Chou's Pseudo Amino Acid Research Articles

Using several pseudo amino acid composition types and different machine learning algorithms to classify and predict archaeal phospholipases.

Phospholipases, as important lipolytic enzymes, have diverse industrial applications. Regarding the stability of extremophilic archaea's proteins in harsh conditions, analyses of unusual features of their proteins are significantly important for their utilization. This research was accomplished to in silico study of archaeal phospholipases' properties and to develop a pioneering method for distinguishing these enzymes from other archaeal enzymes via machine learning algorithms and Chou's pseudo-amino acid composition concept. The non-redundant sequences of archaeal phospholipases were collected. BioSeq-Analysis sever was used with Support Vector Machine (SVM), Random Forests (RF), Covariance Discrimination (CD), and Optimized Evidence-Theoretic K-nearest Neighbor (OET-KNN) as powerful machine learnings algorithms. Also, different Chou's pseudo-amino acid composition modes were performed and then, 5-fold cross-validation was applied to the sequences. Based on our results, the OET-KNN predictor, with 96% accuracy, yields the best performance in SC-PseAAC mode by 5-fold cross-validation. This predictor also achieved very high values of specificity (95%), sensitivity (96%), Matthews's correlation coefficient (0.92), and accuracy (96%). The present investigation yielded a robust anticipatory model for the archaeal phospholipase prediction utilizing the tenets PseAAC and OET-KNN machine learning algorithm.

IPhosS(Deep)-PseAAC: Identification of Phosphoserine Sites in Proteins Using Deep Learning on General Pseudo Amino Acid Compositions.

Among all the PTMs, the protein phosphorylation is pivotal for various pathological and physiological processes. About 30 percent of eukaryotic proteins undergo the phosphorylation modification, leading to various changes in conformation, function, stability, localization, and so forth. In eukaryotic proteins, phosphorylation occurs on serine (S), Threonine (T) and Tyrosine (Y) residues. Among these all, serine phosphorylation has its own importance as it is associated with various importance biological processes, including energy metabolism, signal transduction pathways, cell cycling, and apoptosis. Thus, its identification is important, however, the in vitro, ex vivo and in vivo identification can be laborious, time-taking and costly. There is a dire need of an efficient and accurate computational model to help researchers and biologists identifying these sites, in an easy manner. Herein, we propose a novel predictor for identification of Phosphoserine sites (PhosS) in proteins, by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) with deep features. We used well-known DNNs for both the tasks of learning a feature representation of peptide sequences and performing classifications. Among different DNNs, the best score is shown by Covolutional Neural Network based model which renders CNN based prediction model the best for Phosphoserine prediction. Based on these results, it is concluded that the proposed model can help to identify PhosS sites in a very efficient and accurate manner which can help scientists understand the mechanism of this modification in proteins.

Using CHOU'S 5-Steps Rule to Predict O-Linked Serine Glycosylation Sites by Blending Position Relative Features and Statistical Moment.

Glycosylation of proteins in eukaryote cells is an important and complicated post-translation modification due to its pivotal role and association with crucial physiological functions within most of the proteins. Identification of glycosylation sites in a polypeptide chain is not an easy task due to multiple impediments. Analytical identification of these sites is expensive and laborious. There is a dire need to develop a reliable computational method for precise determination of such sites which can help researchers to save time and effort. Herein, we propose a novel predictor namely iGlycoS-PseAAC by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) and relative/absolute position-based features. The self-consistency results show that the accuracy revealed by the model using the benchmark dataset for prediction of O-linked glycosylation having serine sites is 98.8 percent. The overall accuracy of predictor achieved through 10-fold cross validation by combining the positive and negative results is 97.2 percent. The overall accuracy achieved through Jackknife test is 96.195 percent by aggregating of all the prediction results. Thus the proposed predictor can help in predicting the O-linked glycosylated serine sites in an efficient and accurate way. The overall results show that the accuracy of the iGlycoS-PseAAC is higher than the existing tools.

