On position-specific scoring matrix for protein function prediction

Robust ensemble of handcrafted and learned approaches for DNA-binding proteins

Purpose

Automatic DNA-binding protein (DNA-BP) classification is now an essential proteomic technology. Unfortunately, many systems reported in the literature are tested on only one or two datasets/tasks. The purpose of this study is to create the most optimal and universal system for DNA-BP classification, one that performs competitively across several DNA-BP classification tasks.

Design/methodology/approach

Efficient DNA-BP classifier systems require the discovery of powerful protein representations and feature extraction methods. Experiments were performed that combined and compared descriptors extracted from state-of-the-art matrix/image protein representations. These descriptors were trained on separate support vector machines (SVMs) and evaluated. Convolutional neural networks with different parameter settings were fine-tuned on two matrix representations of proteins. Decisions were fused with the SVMs using the weighted sum rule and evaluated to experimentally derive the most powerful general-purpose DNA-BP classifier system.

Findings

The best ensemble proposed here produced comparable, if not superior, classification results on a broad and fair comparison with the literature across four different datasets representing a variety of DNA-BP classification tasks, thereby demonstrating both the power and generalizability of the proposed system.

Originality/value

Most DNA-BP methods proposed in the literature are only validated on one (rarely two) datasets/tasks. In this work, the authors report the performance of our general-purpose DNA-BP system on four datasets representing different DNA-BP classification tasks. The excellent results of the proposed best classifier system demonstrate the power of the proposed approach. These results can now be used for baseline comparisons by other researchers in the field.

MK-FSVM-SVDD: A Multiple Kernel-based Fuzzy SVM Model for Predicting DNA-binding Proteins via Support Vector Data Description

Background:

Detecting DNA-binding proteins (DBPs) based on biological and chemical methods is time-consuming and expensive.

Objective:

In recent years, the rise of computational biology methods based on Machine Learning (ML) has greatly improved the detection efficiency of DBPs.

Method:

In this study, the Multiple Kernel-based Fuzzy SVM Model with Support Vector Data Description (MK-FSVM-SVDD) is proposed to predict DBPs. Firstly, sex features are extracted from the protein sequence. Secondly, multiple kernels are constructed via these sequence features. Then, multiple kernels are integrated by Centered Kernel Alignment-based Multiple Kernel Learning (CKA-MKL). Next, fuzzy membership scores of training samples are calculated with Support Vector Data Description (SVDD). FSVM is trained and employed to detect new DBPs.

Results:

Our model is evaluated on several benchmark datasets. Compared with other methods, MKFSVM- SVDD achieves best Matthew's Correlation Coefficient (MCC) on PDB186 (0.7250) and PDB2272 (0.5476).

Conclusion:

We can conclude that MK-FSVM-SVDD is more suitable than common SVM, as the classifier for DNA-binding proteins identification.

A protein structural study based on the centrality analysis of protein sequence feature networks

In this paper, we use network approaches to analyze the relations between protein sequence features for the top hierarchical classes of CATH and SCOP. We use fundamental connectivity measures such as correlation (CR), normalized mutual information rate (nMIR), and transfer entropy (TE) to analyze the pairwise-relationships between the protein sequence features, and use centrality measures to analyze weighted networks constructed from the relationship matrices. In the centrality analysis, we find both commonalities and differences between the different protein 3D structural classes. Results show that all top hierarchical classes of CATH and SCOP present strong non-deterministic interactions for the composition and arrangement features of Cystine (C), Methionine (M), Tryptophan (W), and also for the arrangement features of Histidine (H). The different protein 3D structural classes present different preferences in terms of their centrality distributions and significant features.

PepFun: Open Source Protocols for Peptide-Related Computational Analysis

Peptide research has increased during the last years due to their applications as biomarkers, therapeutic alternatives or as antigenic sub-units in vaccines. The implementation of computational resources have facilitated the identification of novel sequences, the prediction of properties, and the modelling of structures. However, there is still a lack of open source protocols that enable their straightforward analysis. Here, we present PepFun, a compilation of bioinformatics and cheminformatics functionalities that are easy to implement and customize for studying peptides at different levels: sequence, structure and their interactions with proteins. PepFun enables calculating multiple characteristics for massive sets of peptide sequences, and obtaining different structural observables derived from protein-peptide complexes. In addition, random or guided library design of peptide sequences can be customized for screening campaigns. The package has been created under the python language based on built-in functions and methods available in the open source projects BioPython and RDKit. We present two tutorials where we tested peptide binders of the MHC class II and the Granzyme B protease.

TMP- SSurface2: A Novel Deep Learning-Based Surface Accessibility Predictor for Transmembrane Protein Sequence

Transmembrane protein (TMP) is an important type of membrane protein that is involved in various biological membranes related biological processes. As major drug targets, TMPs’ surfaces are highly concerned to form the structural biases of their material-bindings for drugs or other biological molecules. However, the quantity of determinate TMP structures is still far less than the requirements, while artificial intelligence technologies provide a promising approach to accurately identify the TMP surfaces, merely depending on their sequences without any feature-engineering. For this purpose, we present an updated TMP surface residue predictor TMP-SSurface2 which achieved an even higher prediction accuracy compared to our previous version. The method uses an attention-enhanced Bidirectional Long Short Term Memory (BiLSTM) network, benefiting from its efficient learning capability, some useful latent information is abstracted from protein sequences, thus improving the Pearson correlation coefficients (CC) value performance of the old version from 0.58 to 0.66 on an independent test dataset. The results demonstrate that TMP-SSurface2 is efficient in predicting the surface of transmembrane proteins, representing new progress in transmembrane protein structure modeling based on primary sequences. TMP-SSurface2 is freely accessible at https://github.com/NENUBioCompute/TMP-SSurface-2.0.

