide patterns grows exponentially when the number of cysteine residues increases. In the previous studies, disulfide connectivity prediction was usually performed in high-dimensional feature space, which can cause a variety of problems in statistical learning, such as the dimension disaster, overfitting, and feature redundancy. In this study, we propose an efficient feature selection technique for analyzing the importance of each feature component. On the basis of this approach, we selected the most important features for predicting the connectivity pattern of intra-chain disulfide bonds. Our results have shown that the high-dimensional features contain redundant information, and the prediction performance can be further improved when these high-dimensional features are reduced to a lower but more compact dimensional space. Our results also indicate that the global protein features contribute little to the formation and prediction of disulfide bonds, while the local sequential and structural information play important roles. All these findings provide important insights for structural studies of disulfide-rich proteins.

Prediction of neurotoxins by support vector machine based on multiple feature vectors

Neurotoxin is a toxin which acts on nerve cells by interacting with membrane proteins. Different neurotoxins have different functions and sources. With much more knowledge of neurotoxins it would be greatly helpful for the development of drug design. The support vector machine (SVM) was used to predict the neurotoxin based on multiple feature vector descriptors, including the amino acid composition, length of the protein sequence, weight of the protein and the evolution information described by position specific scoring matrix (PSSM). After a five-fold cross-validation procedure, the method achieved an accuracy of 100% in discriminating neurotoxins from non-toxins. As for classifying neurotoxins based on their sources and functions, the accuracy was 99.50% and 99.38% respectively. At last, the method yielded a good performance in sub-classification of ion channels inhibitors with the total accuracy of 87.27%. These results indicate that this method outperforms previously described NTXpred method.

DBCP: a web server for disulfide bonding connectivity pattern prediction without the prior knowledge of the bonding state of cysteines

The proper prediction of the location of disulfide bridges is efficient in helping to solve the protein folding problem. Most of the previous works on the prediction of disulfide connectivity pattern use the prior knowledge of the bonding state of cysteines. The DBCP web server provides prediction of disulfide bonding connectivity pattern without the prior knowledge of the bonding state of cysteines. The method used in this server improves the accuracy of disulfide connectivity pattern prediction (Q_p) over the previous studies reported in the literature. This DBCP server can be accessed at http://120.107.8.16/dbcp or http://140.120.14.136/dbcp.

Learning gene regulatory networks from only positive and unlabeled data

Background

Recently, supervised learning methods have been exploited to reconstruct gene regulatory networks from gene expression data. The reconstruction of a network is modeled as a binary classification problem for each pair of genes. A statistical classifier is trained to recognize the relationships between the activation profiles of gene pairs. This approach has been proven to outperform previous unsupervised methods. However, the supervised approach raises open questions. In particular, although known regulatory connections can safely be assumed to be positive training examples, obtaining negative examples is not straightforward, because definite knowledge is typically not available that a given pair of genes do not interact.

Results

A recent advance in research on data mining is a method capable of learning a classifier from only positive and unlabeled examples, that does not need labeled negative examples. Applied to the reconstruction of gene regulatory networks, we show that this method significantly outperforms the current state of the art of machine learning methods. We assess the new method using both simulated and experimental data, and obtain major performance improvement.

Conclusions

Compared to unsupervised methods for gene network inference, supervised methods are potentially more accurate, but for training they need a complete set of known regulatory connections. A supervised method that can be trained using only positive and unlabeled data, as presented in this paper, is especially beneficial for the task of inferring gene regulatory networks, because only an incomplete set of known regulatory connections is available in public databases such as RegulonDB, TRRD, KEGG, Transfac, and IPA.

APIS: accurate prediction of hot spots in protein interfaces by combining protrusion index with solvent accessibility

BACKGROUND

It is well known that most of the binding free energy of protein interaction is contributed by a few key hot spot residues. These residues are crucial for understanding the function of proteins and studying their interactions. Experimental hot spots detection methods such as alanine scanning mutagenesis are not applicable on a large scale since they are time consuming and expensive. Therefore, reliable and efficient computational methods for identifying hot spots are greatly desired and urgently required.

RESULTS

In this work, we introduce an efficient approach that uses support vector machine (SVM) to predict hot spot residues in protein interfaces. We systematically investigate a wide variety of 62 features from a combination of protein sequence and structure information. Then, to remove redundant and irrelevant features and improve the prediction performance, feature selection is employed using the F-score method. Based on the selected features, nine individual-feature based predictors are developed to identify hot spots using SVMs. Furthermore, a new ensemble classifier, namely APIS (A combined model based on Protrusion Index and Solvent accessibility), is developed to further improve the prediction accuracy. The results on two benchmark datasets, ASEdb and BID, show that this proposed method yields significantly better prediction accuracy than those previously published in the literature. In addition, we also demonstrate the predictive power of our proposed method by modelling two protein complexes: the calmodulin/myosin light chain kinase complex and the heat shock locus gene products U and V complex, which indicate that our method can identify more hot spots in these two complexes compared with other state-of-the-art methods.