Introducing of an integrated artificial neural network and Chou's pseudo amino acid composition approach for computational epitope-mapping of Crimean-Congo haemorrhagic fever virus antigens

This study was aimed to introduce a novel algorithm for determining linear B- and T-cell epitopes from Crimean-Congo haemorrhagic fever virus (CCHFV) antigens. To this end, 387 approved B- and T-cell epitopes, as well as 331 non-epitope peptides from different serotypes of the virus were collected from IEDB database for generating of the train datasets. After that, the physicochemical properties of the epitopes were expressed as the numeric vectors using Chou's pseudo amino acid composition method. The vectors then were used for training of four machine learning algorithms including artificial neural network (ANN), k-nearest neighbors (kNN), support vector machine (SVM) and Random forest (RF). The results confirmed that ANN was the most accurate algorithm for discriminating between the epitopes and non-epitopes with the accuracy of 0.90. Furthermore, for evaluating the performance of the ANN algorithm, an epitope prediction challenge was performed to a random peptide library from envelopment polyprotein of CCHFV. Moreover, the efficiency of the predicted epitopes in term of antigenicity and affinity to MHC-II were compared to the predicted epitope by standard epitope prediction tools based on their VaxiJen 2.0 score and molecular docking outputs. Finally, the ability of the screened epitopes to stimulation of humoral and cellular responses was evaluated by an in silico immune simulation process thought C-Immsim 10.1 server. The results confirmed that this method has more accuracy for epitope-mapping than the standard tools and could considered as an effective algorithm to develop a serotype independent one-click automated epitope based vaccine design tool.

Accurate prediction of potential druggable proteins based on genetic algorithm and Bagging-SVM ensemble classifier.

Discovering and accurately locating drug targets is of great significance for the research and development of new drugs. As a different approach to traditional drug development, the machine learning algorithm is used to predict the drug target by mining the data. Because of its advantages of short time and low cost, it has received more and more attention in recent years. In this paper, we propose a novel method for predicting druggable proteins. Firstly, the features of the protein sequence are extracted by combining Chou's pseudo amino acid composition (PseAAC), dipeptide composition (DPC) and reduced sequence (RS), getting the 591 dimension of drug target dataset. Then, the feature information of druggable proteins dataset is selected by genetic algorithm (GA). Finally, we use Bagging ensemble learning to improve SVM classifier to get the final prediction model. The predictive accuracy rate reaches 93.78% by using 5-fold cross-validation and compared with other state-of-the-art predictive methods. The results indicate that the method proposed in this paper has a high reference value for the prediction of potential drug targets, which will successfully play a key role in the drug research and development. The source code and all datasets are available at https://github.com/QUST-AIBBDRC/GA-Bagging-SVM.

SPrenylC-PseAAC: A sequence-based model developed via Chou's 5-steps rule and general PseAAC for identifying S-prenylation sites in proteins

The protein prenylation (or S-prenylation) is one of the most essential modifications, required for the association of membrane of a plethora of signalling proteins with the key biological process such as protein trafficking, cell growth, proliferation and differentiation. Due to the ubiquitous nature of S-prenylation and its role in cellular functions, any defect in the biosynthesis or regulation of the isoprenoid leads to the occurrence of a variety of diseases including neurodegenerative disorders, metabolic issues, cardiovascular diseases and one of the most fatal diseases, cancer. This depicts the strong biological significance of S-prenylation, thus, the timely and accurate identification of S-prenylation sites is crucial and may provide with possible ways to understand the mechanism of this modification in proteins. To avoid laborious, resource demanding and expensive experimental techniques of identifying S-prenylation sites, here, we propose a novel predictor namely SPrenylC-PseAAC by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) and relative/absolute position-based features. A 2-tier classification was performed i.e., at first level, identification of prenylation and non-prenylation sites is performed, while at the second level, identification of S-farnesylation and S-geranylgeranylation sites is performed. Using jackknife, perdition model validation gave 95.31% accuracy for tier-1 classification and 91.42% for tier 2 classification, while for 10-fold cross-validation, it gave 93.68% accuracy for tier-1 classification and 89.70% for tier 2 classification. Thus the proposed predictor can help in predicting the Prenylation sites in an efficient and accurate way. The SPrenylC-PseAAC is available at (biopred.org/prenyl).

SPalmitoylC-PseAAC: A sequence-based model developed via Chou's 5-steps rule and general PseAAC for identifying S-palmitoylation sites in proteins

S-Palmitoylation is a uniquely reversible and biologically important post-translational modification as it plays an essential role in a variety of cellular processes including signal transduction, protein-membrane interactions, neuronal development, lipid raft targeting, subcellular localization and apoptosis. Due to its association with the neuronal development, it plays a pivotal role in a variety of neurodegenerative diseases, mainly Alzheimer's, Schizophrenia and Huntington's disease. It is also essential for developmental life cycles and pathogenesis of Toxoplasma gondii and Plasmodium falciparum, known to cause toxoplasmosis and malaria, respectively. This depicts the strong biological significance of S-Palmitoylation, thus, the timely and accurate identification of S-palmitoylation sites is crucial. Herein, we propose a predictor for S-Palmitoylation sites in proteins namely SPalmitoylC-PseAAC by integrating the Chou's Pseudo Amino Acid Composition (PseAAC) and relative/absolute position-based features. Self-consistency testing and 10-fold cross-validation are performed to evaluate the performance of SPalmitoylC-PseAAC, using accuracy metrics. For self-consistency testing, 99.79% Acc, 99.77% Sp, 99.80% Sn and 1.00 MCC was observed, whereas, for 10-fold cross validation 97.22% Acc, 98.85% Sp, 95.80% Sn and 0.94 MCC was observed. Thus the proposed predictor can help in predicting the palmitoylation sites in an efficient and accurate way. The SPalmitoylC-PseAAC is available at (biopred.org/palm).