PseKNC and Adaboost-Based Method for DNA-Binding Proteins Recognition

DNA-binding proteins are an essential part of the DNA. It also an integral component during life processes of various organisms, for instance, DNA recombination, replication, and so on. Recognition of such proteins helps medical researchers pinpoint the cause of disease. Traditional techniques of identifying DNA-binding proteins are expensive and time-consuming. Machine learning methods can identify these proteins quickly and efficiently. However, the accuracies of the existing related methods were not high enough. In this paper, we propose a framework to identify DNA-binding proteins. The proposed framework first uses PseKNC (ps), MomoKGap (mo), and MomoDiKGap (md) methods to combine three algorithms to extract features. Further, we apply Adaboost weight ranking to select optimal feature subsets from the above three types of features. Based on the selected features, three algorithms (k-nearest neighbor (knn), Support Vector Machine (SVM), and Random Forest (RF)) are applied to classify it. Finally, three predictors for identifying DNA-binding proteins are established, including [Formula: see text], [Formula: see text], [Formula: see text]. We utilize benchmark and independent datasets to train and evaluate the proposed framework. Three tests are performed, including Jackknife test, 10-fold cross-validation and independent test. Among them, the accuracy of ps+md is the highest. We named the model with the best result as psmdDBPs and applied it to identify DNA-binding proteins.

CrystalM: A Multi-View Fusion Approach for Protein Crystallization Prediction

Improving the accuracy of predicting protein crystallization is very important for protein crystallization projects, which is a critical step for the determination of protein structure by X-ray crystallography. At present, many machine learning methods are used to predict protein crystallization. Here, we use a novel feature combination to construct a SVM model in the prediction of protein crystallization, called as CrystalM. In this work, we extract six features to represent protein sequences, namely Average Block-Position specific scoring matrix (AVBlock-PSSM), Average Block-Secondary Structure (AVBlock-SS), Global Encoding (GE), Pseudo-Position specific scoring matrix (PsePSSM), Protscale, and Discrete Wavelet Transform-Position specific scoring matrix (DWT-PSSM). Moreover, we employ two training datasets (TRAIN3587 and TRAIN1500) and their corresponding independent test datasets (TEST3585 and TEST500) to evaluate CrystalM by feeding multi-view features into Support Vector Machine (SVM) classifier. Two training datasets are employed for five-fold cross validation, and two test datasets are separately used to test the corresponding datasets. Finally, we compare CrystalM with other existing methods in the performance. For the datasets of TRAIN3587 and TEST3585, CrystalM achieves best Accuracy (ACC), best Specificity (SP), and the same Mathew's correlation coefficient (MCC) as the previous outperforming methods in the five-fold cross validation. In particular, ACC, SP, and MCC have surpassed the existing methods in independent test, which proves the effectiveness of CrystalM. Meanwhile, ACC, SP, and MCC are higher than existing methods in the five-fold cross validation for TRAIN1500. Although the performance of independent test for TEST500 is not the best, CrystalM also has a certain predictability in the prediction of protein crystallization. In addition, we find that only choosing the first four features can improve the performance of prediction for TRAIN1500 and TEST500, not only in independent tests but also in five-fold cross validation. This phenomenon indicates that the latter two features can not effectively represent proteins of TRAIN1500 and TEST500. CrystalM is a sequence-based protein crystallization prediction method. The good performance on the datasets proves the effectiveness of CrystalM and the better performance on large datasets further demonstrates the stability and superiority of CrystalM.

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.

PaCRISPR: a server for predicting and visualizing anti-CRISPR proteins

Anti-CRISPRs are widespread amongst bacteriophage and promote bacteriophage infection by inactivating the bacterial host's CRISPR–Cas defence system. Identifying and characterizing anti-CRISPR proteins opens an avenue to explore and control CRISPR–Cas machineries for the development of new CRISPR–Cas based biotechnological and therapeutic tools. Past studies have identified anti-CRISPRs in several model phage genomes, but a challenge exists to comprehensively screen for anti-CRISPRs accurately and efficiently from genome and metagenome sequence data. Here, we have developed an ensemble learning based predictor, PaCRISPR, to accurately identify anti-CRISPRs from protein datasets derived from genome and metagenome sequencing projects. PaCRISPR employs different types of feature recognition united within an ensemble framework. Extensive cross-validation and independent tests show that PaCRISPR achieves a significantly more accurate performance compared with homology-based baseline predictors and an existing toolkit. The performance of PaCRISPR was further validated in discovering anti-CRISPRs that were not part of the training for PaCRISPR, but which were recently demonstrated to function as anti-CRISPRs for phage infections. Data visualization on anti-CRISPR relationships, highlighting sequence similarity and phylogenetic considerations, is part of the output from the PaCRISPR toolkit, which is freely available at http://pacrispr.erc.monash.edu/.

