Using principal component analysis and support vector machine to predict protein structural class for low-similarity sequences via PSSM

CRISPRCasStack: a stacking strategy-based ensemble learning framework for accurate identification of Cas proteins

CRISPR-Cas system is an adaptive immune system widely found in most bacteria and archaea to defend against exogenous gene invasion. One of the most critical steps in the study of exploring and classifying novel CRISPR-Cas systems and their functional diversity is the identification of Cas proteins in CRISPR-Cas systems. The discovery of novel Cas proteins has also laid the foundation for technologies such as CRISPR-Cas-based gene editing and gene therapy. Currently, accurate and efficient screening of Cas proteins from metagenomic sequences and proteomic sequences remains a challenge. For Cas proteins with low sequence conservation, existing tools for Cas protein identification based on homology cannot guarantee identification accuracy and efficiency. In this paper, we have developed a novel stacking-based ensemble learning framework for Cas protein identification, called CRISPRCasStack. In particular, we applied the SHAP (SHapley Additive exPlanations) method to analyze the features used in CRISPRCasStack. Sufficient experimental validation and independent testing have demonstrated that CRISPRCasStack can address the accuracy deficiencies and inefficiencies of the existing state-of-the-art tools. We also provide a toolkit to accurately identify and analyze potential Cas proteins, Cas operons, CRISPR arrays and CRISPR-Cas locus in prokaryotic sequences. The CRISPRCasStack toolkit is available at https://github.com/yrjia1015/CRISPRCasStack.

PSSMCOOL: A Comprehensive R Package for Generating Evolutionary-based Descriptors of Protein Sequences from PSSM Profiles

Position-specific scoring matrix (PSSM), also called profile, is broadly used for representing the evolutionary history of a given protein sequence. Several investigations reported that the PSSM-based feature descriptors can improve the prediction of various protein attributes such as interaction, function, subcellular localization, secondary structure, disorder regions, and accessible surface area. While plenty of algorithms have been suggested for extracting evolutionary features from PSSM in recent years, there is not any integrated standalone tool for providing these descriptors. Here, we introduce PSSMCOOL, a flexible comprehensive R package that generates 38 PSSM-based feature vectors. To our best knowledge, PSSMCOOL is the first PSSM-based feature extraction tool implemented in R. With the growing demand for exploiting machine-learning algorithms in computational biology, this package would be a practical tool for machine-learning predictions.

VTP-Identifier: Vesicular Transport Proteins Identification Based on PSSM Profiles and XGBoost

Vesicular transport proteins are related to many human diseases, and they threaten human health when they undergo pathological changes. Protein function prediction has been one of the most in-depth topics in bioinformatics. In this work, we developed a useful tool to identify vesicular transport proteins. Our strategy is to extract transition probability composition, autocovariance transformation and other information from the position-specific scoring matrix as feature vectors. EditedNearesNeighbours (ENN) is used to address the imbalance of the data set, and the Max-Relevance-Max-Distance (MRMD) algorithm is adopted to reduce the dimension of the feature vector. We used 5-fold cross-validation and independent test sets to evaluate our model. On the test set, VTP-Identifier presented a higher performance compared with GRU. The accuracy, Matthew's correlation coefficient (MCC) and area under the ROC curve (AUC) were 83.6%, 0.531 and 0.873, respectively.

Enhanced Protein Structural Class Prediction Using Effective Feature Modeling and Ensemble of Classifiers

Protein Secondary Structural Class (PSSC) information is important in investigating further challenges of protein sequences like protein fold recognition, protein tertiary structure prediction, and analysis of protein functions for drug discovery. Identification of PSSC using biological methods is time-consuming and cost-intensive. Several computational models have been developed to predict the structural class; however, they lack in generalization of the model. Hence, predicting PSSC based on protein sequences is still proving to be an uphill task. In this article, we proposed an effective, novel and generalized prediction model consisting of a feature modeling and an ensemble of classifiers. The proposed feature modeling extracts discriminating information (features) by leveraging three techniques: (i) Embedding - features are extracted on the basis of spatial residue arrangements of the sequences using word embedding approaches; (ii) SkipXGram Bi-gram - various sets of skipped bi-gram features are extracted from the sequences; and (iii) General Statistical (GS) based features are extracted which covers the global information of structural sequences. The combined effective sets of features are trained and classified using an ensemble of three classifiers: Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Machines (GBM). The proposed model when assessed on five benchmark datasets (high and low sequence similarity), viz. z277, z498, 25PDB, 1189, and FC699, reported an overall accuracy of 93.55, 97.58, 81.82, 81.11, and 93.93 percent respectively. The proposed model is further validated on a large-scale updated low similarity ( ≤ 25%) dataset, where it achieved an overall accuracy of 81.11 percent. The proposed generalized model is robust and consistently outperformed several state-of-the-art models on all the five benchmark datasets.