A Brief Review on Software Tools in Generating Chou's Pseudo-factor Representations for All Types of Biological Sequences.

In the post-genome age, it is more urgent to understand the functions of genes and proteins. Since experimental methods are usually costly and time consuming, computational predictions are recognized as an alternative approach. In developing a predictive method for functional genomics and proteomics, one of the most important steps is to represent biological sequences with a fixed length numerical form, which can be further analyzed using machine learning algorithms. Chou's pseudo-amino acid compositions and the pseudo k-nucleotide compositions are algorithms for this purpose. Since the appearance of these algorithms, several software tools have been developed as implementations. These software tools facilitate the application of these algorithms. As these software tools are developed with different technologies and for different application scenarios, we will briefly review the technical aspect of these software tools in this short review.

Computational prediction of antifungal peptides via Chou's PseAAC and SVM.

With the increase in immunocompromised patients in the recent years, fungal infections have emerged as new and serious threat in hospitals. This, and the insufficiency of current antifungal therapies alongside their toxic effects on patients, has led to the increased interest in seeking new antifungal peptides. In the present study, we have developed a prediction method for screening of antifungal peptides. For this, we have chosen Chou's pseudo amino acid composition (PseAAC) to translate peptide sequences into numeric values. Thus, the SVM classifier was performed for binomial classification of antifungal peptides. The performance of the classifier was evaluated via ten-fold cross-validation and an independent dataset. For further validation of the model developed, 22 P24-derived peptides were predicted using the classifier and in vitro assays were performed on the three peptides with the highest prediction score. The results showed that the PseAAC <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:mo>+</mml:mo></mml:math> SVM method is able to predict AFPs with ACC of 94.76%. In vitro results also validate the SEN and SPC of the classifier. The results suggest that the computational approach used in this study is highly efficient for prediction of antifungal peptides, which can save time and money in AFP screening and synthesis of novel peptides.

Predicting protein submitochondrial locations by incorporating the pseudo-position specific scoring matrix into the general Chou's pseudo-amino acid composition

Mitochondrion is important organelle of most eukaryotes and play an important role in participating in various life activities of cells. However, some functions of mitochondria can only be achieved in specific submitochondrial location, the study of submitochondrial locations will help to further understand the biological function of protein, which is a hotspot in proteomics research. In this paper, we propose a new method for protein submitochondrial locations prediction. Firstly, the features of protein sequence are extracted by combining Chou's pseudo-amino acid composition (PseAAC) and pseudo-position specific scoring matrix (PsePSSM). Then the extracted feature information is denoised by two-dimensional (2-D) wavelet denoising. Finally, the optimal feature vectors are input to the SVM classifier to predict the protein submitochondrial locations. We obtained the ideal prediction results by jackknife test and compared with other prediction methods. The results indicate that the proposed method is significantly better than the existing research results, which can provide a new method to predict protein locations in other organelles. The source code and all datasets are available at https://github.com/QUST-BSBRC/PseAAC-PsePSSM-WD/ for academic use.

IMem-2LSAAC: A two-level model for discrimination of membrane proteins and their types by extending the notion of SAAC into chou's pseudo amino acid composition

Membrane proteins execute significant roles in cellular processes of living organisms, ranging from cell signaling to cell adhesion. As a major part of a cell, the identification of membrane proteins and their functional types become a challenging job in the field of bioinformatics and proteomics from last few decades. Traditional experimental procedures are slightly applicable due to lack of recognized structures, enormous time and space. In this regard, the demand for fast, accurate and intelligent computational method is increased day by day.In this paper, a two-tier intelligent automated predictor has been developed called iMem-2LSAAC, which classifies protein sequence as membrane or non-membrane in first-tier (phase1) and in case of membrane the second-tier (phase2) identifies functional types of membrane protein. Quantitative attributes were extracted from protein sequences by applying three discrete features extraction schemes namely amino acid composition, pseudo amino acid composition and split amino acid composition (SAAC). Various learning algorithms were investigated by using jackknife test to select the best one for predictor. Experimental results exhibited that the highest predictive outcomes were yielded by SVM in conjunction with SAAC feature space on all examined datasets. The true classification rate of iMem-2LSAAC predictor is significantly higher than that of other state-of- the- art methods so far in the literature. Finally, it is expected that the proposed predictor will provide a solid framework for the development of pharmaceutical drug discovery and might be useful for researchers and academia.