T4SE-XGB: Interpretable Sequence-Based Prediction of Type IV Secreted Effectors Using eXtreme Gradient Boosting Algorithm

Type IV secreted effectors (T4SEs) can be translocated into the cytosol of host cells via type IV secretion system (T4SS) and cause diseases. However, experimental approaches to identify T4SEs are time- and resource-consuming, and the existing computational tools based on machine learning techniques have some obvious limitations such as the lack of interpretability in the prediction models. In this study, we proposed a new model, T4SE-XGB, which uses the eXtreme gradient boosting (XGBoost) algorithm for accurate identification of type IV effectors based on optimal features based on protein sequences. After trying 20 different types of features, the best performance was achieved when all features were fed into XGBoost by the 5-fold cross validation in comparison with other machine learning methods. Then, the ReliefF algorithm was adopted to get the optimal feature set on our dataset, which further improved the model performance. T4SE-XGB exhibited highest predictive performance on the independent test set and outperformed other published prediction tools. Furthermore, the SHAP method was used to interpret the contribution of features to model predictions. The identification of key features can contribute to improved understanding of multifactorial contributors to host-pathogen interactions and bacterial pathogenesis. In addition to type IV effector prediction, we believe that the proposed framework can provide instructive guidance for similar studies to construct prediction methods on related biological problems. The data and source code of this study can be freely accessed at https://github.com/CT001002/T4SE-XGB.

Deep Robust Framework for Protein Function Prediction Using Variable-Length Protein Sequences

The order of amino acids in a protein sequence enables the protein to acquire a conformation suitable for performing functions, thereby motivating the need to analyze these sequences for predicting functions. Although machine learning based approaches are fast compared to methods using BLAST, FASTA, etc., they fail to perform well for long protein sequences (with more than 300 amino acids). In this paper, we introduce a novel method for construction of two separate feature sets for protein using bi-directional long short-term memory network based on the analysis of fixed 1) single-sized segments and 2) multi-sized segments. The model trained on the proposed feature set based on multi-sized segments is combined with the model trained using state-of-the-art Multi-label Linear Discriminant Analysis (MLDA) features to further improve the accuracy. Extensive evaluations using separate datasets for biological processes and molecular functions demonstrate not only improved results for long sequences, but also significantly improve the overall accuracy over state-of-the-art method. The single-sized approach produces an improvement of +3.37 percent for biological processes and +5.48 percent for molecular functions over the MLDA based classifier. The corresponding numbers for multi-sized approach are +5.38 and +8.00 percent. Combining the two models, the accuracy further improves to +7.41 and +9.21 percent, respectively.

Using Weighted Extreme Learning Machine Combined With Scale-Invariant Feature Transform to Predict Protein-Protein Interactions From Protein Evolutionary Information

Protein-Protein Interactions (PPIs) play an irreplaceable role in biological activities of organisms. Although many high-throughput methods are used to identify PPIs from different kinds of organisms, they have some shortcomings, such as high cost and time-consuming. To solve the above problems, computational methods are developed to predict PPIs. Thus, in this paper, we present a method to predict PPIs using protein sequences. First, protein sequences are transformed into Position Weight Matrix (PWM), in which Scale-Invariant Feature Transform (SIFT) algorithm is used to extract features. Then Principal Component Analysis (PCA) is applied to reduce the dimension of features. At last, Weighted Extreme Learning Machine (WELM) classifier is employed to predict PPIs and a series of evaluation results are obtained. In our method, since SIFT and WELM are used to extract features and classify respectively, we called the proposed method SIFT-WELM. When applying the proposed method on three well-known PPIs datasets of Yeast, Human and Helicobacter.pylori, the average accuracies of our method using five-fold cross validation are obtained as high as 94.83, 97.60 and 83.64 percent, respectively. In order to evaluate the proposed approach properly, we compare it with Support Vector Machine (SVM) classifier and other recent-developed methods in different aspects. Moreover, the training time of our method is greatly shortened, which is obviously superior to the previous methods, such as SVM, ACC, PCVMZM and so on.

Use Chou's 5-Step Rule to Predict DNA-Binding Proteins with Evolutionary Information

The knowledge of DNA-binding proteins would help to understand the functions of proteins better in cellular biological processes. Research on the prediction of DNA-binding proteins can promote the research of drug proteins and computer acidified drugs. In recent years, methods based on machine learning are usually used to predict proteins. Although great predicted performance can be achieved via current methods, researchers still need to invest more research in terms of the improvement of predicted performance. In this study, the prediction of DNA-binding proteins is studied from the perspective of evolutionary information and the support vector machine method. One machine learning model for predicting DNA-binding proteins based on evolutionary features by using Chou's 5-step rule is put forward. The results show that great predicted performance is obtained on benchmark dataset PDB1075 and independent dataset PDB186, achieving the accuracy of 86.05% and 75.30%, respectively. Thus, the method proposed is comparable to a certain degree, and it may work even better than other methods to some extent.

Prediction of oxidoreductase subfamily classes based on RFE-SND-CC-PSSM and machine learning methods

Oxidoreductase is an enzyme that widely exists in organisms. It plays an important role in cellular energy metabolism and biotransformation processes. Oxidoreductases have many subclasses with different functions, creating an important classification task in bioinformatics. In this paper, a dataset of 2640 oxidoreductase sequences was used to perform an analysis and comparison. The idea of dipeptides was introduced to process the Position Specific Score Matrix (PSSM), since each dipeptide consists of two amino acids and each column of PSSM corresponds to the information of one amino acid. Two kinds of dipeptide scores were proposed, the Standardization Normal Distribution PSSM (SND-PSSM) and the Correlation Coefficient PSSM (CC-PSSM). Recursive Feature Elimination (RFE) is used to extract features from the SND-PSSM and CC-PSSM, and the two sets of extracted features are combined to form a new feature matrix, the RFE-SND-CC-PSSM. The results show that, with the proposed method and a kernel-based nonlinear SVM classifier, the accuracy can reach 95.56% by the Jackknife test. Our method greatly improves the accuracy of oxidoreductase subclass prediction. Using this method to predict the categories of the 6 major types of enzymes effectively improves its prediction accuracy to 94.54%, indicating that this method has general applicability to other protein problems. The results show that our method is effective and universally applicable, and might be complementary to the existing methods.