Structural classification of proteins based on the computationally efficient recurrence quantification analysis and horizontal visibility graphs

MOTIVATION

Protein structural class prediction is one of the most significant problems in bioinformatics, as it has a prominent role in understanding the function and evolution of proteins. Designing a computationally efficient but at the same time accurate prediction method remains a pressing issue, especially for sequences that we cannot obtain a sufficient amount of homologous information from existing protein sequence databases. Several studies demonstrate the potential of utilizing chaos game representation (CGR) along with time series analysis tools such as recurrence quantification analysis (RQA), complex networks, horizontal visibility graphs (HVG) and others. However, the majority of existing works involve a large amount of features and they require an exhaustive, time consuming search of the optimal parameters. To address the aforementioned problems, this work adopts the generalized multidimensional recurrence quantification analysis (GmdRQA) as an efficient tool that enables to process concurrently a multidimensional time series and reduce the number of features. In addition, two data-driven algorithms, namely average mutual information (AMI) and false nearest neighbors (FNN), are utilized to define in a fast yet precise manner the optimal GmdRQA parameters.

RESULTS

The classification accuracy is improved by the combination of GmdRQA with the HVG. Experimental evaluation on a real benchmark dataset demonstrates that our methods achieve similar performance with the state-of-the-art but with a smaller computational cost.

AVAILABILITY

The code to reproduce all the results is available at https://github.com/aretiz/protein_structure_classification/tree/main.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Variable selection from a feature representing protein sequences: a case of classification on bacterial type IV secreted effectors

Background

Classification of certain proteins with specific functions is momentous for biological research. Encoding approaches of protein sequences for feature extraction play an important role in protein classification. Many computational methods (namely classifiers) are used for classification on protein sequences according to various encoding approaches. Commonly, protein sequences keep certain labels corresponding to different categories of biological functions (e.g., bacterial type IV secreted effectors or not), which makes protein prediction a fantasy. As to protein prediction, a kernel set of protein sequences keeping certain labels certified by biological experiments should be existent in advance. However, it has been hardly ever seen in prevailing researches. Therefore, unsupervised learning rather than supervised learning (e.g. classification) should be considered. As to protein classification, various classifiers may help to evaluate the effectiveness of different encoding approaches. Besides, variable selection from an encoded feature representing protein sequences is an important issue that also needs to be considered.

Results

Focusing on the latter problem, we propose a new method for variable selection from an encoded feature representing protein sequences. Taking a benchmark dataset containing 1947 protein sequences as a case, experiments are made to identify bacterial type IV secreted effectors (T4SE) from protein sequences, which are composed of 399 T4SE and 1548 non-T4SE. Comparable and quantified results are obtained only using certain components of the encoded feature, i.e., position-specific scoring matix, and that indicates the effectiveness of our method.

Conclusions

Certain variables other than an encoded feature they belong to do work for discrimination between different types of proteins. In addition, ensemble classifiers with an automatic assignment of different base classifiers do achieve a better classification result.

PeNGaRoo, a combined gradient boosting and ensemble learning framework for predicting non-classical secreted proteins

MOTIVATION

Gram-positive bacteria have developed secretion systems to transport proteins across their cell wall, a process that plays an important role during host infection. These secretion mechanisms have also been harnessed for therapeutic purposes in many biotechnology applications. Accordingly, the identification of features that select a protein for efficient secretion from these microorganisms has become an important task. Among all the secreted proteins, 'non-classical' secreted proteins are difficult to identify as they lack discernable signal peptide sequences and can make use of diverse secretion pathways. Currently, several computational methods have been developed to facilitate the discovery of such non-classical secreted proteins; however, the existing methods are based on either simulated or limited experimental datasets. In addition, they often employ basic features to train the models in a simple and coarse-grained manner. The availability of more experimentally validated datasets, advanced feature engineering techniques and novel machine learning approaches creates new opportunities for the development of improved predictors of 'non-classical' secreted proteins from sequence data.