Accurate prediction of subcellular location of apoptosis proteins combining Chou's PseAAC and PsePSSM based on wavelet denoising.

Apoptosis proteins subcellular localization information are very important for understanding the mechanism of programmed cell death and the development of drugs. The prediction of subcellular localization of an apoptosis protein is still a challenging task because the prediction of apoptosis proteins subcellular localization can help to understand their function and the role of metabolic processes. In this paper, we propose a novel method for protein subcellular localization prediction. Firstly, the features of the protein sequence are extracted by combining Chou's pseudo amino acid composition (PseAAC) and pseudo-position specific scoring matrix (PsePSSM), then the feature information of the extracted is denoised by two-dimensional (2-D) wavelet denoising. Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of apoptosis proteins. Quite promising predictions are obtained using the jackknife test on three widely used datasets and compared with other state-of-the-art methods. The results indicate that the method proposed in this paper can remarkably improve the prediction accuracy of apoptosis protein subcellular localization, which will be a supplementary tool for future proteomics research.

Prediction subcellular localization of Gram-negative bacterial proteins by support vector machine using wavelet denoising and Chou's pseudo amino acid composition

Information on the subcellular localization of Gram-negative bacterial proteins is of great significance to study the pathogenesis, drug design and discovery of certain diseases. Protein subcellular localization is an important part of proteomics, while providing new opportunities and challenges for chemometrics. Since the prediction of protein subcellular localization can help to understand their function and the role played by their metabolic processes, a number of protein subcellular localization prediction methods have been developed in recent years. In this paper, we propose a novel method by combining wavelet denoising with support vector machine to predict the subcellular localization of proteins for the first time. Firstly, the features of the protein sequence are extracted by Chou's pseudo amino acid composition (PseAAC), then the feature information of the extracted is denoised by two-dimensional (2-D) wavelet. Finally, the optimal feature vectors are input to the SVM classifier to predict subcellular location of the Gram-negative bacterial proteins. Quite promising predictions are obtained using the jackknife test and compared with other predictive methods. The results indicate that the method proposed in this paper can remarkably improve the prediction accuracy of protein subcellular localization, and it can be used to predict the other attributes of proteins.

A novel alignment-free method to classify protein folding types by combining spectral graph clustering with Chou's pseudo amino acid composition

The present work employs pseudo amino acid composition (PseAAC) for encoding the protein sequences in their numeric form. Later this will be arranged in the similarity matrix, which serves as input for spectral graph clustering method. Spectral methods are used previously also for clustering of protein sequences, but they uses pair wise alignment scores of protein sequences, in similarity matrix. The alignment score depends on the length of sequences, so clustering short and long sequences together may not good idea. Therefore the idea of introducing PseAAC with spectral clustering algorithm came into scene. We extensively tested our method and compared its performance with other existing machine learning methods. It is consistently observed that, the number of clusters that we obtained for a given set of proteins is close to the number of superfamilies in that set and PseAAC combined with spectral graph clustering shows the best classification results.

OOgenesis_Pred: A sequence-based method for predicting oogenesis proteins by six different modes of Chou's pseudo amino acid composition

Regarding to critical roles of oogenesis in formation of ova or unfertilized eggs from the oogonia by mitotic division and subsequent differentiation, the identification of oogenesis-related proteins is of great interest. However, the experimental determination of proteins involved in oogenesis is expensive, time consuming and labor-intensive. Therefore, a new powerful discriminating model is indispensable for classifying oogenesis/non-oogenesis-related proteins with high accuracy and precision. Hereby, for the first time we developed a support vector machine based oogenesis protein prediction method which differentiates oogenesis from non-oogenesis proteins. By means of informative protein physicochemical properties and in addition parameter optimization scheme, our method yields a robust and consistent performance. Our model achieved 87.68% and 84.82% prediction accuracy by five-fold cross validation test for datasets with 90% and 50% identity, respectively. The prediction model was also assessed using the independent dataset and yielded 91.62% and 85.38% prediction accuracy for datasets with 90% and 50% identity, respectively, which further demonstrates the effectiveness of our method. Moreover, by applying 10 different feature weighting methods, the more important protein features for oogenesis/non-oogenesis-related proteins discrimination, including serine and glycine frequency, quasi-sequence-order, pseudo-amino acid composition, distribution and conjoint triad, were determined. The success rates revealed that our model can be considered as a new encouraging and strong model for predicting proteins involved in oogenesis with appropriate performance. To enhance the value of the practical applications of the proposed method, we developed a standalone software for predicting oogenesis candidate proteins called OOgenesis_Pred. This software is the first predictor ever established for identifying oogenesis proteins. We also showed the capability of OOgenesis_Pred by making oogenesis-related proteins prediction for some of the oogenesis candidate proteins. It is anticipated that OOgenesis_Pred will become a powerful tool for future proteomic studies related to oogenesis.