Using Random Forest Model Combined With Gabor Feature to Predict Protein-Protein Interaction From Protein Sequence

Protein-protein interactions (PPIs) play a crucial role in the life cycles of living cells. Thus, it is important to understand the underlying mechanisms of PPIs. Although many high-throughput technologies have generated large amounts of PPI data in different organisms, the experiments for detecting PPIs are still costly and time-consuming. Therefore, novel computational methods are urgently needed for predicting PPIs. For this reason, developing a new computational method for predicting PPIs is drawing more and more attention. In this study, we proposed a novel computational method based on texture feature of protein sequence for predicting PPIs. Especially, the Gabor feature is used to extract texture feature and protein evolutionary information from Position-Specific Scoring Matrix, which is generated by Position-Specific Iterated Basic Local Alignment Search Tool. Then, random forest–based classifiers are used to infer the protein interactions. When performed on PPI data sets of yeast, human, and Helicobacter pylori, we obtained good results with average accuracies of 92.10%, 97.03%, and 86.45%, respectively. To better evaluate the proposed method, we compared Gabor feature, Discrete Cosine Transform, and Local Phase Quantization. Our results show that the proposed method is both feasible and stable and the Gabor feature descriptor is reliable in extracting protein sequence information. Furthermore, additional experiments have been conducted to predict PPIs of other 4 species data sets. The promising results indicate that our proposed method is both powerful and robust.

DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy

Virulence factors (VFs) enable pathogens to infect their hosts. A wealth of individual, disease-focused studies has identified a wide variety of VFs, and the growing mass of bacterial genome sequence data provides an opportunity for computational methods aimed at predicting VFs. Despite their attractive advantages and performance improvements, the existing methods have some limitations and drawbacks. Firstly, as the characteristics and mechanisms of VFs are continually evolving with the emergence of antibiotic resistance, it is more and more difficult to identify novel VFs using existing tools that were previously developed based on the outdated data sets; secondly, few systematic feature engineering efforts have been made to examine the utility of different types of features for model performances, as the majority of tools only focused on extracting very few types of features. By addressing the aforementioned issues, the accuracy of VF predictors can likely be significantly improved. This, in turn, would be particularly useful in the context of genome wide predictions of VFs. In this work, we present a deep learning (DL)-based hybrid framework (termed DeepVF) that is utilizing the stacking strategy to achieve more accurate identification of VFs. Using an enlarged, up-to-date dataset, DeepVF comprehensively explores a wide range of heterogeneous features with popular machine learning algorithms. Specifically, four classical algorithms, including random forest, support vector machines, extreme gradient boosting and multilayer perceptron, and three DL algorithms, including convolutional neural networks, long short-term memory networks and deep neural networks are employed to train 62 baseline models using these features. In order to integrate their individual strengths, DeepVF effectively combines these baseline models to construct the final meta model using the stacking strategy. Extensive benchmarking experiments demonstrate the effectiveness of DeepVF: it achieves a more accurate and stable performance compared with baseline models on the benchmark dataset and clearly outperforms state-of-the-art VF predictors on the independent test. Using the proposed hybrid ensemble model, a user-friendly online predictor of DeepVF (http://deepvf.erc.monash.edu/) is implemented. Furthermore, its utility, from the user's viewpoint, is compared with that of existing toolkits. We believe that DeepVF will be exploited as a useful tool for screening and identifying potential VFs from protein-coding gene sequences in bacterial genomes.

Systematic evaluation of machine learning methods for identifying human-pathogen protein-protein interactions

In recent years, high-throughput experimental techniques have significantly enhanced the accuracy and coverage of protein-protein interaction identification, including human-pathogen protein-protein interactions (HP-PPIs). Despite this progress, experimental methods are, in general, expensive in terms of both time and labour costs, especially considering that there are enormous amounts of potential protein-interacting partners. Developing computational methods to predict interactions between human and bacteria pathogen has thus become critical and meaningful, in both facilitating the detection of interactions and mining incomplete interaction maps. In this paper, we present a systematic evaluation of machine learning-based computational methods for human-bacterium protein-protein interactions (HB-PPIs). We first reviewed a vast number of publicly available databases of HP-PPIs and then critically evaluate the availability of these databases. Benefitting from its well-structured nature, we subsequently preprocess the data and identified six bacterium pathogens that could be used to study bacterium subjects in which a human was the host. Additionally, we thoroughly reviewed the literature on 'host-pathogen interactions' whereby existing models were summarized that we used to jointly study the impact of different feature representation algorithms and evaluate the performance of existing machine learning computational models. Owing to the abundance of sequence information and the limited scale of other protein-related information, we adopted the primary protocol from the literature and dedicated our analysis to a comprehensive assessment of sequence information and machine learning models. A systematic evaluation of machine learning models and a wide range of feature representation algorithms based on sequence information are presented as a comparison survey towards the prediction performance evaluation of HB-PPIs.

Accurate Identification of Human Phosphorylated Proteins by Ensembling Supervised Kernel Self-organizing Maps

Protein phosphorylation is a vital physiological process, which plays a critical role in controlling survival differentiation, cell growth, metabolism and apoptosis. The accurate identification of whether a protein will be phosphorylated solely from protein sequence is especially useful for both basic research and drug development. In this study, a new predictor specifically designed for the prediction of human phosphorylated proteins is proposed. The proposed method first train two supervised kernel self-organizing maps (SKSOMs): one is trained with feature from protein physiochemical composition view, while the other is trained with feature from protein evolutionary information view. Then, the two trained SKSOMs are ensembled to perform the final prediction. Rigorous computational experiments show that the proposed method achieves 78.75 % and 0.561 on ACC and MCC, which are 6.96 % and 12.5 % higher than that of the state-of-the-art predictor. Overall, the study demonstrated a new sensitive avenue to identify human phosphorylated proteins and could be readily extended to recognize phosphorylated proteins for other species.