RESULTS

In this work, we first constructed a high-quality dataset of experimentally verified 'non-classical' secreted proteins, which we then used to create benchmark datasets. Using these benchmark datasets, we comprehensively analyzed a wide range of features and assessed their individual performance. Subsequently, we developed a two-layer Light Gradient Boosting Machine (LightGBM) ensemble model that integrates several single feature-based models into an overall prediction framework. At this stage, LightGBM, a gradient boosting machine, was used as a machine learning approach and the necessary parameter optimization was performed by a particle swarm optimization strategy. All single feature-based LightGBM models were then integrated into a unified ensemble model to further improve the predictive performance. Consequently, the final ensemble model achieved a superior performance with an accuracy of 0.900, an F-value of 0.903, Matthew's correlation coefficient of 0.803 and an area under the curve value of 0.963, and outperforming previous state-of-the-art predictors on the independent test. Based on our proposed optimal ensemble model, we further developed an accessible online predictor, PeNGaRoo, to serve users' demands. We believe this online web server, together with our proposed methodology, will expedite the discovery of non-classically secreted effector proteins in Gram-positive bacteria and further inspire the development of next-generation predictors.

AVAILABILITY AND IMPLEMENTATION

http://pengaroo.erc.monash.edu/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

FCTP-WSRC: Protein-Protein Interactions Prediction via Weighted Sparse Representation Based Classification

The task of predicting protein–protein interactions (PPIs) has been essential in the context of understanding biological processes. This paper proposes a novel computational model namely FCTP-WSRC to predict PPIs effectively. Initially, combinations of the F-vector, composition (C) and transition (T) are used to map each protein sequence onto numeric feature vectors. Afterwards, an effective feature extraction method PCA (principal component analysis) is employed to reconstruct the most discriminative feature subspaces, which is subsequently used as input in weighted sparse representation based classification (WSRC) for prediction. The FCTP-WSRC model achieves accuracies of 96.67%, 99.82%, and 98.09% for H. pylori, Human and Yeast datasets respectively. Furthermore, the FCTP-WSRC model performs well when predicting three significant PPIs networks: the single-core network (CD9), the multiple-core network (Ras-Raf-Mek-Erk-Elk-Srf pathway), and the cross-connection network (Wnt-related Network). Consequently, the promising results show that the proposed method can be a powerful tool for PPIs prediction with excellent performance and less time.

Identification of amyloidogenic peptides via optimized integrated features space based on physicochemical properties and PSSM

At present, the identification of amyloid becomes more and more essential and meaningful. Because its mis-aggregation may cause some diseases such as Alzheimer's and Parkinson's diseases. This paper focus on the classification of amyloidogenic peptides and a novel feature representation called PhyAve_PSSMDwt is proposed. It includes two parts. One is based on physicochemical properties involving hydrophilicity, hydrophobicity, aggregation tendency, packing density and H-bonding which extracts 15-dimensional features in total. And the other is 60-dimensional features through recursive feature elimination from PSSM by discrete wavelet transform. In this period, sliding window is introduced to reconstruct PSSM so that the evolutionary information of short sequences can still be extracted. At last, the support vector machine is adopted as a classifier. The experimental result on Pep424 dataset shows that PSSM's information makes a great contribution on performance. And compared with other existing methods, our results after cross-validation increase by 3.1%, 3.3%, 0.136 and 0.007 in accuracy, specificity, Matthew's correlation coefficient and AUC value, respectively. It indicates that our method is effective and competitive.