CONCLUSION

We have developed an accurate prediction model for hot spot residues, given the structure of a protein complex. A major contribution of this study is to propose several new features based on the protrusion index of amino acid residues, which has been shown to significantly improve the prediction performance of hot spots. Moreover, we identify a compact and useful feature subset that has an important implication for identifying hot spot residues. Our results indicate that these features are more effective than the conventional evolutionary conservation, pairwise residue potentials and other traditional features considered previously, and that the combination of our and traditional features may support the creation of a discriminative feature set for efficient prediction of hot spot residues. The data and source code are available on web site http://home.ustc.edu.cn/~jfxia/hotspot.html.

Cascleave: towards more accurate prediction of caspase substrate cleavage sites

MOTIVATION

The caspase family of cysteine proteases play essential roles in key biological processes such as programmed cell death, differentiation, proliferation, necrosis and inflammation. The complete repertoire of caspase substrates remains to be fully characterized. Accordingly, systematic computational screening studies of caspase substrate cleavage sites may provide insight into the substrate specificity of caspases and further facilitating the discovery of putative novel substrates.

RESULTS

In this article we develop an approach (termed Cascleave) to predict both classical (i.e. following a P(1) Asp) and non-typical caspase cleavage sites. When using local sequence-derived profiles, Cascleave successfully predicted 82.2% of the known substrate cleavage sites, with a Matthews correlation coefficient (MCC) of 0.667. We found that prediction performance could be further improved by incorporating information such as predicted solvent accessibility and whether a cleavage sequence lies in a region that is most likely natively unstructured. Novel bi-profile Bayesian signatures were found to significantly improve the prediction performance and yielded the best performance with an overall accuracy of 87.6% and a MCC of 0.747, which is higher accuracy than published methods that essentially rely on amino acid sequence alone. It is anticipated that Cascleave will be a powerful tool for predicting novel substrate cleavage sites of caspases and shedding new insights on the unknown caspase-substrate interactivity relationship.

AVAILABILITY

http://sunflower.kuicr.kyoto-u.ac.jp/ approximately sjn/Cascleave/

CONTACT

jiangning.song@med.monash.edu.au; takutsu@kuicr.kyoto-u.ac.jp; james; whisstock@med.monash.edu.au

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prediction of protein binding sites in protein structures using hidden Markov support vector machine

Background

Predicting the binding sites between two interacting proteins provides important clues to the function of a protein. Recent research on protein binding site prediction has been mainly based on widely known machine learning techniques, such as artificial neural networks, support vector machines, conditional random field, etc. However, the prediction performance is still too low to be used in practice. It is necessary to explore new algorithms, theories and features to further improve the performance.

Results

In this study, we introduce a novel machine learning model hidden Markov support vector machine for protein binding site prediction. The model treats the protein binding site prediction as a sequential labelling task based on the maximum margin criterion. Common features derived from protein sequences and structures, including protein sequence profile and residue accessible surface area, are used to train hidden Markov support vector machine. When tested on six data sets, the method based on hidden Markov support vector machine shows better performance than some state-of-the-art methods, including artificial neural networks, support vector machines and conditional random field. Furthermore, its running time is several orders of magnitude shorter than that of the compared methods.

Conclusion

The improved prediction performance and computational efficiency of the method based on hidden Markov support vector machine can be attributed to the following three factors. Firstly, the relation between labels of neighbouring residues is useful for protein binding site prediction. Secondly, the kernel trick is very advantageous to this field. Thirdly, the complexity of the training step for hidden Markov support vector machine is linear with the number of training samples by using the cutting-plane algorithm.

Prodepth: predict residue depth by support vector regression approach from protein sequences only

Residue depth (RD) is a solvent exposure measure that complements the information provided by conventional accessible surface area (ASA) and describes to what extent a residue is buried in the protein structure space. Previous studies have established that RD is correlated with several protein properties, such as protein stability, residue conservation and amino acid types. Accurate prediction of RD has many potentially important applications in the field of structural bioinformatics, for example, facilitating the identification of functionally important residues, or residues in the folding nucleus, or enzyme active sites from sequence information. In this work, we introduce an efficient approach that uses support vector regression to quantify the relationship between RD and protein sequence. We systematically investigated eight different sequence encoding schemes including both local and global sequence characteristics and examined their respective prediction performances. For the objective evaluation of our approach, we used 5-fold cross-validation to assess the prediction accuracies and showed that the overall best performance could be achieved with a correlation coefficient (CC) of 0.71 between the observed and predicted RD values and a root mean square error (RMSE) of 1.74, after incorporating the relevant multiple sequence features. The results suggest that residue depth could be reliably predicted solely from protein primary sequences: local sequence environments are the major determinants, while global sequence features could influence the prediction performance marginally. We highlight two examples as a comparison in order to illustrate the applicability of this approach. We also discuss the potential implications of this new structural parameter in the field of protein structure prediction and homology modeling. This method might prove to be a powerful tool for sequence analysis.