Protein Secondary Structure Prediction: A Review of Progress and Directions

Background:

Over the last few decades, a search for the theory of protein folding has grown into a full-fledged research field at the intersection of biology, chemistry and informatics. Despite enormous effort, there are still open questions and challenges, like understanding the rules by which amino acid sequence determines protein secondary structure.

Objective:

In this review, we depict the progress of the prediction methods over the years and identify sources of improvement.

Methods:

The protein secondary structure prediction problem is described followed by the discussion on theoretical limitations, description of the commonly used data sets, features and a review of three generations of methods with the focus on the most recent advances. Additionally, methods with available online servers are assessed on the independent data set.

Results:

The state-of-the-art methods are currently reaching almost 88% for 3-class prediction and 76.5% for an 8-class prediction.

Conclusion:

This review summarizes recent advances and outlines further research directions.

Computational Identification and Analysis of Ubiquinone-Binding Proteins

Ubiquinone is an important cofactor that plays vital and diverse roles in many biological processes. Ubiquinone-binding proteins (UBPs) are receptor proteins that dock with ubiquinones. Analyzing and identifying UBPs via a computational approach will provide insights into the pathways associated with ubiquinones. In this work, we were the first to propose a UBPs predictor (UBPs-Pred). The optimal feature subset selected from three categories of sequence-derived features was fed into the extreme gradient boosting (XGBoost) classifier, and the parameters of XGBoost were tuned by multi-objective particle swarm optimization (MOPSO). The experimental results over the independent validation demonstrated considerable prediction performance with a Matthews correlation coefficient (MCC) of 0.517. After that, we analyzed the UBPs using bioinformatics methods, including the statistics of the binding domain motifs and protein distribution, as well as an enrichment analysis of the gene ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway.

RPI-SE: a stacking ensemble learning framework for ncRNA-protein interactions prediction using sequence information

Background

The interactions between non-coding RNAs (ncRNA) and proteins play an essential role in many biological processes. Several high-throughput experimental methods have been applied to detect ncRNA-protein interactions. However, these methods are time-consuming and expensive. Accurate and efficient computational methods can assist and accelerate the study of ncRNA-protein interactions.

Results

In this work, we develop a stacking ensemble computational framework, RPI-SE, for effectively predicting ncRNA-protein interactions. More specifically, to fully exploit protein and RNA sequence feature, Position Weight Matrix combined with Legendre Moments is applied to obtain protein evolutionary information. Meanwhile, k-mer sparse matrix is employed to extract efficient feature of ncRNA sequences. Finally, an ensemble learning framework integrated different types of base classifier is developed to predict ncRNA-protein interactions using these discriminative features. The accuracy and robustness of RPI-SE was evaluated on three benchmark data sets under five-fold cross-validation and compared with other state-of-the-art methods.

Conclusions

The results demonstrate that RPI-SE is competent for ncRNA-protein interactions prediction task with high accuracy and robustness. It’s anticipated that this work can provide a computational prediction tool to advance ncRNA-protein interactions related biomedical research.

A study on separation of the protein structural types in amino acid sequence feature spaces

Proteins are diverse with their sequences, structures and functions, it is important to study the relations between the sequences, structures and functions. In this paper, we conduct a study that surveying the relations between the protein sequences and their structures. In this study, we use the natural vector (NV) and the averaged property factor (APF) features to represent protein sequences into feature vectors, and use the multi-class MSE and the convex hull methods to separate proteins of different structural classes into different regions. We found that proteins from different structural classes are separable by hyper-planes and convex hulls in the natural vector feature space, where the feature vectors of different structural classes are separated into disjoint regions or convex hulls in the high dimensional feature spaces. The natural vector outperforms the averaged property factor method in identifying the structures, and the convex hull method outperforms the multi-class MSE in separating the feature points. These outcomes convince the strong connections between the protein sequences and their structures, and may imply that the amino acids composition and their sequence arrangements represented by the natural vectors have greater influences to the structures than the averaged physical property factors of the amino acids.

Identifying protein-protein interface via a novel multi-scale local sequence and structural representation

Background

Protein-protein interaction plays a key role in a multitude of biological processes, such as signal transduction, de novo drug design, immune responses, and enzymatic activities. Gaining insights of various binding abilities can deepen our understanding of the interaction. It is of great interest to understand how proteins in a complex interact with each other. Many efficient methods have been developed for identifying protein-protein interface.

Results

In this paper, we obtain the local information on protein-protein interface, through multi-scale local average block and hexagon structure construction. Given a pair of proteins, we use a trained support vector regression (SVR) model to select best configurations. On Benchmark v4.0, our method achieves average I_rmsd value of 3.28Å and overall F_nat value of 63%, which improves upon I_rmsd of 3.89Å and F_nat of 49% for ZRANK, and I_rmsd of 3.99Å and F_nat of 46% for ClusPro. On CAPRI targets, our method achieves average I_rmsd value of 3.45Å and overall F_nat value of 46%, which improves upon I_rmsd of 4.18Å and F_nat of 40% for ZRANK, and I_rmsd of 5.12Å and F_nat of 32% for ClusPro. The success rates by our method, FRODOCK 2.0, InterEvDock and SnapDock on Benchmark v4.0 are 41.5%, 29.0%, 29.4% and 37.0%, respectively.