DP-BINDER: machine learning model for prediction of DNA-binding proteins by fusing evolutionary and physicochemical information

DNA-binding proteins (DBPs) participate in various biological processes including DNA replication, recombination, and repair. In the human genome, about 6-7% of these proteins are utilized for genes encoding. DBPs shape the DNA into a compact structure known chromatin while some of these proteins regulate the chromosome packaging and transcription process. In the pharmaceutical industry, DBPs are used as a key component of antibiotics, steroids, and cancer drugs. These proteins also involve in biophysical, biological, and biochemical studies of DNA. Due to the crucial role in various biological activities, identification of DBPs is a hot issue in protein science. A series of experimental and computational methods have been proposed, however, some methods didn't achieve the desired results while some are inadequate in its accuracy and authenticity. Still, it is highly desired to present more intelligent computational predictors. In this work, we introduce an innovative computational method namely DP-BINDER based on physicochemical and evolutionary information. We captured local highly decisive features from physicochemical properties of primary protein sequences via normalized Moreau-Broto autocorrelation (NMBAC) and evolutionary information by position specific scoring matrix-transition probability composition (PSSM-TPC) and pseudo-position specific scoring matrix (PsePSSM) using training and independent datasets. The optimal features were selected by the support vector machine-recursive feature elimination and correlation bias reduction (SVM-RFE + CBR) from fused features and were fed into random forest (RF) and support vector machine (SVM). Our method attained 92.46% and 89.58% accuracy with jackknife and ten-fold cross-validation, respectively on the training dataset, while 81.17% accuracy on the independent dataset for prediction of DBPs. These results demonstrate that our method attained the highest success rate in the literature. The superiority of DP-BINDER over existing approaches due to several reasons including abstraction of local dominant features via effective feature descriptors, utilization of appropriate feature selection algorithms and effective classifier.

Bastion3: a two-layer ensemble predictor of type III secreted effectors

MOTIVATION

Type III secreted effectors (T3SEs) can be injected into host cell cytoplasm via type III secretion systems (T3SSs) to modulate interactions between Gram-negative bacterial pathogens and their hosts. Due to their relevance in pathogen-host interactions, significant computational efforts have been put toward identification of T3SEs and these in turn have stimulated new T3SE discoveries. However, as T3SEs with new characteristics are discovered, these existing computational tools reveal important limitations: (i) most of the trained machine learning models are based on the N-terminus (or incorporating also the C-terminus) instead of the proteins' complete sequences, and (ii) the underlying models (trained with classic algorithms) employed only few features, most of which were extracted based on sequence-information alone. To achieve better T3SE prediction, we must identify more powerful, informative features and investigate how to effectively integrate these into a comprehensive model.

RESULTS

In this work, we present Bastion3, a two-layer ensemble predictor developed to accurately identify type III secreted effectors from protein sequence data. In contrast with existing methods that employ single models with few features, Bastion3 explores a wide range of features, from various types, trains single models based on these features and finally integrates these models through ensemble learning. We trained the models using a new gradient boosting machine, LightGBM and further boosted the models' performances through a novel genetic algorithm (GA) based two-step parameter optimization strategy. Our benchmark test demonstrates that Bastion3 achieves a much better performance compared to commonly used methods, with an ACC value of 0.959, F-value of 0.958, MCC value of 0.917 and AUC value of 0.956, which comprehensively outperformed all other toolkits by more than 5.6% in ACC value, 5.7% in F-value, 12.4% in MCC value and 5.8% in AUC value. Based on our proposed two-layer ensemble model, we further developed a user-friendly online toolkit, maximizing convenience for experimental scientists toward T3SE prediction. With its design to ease future discoveries of novel T3SEs and improved performance, Bastion3 is poised to become a widely used, state-of-the-art toolkit for T3SE prediction.

AVAILABILITY AND IMPLEMENTATION

http://bastion3.erc.monash.edu/.

CONTACT

selkrig@embl.de or wyztli@163.com or or trevor.lithgow@monash.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

POSSUM: a bioinformatics toolkit for generating numerical sequence feature descriptors based on PSSM profiles

Summary

Evolutionary information in the form of a Position-Specific Scoring Matrix (PSSM) is a widely used and highly informative representation of protein sequences. Accordingly, PSSM-based feature descriptors have been successfully applied to improve the performance of various predictors of protein attributes. Even though a number of algorithms have been proposed in previous studies, there is currently no universal web server or toolkit available for generating this wide variety of descriptors. Here, we present POSSUM ( Po sition- S pecific S coring matrix-based feat u re generator for m achine learning), a versatile toolkit with an online web server that can generate 21 types of PSSM-based feature descriptors, thereby addressing a crucial need for bioinformaticians and computational biologists. We envisage that this comprehensive toolkit will be widely used as a powerful tool to facilitate feature extraction, selection, and benchmarking of machine learning-based models, thereby contributing to a more effective analysis and modeling pipeline for bioinformatics research.