Conclusion

Experiments show that our method performs better than some state-of-the-art methods, based on the prediction quality improved in terms of CAPRI evaluation criteria. All these results demonstrate that our method is a valuable technological tool for identifying protein-protein interface.

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.

Prediction of drug-target interaction based on protein features using undersampling and feature selection techniques with boosting

Accurate identification of drug-target interaction (DTI) is a crucial and challenging task in the drug discovery process, having enormous benefit to the patients and pharmaceutical company. The traditional wet-lab experiments of DTI is expensive, time-consuming, and labor-intensive. Therefore, many computational techniques have been established for this purpose; although a huge number of interactions are still undiscovered. Here, we present pdti-EssB, a new computational model for identification of DTI using protein sequence and drug molecular structure. More specifically, each drug molecule is transformed as the molecular substructure fingerprint. For a protein sequence, different descriptors are utilized to represent its evolutionary, sequence, and structural information. Besides, our proposed method uses data balancing techniques to handle the imbalance problem and applies a novel feature eliminator to extract the best optimal features for accurate prediction. In this paper, four classes of DTI benchmark datasets are used to construct a predictive model with XGBoost. Here, the auROC is utilized as an evaluation metric to compare the performance of pdti-EssB method with recent methods, applying five-fold cross-validation. Finally, the experimental results indicate that our proposed method is able to outperform other approaches in predicting DTI, and introduces new drug-target interaction samples based on prediction probability scores. pdti-EssB webserver is available online at http://pdtiessb-uestc.com/.

Machine learning techniques for protein function prediction

Proteins play important roles in living organisms, and their function is directly linked with their structure. Due to the growing gap between the number of proteins being discovered and their functional characterization (in particular as a result of experimental limitations), reliable prediction of protein function through computational means has become crucial. This paper reviews the machine learning techniques used in the literature, following their evolution from simple algorithms such as logistic regression to more advanced methods like support vector machines and modern deep neural networks. Hyperparameter optimization methods adopted to boost prediction performance are presented. In parallel, the metamorphosis in the features used by these algorithms from classical physicochemical properties and amino acid composition, up to text-derived features from biomedical literature and learned feature representations using autoencoders, together with feature selection and dimensionality reduction techniques, are also reviewed. The success stories in the application of these techniques to both general and specific protein function prediction are discussed.

FKRR-MVSF: A Fuzzy Kernel Ridge Regression Model for Identifying DNA-Binding Proteins by Multi-View Sequence Features via Chou's Five-Step Rule

DNA-binding proteins play an important role in cell metabolism. In biological laboratories, the detection methods of DNA-binding proteins includes yeast one-hybrid methods, bacterial singles and X-ray crystallography methods and others, but these methods involve a lot of labor, material and time. In recent years, many computation-based approachs have been proposed to detect DNA-binding proteins. In this paper, a machine learning-based method, which is called the Fuzzy Kernel Ridge Regression model based on Multi-View Sequence Features (FKRR-MVSF), is proposed to identifying DNA-binding proteins. First of all, multi-view sequence features are extracted from protein sequences. Next, a Multiple Kernel Learning (MKL) algorithm is employed to combine multiple features. Finally, a Fuzzy Kernel Ridge Regression (FKRR) model is built to detect DNA-binding proteins. Compared with other methods, our model achieves good results. Our method obtains an accuracy of 83.26% and 81.72% on two benchmark datasets (PDB1075 and compared with PDB186), respectively.

Predicting Protein-Protein Interactions from Matrix-Based Protein Sequence Using Convolution Neural Network and Feature-Selective Rotation Forest

Protein is an essential component of the living organism. The prediction of protein-protein interactions (PPIs) has important implications for understanding the behavioral processes of life, preventing diseases, and developing new drugs. Although the development of high-throughput technology makes it possible to identify PPIs in large-scale biological experiments, it restricts the extensive use of experimental methods due to the constraints of time, cost, false positive rate and other conditions. Therefore, there is an urgent need for computational methods as a supplement to experimental methods to predict PPIs rapidly and accurately. In this paper, we propose a novel approach, namely CNN-FSRF, for predicting PPIs based on protein sequence by combining deep learning Convolution Neural Network (CNN) with Feature-Selective Rotation Forest (FSRF). The proposed method firstly converts the protein sequence into the Position-Specific Scoring Matrix (PSSM) containing biological evolution information, then uses CNN to objectively and efficiently extracts the deeply hidden features of the protein, and finally removes the redundant noise information by FSRF and gives the accurate prediction results. When performed on the PPIs datasets Yeast and Helicobacter pylori, CNN-FSRF achieved a prediction accuracy of 97.75% and 88.96%. To further evaluate the prediction performance, we compared CNN-FSRF with SVM and other existing methods. In addition, we also verified the performance of CNN-FSRF on independent datasets. Excellent experimental results indicate that CNN-FSRF can be used as a useful complement to biological experiments to identify protein interactions.

MPLs-Pred: Predicting Membrane Protein-Ligand Binding Sites Using Hybrid Sequence-Based Features and Ligand-Specific Models

Membrane proteins (MPs) are involved in many essential biomolecule mechanisms as a pivotal factor in enabling the small molecule and signal transport between the two sides of the biological membrane; this is the reason that a large portion of modern medicinal drugs target MPs. Therefore, accurately identifying the membrane protein-ligand binding sites (MPLs) will significantly improve drug discovery. In this paper, we propose a sequence-based MPLs predictor called MPLs-Pred, where evolutionary profiles, topology structure, physicochemical properties, and primary sequence segment descriptors are combined as features applied to a random forest classifier, and an under-sampling scheme is used to enhance the classification capability with imbalanced samples. Additional ligand-specific models were taken into consideration in refining the prediction. The corresponding experimental results based on our method achieved an appreciable performance, with 0.63 MCC (Matthews correlation coefficient) as the overall prediction precision, and those values were 0.604, 0.7, and 0.692, respectively, for the three main types of ligands: drugs, metal ions, and biomacromolecules. MPLs-Pred is freely accessible at http://icdtools.nenu.edu.cn/.

Identification of protein subcellular localization via integrating evolutionary and physicochemical information into Chou's general PseAAC

Identifying the location of proteins in a cell plays an important role in understanding their functions, such as drug design, therapeutic target discovery and biological research. However, the traditional subcellular localization experiments are time-consuming, laborious and small scale. With the development of next-generation sequencing technology, the number of proteins has grown exponentially, which lays the foundation of the computational method for identifying protein subcellular localization. Although many methods for predicting subcellular localization of proteins have been proposed, most of them are limited to single-location. In this paper, we propose a multi-kernel SVM to predict subcellular localization of both multi-location and single-location proteins. First, we make use of the evolutionary information extracted from position specific scoring matrix (PSSM) and physicochemical properties of proteins, by Chou's general PseAAC and other efficient functions. Then, we propose a multi-kernel support vector machine (SVM) model to identify multi-label protein subcellular localization. As a result, our method has a good performance on predicting subcellular localization of proteins. It achieves an average precision of 0.7065 and 0.6889 on two human datasets, respectively. All results are higher than those achieved by other existing methods. Therefore, we provide an efficient system via a novel perspective to study the protein subcellular localization.

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.

Predicting protein-protein interactions from protein sequences by a stacked sparse autoencoder deep neural network

Protein-protein interactions (PPIs) play an important role in most of the biological processes. How to correctly and efficiently detect protein interaction is a problem that is worth studying. Although high-throughput technologies provide the possibility to detect large-scale PPIs, these cannot be used to detect whole PPIs, and unreliable data may be generated. To solve this problem, in this study, a novel computational method was proposed to effectively predict the PPIs using the information of a protein sequence. The present method adopts Zernike moments to extract the protein sequence feature from a position specific scoring matrix (PSSM). Then, these extracted features were reconstructed using the stacked autoencoder. Finally, a novel probabilistic classification vector machine (PCVM) classifier was employed to predict the protein-protein interactions. When performed on the PPIs datasets of Yeast and H. pylori, the proposed method could achieve average accuracies of 96.60% and 91.19%, respectively. The promising result shows that the proposed method has a better ability to detect PPIs than other detection methods. The proposed method was also applied to predict PPIs on other species, and promising results were obtained. To evaluate the ability of our method, we compared it with the-state-of-the-art support vector machine (SVM) classifier for the Yeast dataset. The results obtained via multiple experiments prove that our method is powerful, efficient, feasible, and make a great contribution to proteomics research.

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.

A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information

The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research.

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/.

Identification of DNA-protein Binding Sites through Multi-Scale Local Average Blocks on Sequence Information

DNA–protein interactions appear as pivotal roles in diverse biological procedures and are paramount for cell metabolism, while identifying them with computational means is a kind of prudent scenario in depleting in vitro and in vivo experimental charging. A variety of state-of-the-art investigations have been elucidated to improve the accuracy of the DNA–protein binding sites prediction. Nevertheless, structure-based approaches are limited under the condition without 3D information, and the predictive validity is still refinable. In this essay, we address a kind of competitive method called Multi-scale Local Average Blocks (MLAB) algorithm to solve this issue. Different from structure-based routes, MLAB exploits a strategy that not only extracts local evolutionary information from primary sequences, but also using predicts solvent accessibility. Moreover, the construction about predictors of DNA–protein binding sites wields an ensemble weighted sparse representation model with random under-sampling. To evaluate the performance of MLAB, we conduct comprehensive experiments of DNA–protein binding sites prediction. MLAB gives MCC of 0.392, 0.315, 0.439 and 0.245 on PDNA-543, PDNA-41, PDNA-316 and PDNA-52 datasets, respectively. It shows that MLAB gains advantages by comparing with other outstanding methods. MCC for our method is increased by at least 0.053, 0.015 and 0.064 on PDNA-543, PDNA-41 and PDNA-316 datasets, respectively.

Classification of G-protein coupled receptors based on a rich generation of convolutional neural network, N-gram transformation and multiple sequence alignments

Sequence classification is crucial in predicting the function of newly discovered sequences. In recent years, the prediction of the incremental large-scale and diversity of sequences has heavily relied on the involvement of machine-learning algorithms. To improve prediction accuracy, these algorithms must confront the key challenge of extracting valuable features. In this work, we propose a feature-enhanced protein classification approach, considering the rich generation of multiple sequence alignment algorithms, N-gram probabilistic language model and the deep learning technique. The essence behind the proposed method is that if each group of sequences can be represented by one feature sequence, composed of homologous sites, there should be less loss when the sequence is rebuilt, when a more relevant sequence is added to the group. On the basis of this consideration, the prediction becomes whether a query sequence belonging to a group of sequences can be transferred to calculate the probability that the new feature sequence evolves from the original one. The proposed work focuses on the hierarchical classification of G-protein Coupled Receptors (GPCRs), which begins by extracting the feature sequences from the multiple sequence alignment results of the GPCRs sub-subfamilies. The N-gram model is then applied to construct the input vectors. Finally, these vectors are imported into a convolutional neural network to make a prediction. The experimental results elucidate that the proposed method provides significant performance improvements. The classification error rate of the proposed method is reduced by at least 4.67% (family level I) and 5.75% (family Level II), in comparison with the current state-of-the-art methods. The implementation program of the proposed work is freely available at: https://github.com/alanFchina/CNN .