Availability and implementation

http://possum.erc.monash.edu/ .

Contact

trevor.lithgow@monash.edu or jiangning.song@monash.edu.

Supplementary information

Supplementary data are available at Bioinformatics online.

Prediction of zinc binding sites in proteins using sequence derived information

Zinc is one the most abundant catalytic cofactor and also an important structural component of a large number of metallo-proteins. Hence prediction of zinc metal binding sites in proteins can be a significant step in annotation of molecular function of a large number of proteins. Majority of existing methods for zinc-binding site predictions are based on a data-set of proteins, which has been compiled nearly a decade ago. Hence there is a need to develop zinc-binding site prediction system using the current updated data to include recently added proteins. Herein, we propose a support vector machine-based method, named as ZincBinder, for prediction of zinc metal-binding site in a protein using sequence profile information. The predictor was trained using fivefold cross validation approach and achieved 85.37% sensitivity with 86.20% specificity during training. Benchmarking on an independent non-redundant data-set, which was not used during training, showed better performance of ZincBinder vis-à-vis existing methods. Executable versions, source code, sample datasets, and usage instructions are available at http://proteininformatics.org/mkumar/znbinder/.

Protein secondary structure prediction based on the fuzzy support vector machine with the hyperplane optimization

The prediction of the protein secondary structure is a crucial point in bioinformatics and related fields. In the last years, machine learning methods have become a valuable tool, achieving satisfactory results. However, the prediction accuracy needs to be further ameliorated. This paper proposes a new method based on an improved fuzzy support vector machine (FSVM) for the prediction of the secondary structure of proteins. Unlike traditional methods to set the membership function, it firstly constructs an approximate optimal separating hyperplane by iterating the class centers in the feature space. Then sample points close to this hyperplane are assigned with large membership values, while outliers with small membership values according to the K-nearest neighbor. And some sample points with low membership values are removed, reducing the training time and improving the prediction accuracy. To optimize the prediction results, our method also exploits information on sequence-based structural similarity. We used three databases (e.g. RS126, CB513 and data1199) to test this method, showing the achievement of 94.2%, 93.1%, 96.7% Q₃ accuracy and 91.7%, 89.7%, 94.1% SOV values for the three datasets, respectively. Overall, our method results are comparable to or often better than commonly used methods (Magnan & Baldi, 2014; Sheng et al., 2016) for secondary structure prediction.

An Alignment-Free Algorithm in Comparing the Similarity of Protein Sequences Based on Pseudo-Markov Transition Probabilities among Amino Acids

In this paper, we have proposed a novel alignment-free method for comparing the similarity of protein sequences. We first encode a protein sequence into a 440 dimensional feature vector consisting of a 400 dimensional Pseudo-Markov transition probability vector among the 20 amino acids, a 20 dimensional content ratio vector, and a 20 dimensional position ratio vector of the amino acids in the sequence. By evaluating the Euclidean distances among the representing vectors, we compare the similarity of protein sequences. We then apply this method into the ND5 dataset consisting of the ND5 protein sequences of 9 species, and the F10 and G11 datasets representing two of the xylanases containing glycoside hydrolase families, i.e., families 10 and 11. As a result, our method achieves a correlation coefficient of 0.962 with the canonical protein sequence aligner ClustalW in the ND5 dataset, much higher than those of other 5 popular alignment-free methods. In addition, we successfully separate the xylanases sequences in the F10 family and the G11 family and illustrate that the F10 family is more heat stable than the G11 family, consistent with a few previous studies. Moreover, we prove mathematically an identity equation involving the Pseudo-Markov transition probability vector and the amino acids content ratio vector.