Predicting Protein-DNA Binding Residues by Weightedly Combining Sequence-Based Features and Boosting Multiple SVMs

Protein-DNA interactions are ubiquitous in a wide variety of biological processes. Correctly locating DNA-binding residues solely from protein sequences is an important but challenging task for protein function annotations and drug discovery, especially in the post-genomic era where large volumes of protein sequences have quickly accumulated. In this study, we report a new predictor, named TargetDNA, for targeting protein-DNA binding residues from primary sequences. TargetDNA uses a protein's evolutionary information and its predicted solvent accessibility as two base features and employs a centered linear kernel alignment algorithm to learn the weights for weightedly combining the two features. Based on the weightedly combined feature, multiple initial predictors with SVM as classifiers are trained by applying a random under-sampling technique to the original dataset, the purpose of which is to cope with the severe imbalance phenomenon that exists between the number of DNA-binding and non-binding residues. The final ensembled predictor is obtained by boosting the multiple initially trained predictors. Experimental simulation results demonstrate that the proposed TargetDNA achieves a high prediction performance and outperforms many existing sequence-based protein-DNA binding residue predictors. The TargetDNA web server and datasets are freely available at http://csbio.njust.edu.cn/bioinf/TargetDNA/ for academic use.

PSFM-DBT: Identifying DNA-Binding Proteins by Combing Position Specific Frequency Matrix and Distance-Bigram Transformation

DNA-binding proteins play crucial roles in various biological processes, such as DNA replication and repair, transcriptional regulation and many other biological activities associated with DNA. Experimental recognition techniques for DNA-binding proteins identification are both time consuming and expensive. Effective methods for identifying these proteins only based on protein sequences are highly required. The key for sequence-based methods is to effectively represent protein sequences. It has been reported by various previous studies that evolutionary information is crucial for DNA-binding protein identification. In this study, we employed four methods to extract the evolutionary information from Position Specific Frequency Matrix (PSFM), including Residue Probing Transformation (RPT), Evolutionary Difference Transformation (EDT), Distance-Bigram Transformation (DBT), and Trigram Transformation (TT). The PSFMs were converted into fixed length feature vectors by these four methods, and then respectively combined with Support Vector Machines (SVMs); four predictors for identifying these proteins were constructed, including PSFM-RPT, PSFM-EDT, PSFM-DBT, and PSFM-TT. Experimental results on a widely used benchmark dataset PDB1075 and an independent dataset PDB186 showed that these four methods achieved state-of-the-art-performance, and PSFM-DBT outperformed other existing methods in this field. For practical applications, a user-friendly webserver of PSFM-DBT was established, which is available at http://bioinformatics.hitsz.edu.cn/PSFM-DBT/.

Computational methods using weighed-extreme learning machine to predict protein self-interactions with protein evolutionary information

Self-interactions Proteins (SIPs) is important for their biological activity owing to the inherent interaction amongst their secondary structures or domains. However, due to the limitations of experimental Self-interactions detection, one major challenge in the study of prediction SIPs is how to exploit computational approaches for SIPs detection based on evolutionary information contained protein sequence. In the work, we presented a novel computational approach named WELM-LAG, which combined the Weighed-Extreme Learning Machine (WELM) classifier with Local Average Group (LAG) to predict SIPs based on protein sequence. The major improvement of our method lies in presenting an effective feature extraction method used to represent candidate Self-interactions proteins by exploring the evolutionary information embedded in PSI-BLAST-constructed position specific scoring matrix (PSSM); and then employing a reliable and robust WELM classifier to carry out classification. In addition, the Principal Component Analysis (PCA) approach is used to reduce the impact of noise. The WELM-LAG method gave very high average accuracies of 92.94 and 96.74% on yeast and human datasets, respectively. Meanwhile, we compared it with the state-of-the-art support vector machine (SVM) classifier and other existing methods on human and yeast datasets, respectively. Comparative results indicated that our approach is very promising and may provide a cost-effective alternative for predicting SIPs. In addition, we developed a freely available web server called WELM-LAG-SIPs to predict SIPs. The web server is available at http://219.219.62.123:8888/WELMLAG/ .

Detection of Interactions between Proteins by Using Legendre Moments Descriptor to Extract Discriminatory Information Embedded in PSSM

Protein-protein interactions (PPIs) play a very large part in most cellular processes. Although a great deal of research has been devoted to detecting PPIs through high-throughput technologies, these methods are clearly expensive and cumbersome. Compared with the traditional experimental methods, computational methods have attracted much attention because of their good performance in detecting PPIs. In our work, a novel computational method named as PCVM-LM is proposed which combines the probabilistic classification vector machine (PCVM) model and Legendre moments (LMs) to predict PPIs from amino acid sequences. The improvement mainly comes from using the LMs to extract discriminatory information embedded in the position-specific scoring matrix (PSSM) combined with the PCVM classifier to implement prediction. The proposed method was evaluated on Yeast and Helicobacter pylori datasets with five-fold cross-validation experiments. The experimental results show that the proposed method achieves high average accuracies of 96.37% and 93.48%, respectively, which are much better than other well-known methods. To further evaluate the proposed method, we also compared the proposed method with the state-of-the-art support vector machine (SVM) classifier and other existing methods on the same datasets. The comparison results clearly show that our method is better than the SVM-based method and other existing methods. The promising experimental results show the reliability and effectiveness of the proposed method, which can be a useful decision support tool for protein research.