Improving the Prediction of Protein Structural Class for Low-Similarity Sequences by Incorporating Evolutionaryand Structural Information

Protein structural class prediction is beneficial to study protein function, regulation and interactions. However, protein structural class prediction for low-similarity sequences (i.e., below 40% in pairwise sequence similarity) remains a challenging problem at present. In this study, a novel computational method is proposed to accurately predict protein structural class for low-similarity sequences. This method is based on support vector machine in conjunction with integrated features from evolutionary information generated with position specific iterative basic local alignment search tool (PSI-BLAST) and predicted secondary structure. Various prediction accuracies evaluated by the jackknife tests are reported on two widely-used low-similarity benchmark datasets (25PDB and 1189), reaching overall accuracies 89.3% and 87.9%, which are significantly higher than those achieved by state-of-the-art in protein structural class prediction. The experimental results suggest that our method could serve as an effective alternative to existing methods in protein structural classification, especially for low-similarity sequences.

A Novel Feature Extraction Method with Feature Selection to Identify Golgi-Resident Protein Types from Imbalanced Data

The Golgi Apparatus (GA) is a major collection and dispatch station for numerous proteins destined for secretion, plasma membranes and lysosomes. The dysfunction of GA proteins can result in neurodegenerative diseases. Therefore, accurate identification of protein subGolgi localizations may assist in drug development and understanding the mechanisms of the GA involved in various cellular processes. In this paper, a new computational method is proposed for identifying cis-Golgi proteins from trans-Golgi proteins. Based on the concept of Common Spatial Patterns (CSP), a novel feature extraction technique is developed to extract evolutionary information from protein sequences. To deal with the imbalanced benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is adopted. A feature selection method called Random Forest-Recursive Feature Elimination (RF-RFE) is employed to search the optimal features from the CSP based features and g-gap dipeptide composition. Based on the optimal features, a Random Forest (RF) module is used to distinguish cis-Golgi proteins from trans-Golgi proteins. Through the jackknife cross-validation, the proposed method achieves a promising performance with a sensitivity of 0.889, a specificity of 0.880, an accuracy of 0.885, and a Matthew's Correlation Coefficient (MCC) of 0.765, which remarkably outperforms previous methods. Moreover, when tested on a common independent dataset, our method also achieves a significantly improved performance. These results highlight the promising performance of the proposed method to identify Golgi-resident protein types. Furthermore, the CSP based feature extraction method may provide guidelines for protein function predictions.

Prediction of Protein Structural Classes for Low-Similarity Sequences Based on Consensus Sequence and Segmented PSSM

Prediction of protein structural classes for low-similarity sequences is useful for understanding fold patterns, regulation, functions, and interactions of proteins. It is well known that feature extraction is significant to prediction of protein structural class and it mainly uses protein primary sequence, predicted secondary structure sequence, and position-specific scoring matrix (PSSM). Currently, prediction solely based on the PSSM has played a key role in improving the prediction accuracy. In this paper, we propose a novel method called CSP-SegPseP-SegACP by fusing consensus sequence (CS), segmented PsePSSM, and segmented autocovariance transformation (ACT) based on PSSM. Three widely used low-similarity datasets (1189, 25PDB, and 640) are adopted in this paper. Then a 700-dimensional (700D) feature vector is constructed and the dimension is decreased to 224D by using principal component analysis (PCA). To verify the performance of our method, rigorous jackknife cross-validation tests are performed on 1189, 25PDB, and 640 datasets. Comparison of our results with the existing PSSM-based methods demonstrates that our method achieves the favorable and competitive performance. This will offer an important complementary to other PSSM-based methods for prediction of protein structural classes for low-similarity sequences.

Briefing in application of machine learning methods in ion channel prediction

In cells, ion channels are one of the most important classes of membrane proteins which allow inorganic ions to move across the membrane. A wide range of biological processes are involved and regulated by the opening and closing of ion channels. Ion channels can be classified into numerous classes and different types of ion channels exhibit different functions. Thus, the correct identification of ion channels and their types using computational methods will provide in-depth insights into their function in various biological processes. In this review, we will briefly introduce and discuss the recent progress in ion channel prediction using machine learning methods.

Customised fragments libraries for protein structure prediction based on structural class annotations

Background

Since experimental techniques are time and cost consuming, in silico protein structure prediction is essential to produce conformations of protein targets. When homologous structures are not available, fragment-based protein structure prediction has become the approach of choice. However, it still has many issues including poor performance when targets’ lengths are above 100 residues, excessive running times and sub-optimal energy functions. Taking advantage of the reliable performance of structural class prediction software, we propose to address some of the limitations of fragment-based methods by integrating structural constraints in their fragment selection process.

Results

Using Rosetta, a state-of-the-art fragment-based protein structure prediction package, we evaluated our proposed pipeline on 70 former CASP targets containing up to 150 amino acids. Using either CATH or SCOP-based structural class annotations, enhancement of structure prediction performance is highly significant in terms of both GDT_TS (at least +2.6, p-values < 0.0005) and RMSD (−0.4, p-values < 0.005). Although CATH and SCOP classifications are different, they perform similarly. Moreover, proteins from all structural classes benefit from the proposed methodology. Further analysis also shows that methods relying on class-based fragments produce conformations which are more relevant to user and converge quicker towards the best model as estimated by GDT_TS (up to 10% in average). This substantiates our hypothesis that usage of structurally relevant templates conducts to not only reducing the size of the conformation space to be explored, but also focusing on a more relevant area.

Conclusions

Since our methodology produces models the quality of which is up to 7% higher in average than those generated by a standard fragment-based predictor, we believe it should be considered before conducting any fragment-based protein structure prediction. Despite such progress, ab initio prediction remains a challenging task, especially for proteins of average and large sizes. Apart from improving search strategies and energy functions, integration of additional constraints seems a promising route, especially if they can be accurately predicted from sequence alone.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-015-0576-2) contains supplementary material, which is available to authorized users.

Predict protein structural class for low-similarity sequences by evolutionary difference information into the general form of Chou's pseudo amino acid composition

Knowledge of protein structural class plays an important role in characterizing the overall folding type of a given protein. At present, it is still a challenge to extract sequence information solely using protein sequence for protein structural class prediction with low similarity sequence in the current computational biology. In this study, a novel sequence representation method is proposed based on position specific scoring matrix for protein structural class prediction. By defined evolutionary difference formula, varying length proteins are expressed as uniform dimensional vectors, which can represent evolutionary difference information between the adjacent residues of a given protein. To perform and evaluate the proposed method, support vector machine and jackknife tests are employed on three widely used datasets, 25PDB, 1189 and 640 datasets with sequence similarity lower than 25%, 40% and 25%, respectively. Comparison of our results with the previous methods shows that our method may provide a promising method to predict protein structural class especially for low-similarity sequences.

PSSP-RFE: accurate prediction of protein structural class by recursive feature extraction from PSI-BLAST profile, physical-chemical property and functional annotations

Protein structure prediction is critical to functional annotation of the massively accumulated biological sequences, which prompts an imperative need for the development of high-throughput technologies. As a first and key step in protein structure prediction, protein structural class prediction becomes an increasingly challenging task. Amongst most homological-based approaches, the accuracies of protein structural class prediction are sufficiently high for high similarity datasets, but still far from being satisfactory for low similarity datasets, i.e., below 40% in pairwise sequence similarity. Therefore, we present a novel method for accurate and reliable protein structural class prediction for both high and low similarity datasets. This method is based on Support Vector Machine (SVM) in conjunction with integrated features from position-specific score matrix (PSSM), PROFEAT and Gene Ontology (GO). A feature selection approach, SVM-RFE, is also used to rank the integrated feature vectors through recursively removing the feature with the lowest ranking score. The definitive top features selected by SVM-RFE are input into the SVM engines to predict the structural class of a query protein. To validate our method, jackknife tests were applied to seven widely used benchmark datasets, reaching overall accuracies between 84.61% and 99.79%, which are significantly higher than those achieved by state-of-the-art tools. These results suggest that our method could serve as an accurate and cost-effective alternative to existing methods in protein structural classification, especially for low similarity datasets.

Proposing a highly accurate protein structural class predictor using segmentation-based features

BACKGROUND

Prediction of the structural classes of proteins can provide important information about their functionalities as well as their major tertiary structures. It is also considered as an important step towards protein structure prediction problem. Despite all the efforts have been made so far, finding a fast and accurate computational approach to solve protein structural class prediction problem still remains a challenging problem in bioinformatics and computational biology.

RESULTS

In this study we propose segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins. By applying SVM to our extracted features, for the first time we enhance the protein structural class prediction accuracy to over 90% and 85% for two popular low-homology benchmarks that have been widely used in the literature. We report 92.2% and 86.3% prediction accuracies for 25PDB and 1189 benchmarks which are respectively up to 7.9% and 2.8% better than previously reported results for these two benchmarks.

CONCLUSION

By proposing segmented distribution and segmented auto covariance feature extraction methods to capture local and global discriminatory information from evolutionary profiles and predicted secondary structure of the proteins, we are able to enhance the protein structural class prediction performance significantly.

Efficient and interpretable prediction of protein functional classes by correspondence analysis and compact set relations

Predicting protein functional classes such as localization sites and modifications plays a crucial role in function annotation. Given a tremendous amount of sequence data yielded from high-throughput sequencing experiments, the need of efficient and interpretable prediction strategies has been rapidly amplified. Our previous approach for subcellular localization prediction, PSLDoc, archives high overall accuracy for Gram-negative bacteria. However, PSLDoc is computational intensive due to incorporation of homology extension in feature extraction and probabilistic latent semantic analysis in feature reduction. Besides, prediction results generated by support vector machines are accurate but generally difficult to interpret.

In this work, we incorporate three new techniques to improve efficiency and interpretability. First, homology extension is performed against a compact non-redundant database using a fast search model to reduce running time. Second, correspondence analysis (CA) is incorporated as an efficient feature reduction to generate a clear visual separation of different protein classes. Finally, functional classes are predicted by a combination of accurate compact set (CS) relation and interpretable one-nearest neighbor (1-NN) algorithm. Besides localization data sets, we also apply a human protein kinase set to validate generality of our proposed method.

Experiment results demonstrate that our method make accurate prediction in a more efficient and interpretable manner. First, homology extension using a fast search on a compact database can greatly accelerate traditional running time up to twenty-five times faster without sacrificing prediction performance. This suggests that computational costs of many other predictors that also incorporate homology information can be largely reduced. In addition, CA can not only efficiently identify discriminative features but also provide a clear visualization of different functional classes. Moreover, predictions based on CS achieve 100% precision. When combined with 1-NN on unpredicted targets by CS, our method attains slightly better or comparable performance compared with the state-of-the-art systems.

Prediction of protein-protein interactions from amino acid sequences with ensemble extreme learning machines and principal component analysis

BACKGROUND

Protein-protein interactions (PPIs) play crucial roles in the execution of various cellular processes and form the basis of biological mechanisms. Although large amount of PPIs data for different species has been generated by high-throughput experimental techniques, current PPI pairs obtained with experimental methods cover only a fraction of the complete PPI networks, and further, the experimental methods for identifying PPIs are both time-consuming and expensive. Hence, it is urgent and challenging to develop automated computational methods to efficiently and accurately predict PPIs.

RESULTS

We present here a novel hierarchical PCA-EELM (principal component analysis-ensemble extreme learning machine) model to predict protein-protein interactions only using the information of protein sequences. In the proposed method, 11188 protein pairs retrieved from the DIP database were encoded into feature vectors by using four kinds of protein sequences information. Focusing on dimension reduction, an effective feature extraction method PCA was then employed to construct the most discriminative new feature set. Finally, multiple extreme learning machines were trained and then aggregated into a consensus classifier by majority voting. The ensembling of extreme learning machine removes the dependence of results on initial random weights and improves the prediction performance.

CONCLUSIONS

When performed on the PPI data of Saccharomyces cerevisiae, the proposed method achieved 87.00% prediction accuracy with 86.15% sensitivity at the precision of 87.59%. Extensive experiments are performed to compare our method with state-of-the-art techniques Support Vector Machine (SVM). Experimental results demonstrate that proposed PCA-EELM outperforms the SVM method by 5-fold cross-validation. Besides, PCA-EELM performs faster than PCA-SVM based method. Consequently, the proposed approach can be considered as a new promising and powerful tools for predicting PPI with excellent performance and less time.