Improved protein-protein interactions prediction via weighted sparse representation model combining continuous wavelet descriptor and PseAA composition.

BackgroundProtein-protein interactions (PPIs) are essential to most biological processes. Since bioscience has entered into the era of genome and proteome, there is a growing demand for the knowledge about PPI network. High-throughput biological technologies can be used to identify new PPIs, but they are expensive, time-consuming, and tedious. Therefore, computational methods for predicting PPIs have an important role. For the past years, an increasing number of computational methods such as protein structure-based approaches have been proposed for predicting PPIs. The major limitation in principle of these methods lies in the prior information of the protein to infer PPIs. Therefore, it is of much significance to develop computational methods which only use the information of protein amino acids sequence.ResultsHere, we report a highly efficient approach for predicting PPIs. The main improvements come from the use of a novel protein sequence representation by combining continuous wavelet descriptor and Chou’s pseudo amino acid composition (PseAAC), and from adopting weighted sparse representation based classifier (WSRC). This method, cross-validated on the PPIs datasets of Saccharomyces cerevisiae, Human and H. pylori, achieves an excellent results with accuracies as high as 92.50%, 95.54% and 84.28% respectively, significantly better than previously proposed methods. Extensive experiments are performed to compare the proposed method with state-of-the-art Support Vector Machine (SVM) classifier.ConclusionsThe outstanding results yield by our model that the proposed feature extraction method combing two kinds of descriptors have strong expression ability and are expected to provide comprehensive and effective information for machine learning-based classification models. In addition, the prediction performance in the comparison experiments shows the well cooperation between the combined feature and WSRC. Thus, the proposed method is a very efficient method to predict PPIs and may be a useful supplementary tool for future proteomics studies.

An Evaluation on Different Machine Learning Algorithms for Classification and Prediction of Antifungal Peptides.

Fungi are an emerging threat in medicine and agriculture and current therapeutics have proved to be insufficient and toxic. This has led to an increased interest in peptide-based therapeutics, especially antifungal peptides (AFPs), being safer and more effective drug candidates against fungal threats. However, screening for peptides with antifungal activity is costly and timeconsuming. However, by using computational techniques, we can overcome these restricting factors. The aim of the present study is to compare different machine learning algorithms in combination with Chou's pseudo amino acid composition in classifying and predicting AFPs to represent a precise model for AFP prediction. Five different machine learning algorithms frequently used for classification of biological data were used and their performance was evaluated and compared based on their accuracy, sensitivity, specificity and Matthew's correlation coefficient. The two algorithms with the best performance were then further verified with an independent test dataset. SVM and Bagged-C4.5 classifiers had the highest performance results among the five algorithms. Further validations showed that the model generated using SVM can be employed for precise classification and prediction of antifungal peptides. All the performance values of this model were above 80%, making the classifier highly accurate and trustable. Using computational approaches, especially data mining techniques, we can develop a precise prediction model for antifungal peptides. The model developed in this study using SVM can be considered a powerful tool for the prediction of antifungal peptides, which can be the first step in synthesis and discovery of novel fungi targeting agents.

Prediction of Golgi-resident protein types using general form of Chou's pseudo-amino acid compositions: Approaches with minimal redundancy maximal relevance feature selection

Recently, several efforts have been made in predicting Golgi-resident proteins. However, it is still a challenging task to identify the type of a Golgi-resident protein. Precise prediction of the type of a Golgi-resident protein plays a key role in understanding its molecular functions in various biological processes. In this paper, we proposed to use a mutual information based feature selection scheme with the general form Chou's pseudo-amino acid compositions to predict the Golgi-resident protein types. The positional specific physicochemical properties were applied in the Chou's pseudo-amino acid compositions. We achieved 91.24% prediction accuracy in a jackknife test with 49 selected features. It has the best performance among all the present predictors. This result indicates that our computational model can be useful in identifying Golgi-resident protein types.

Identification of immunoglobulins using Chou's pseudo amino acid composition with feature selection technique.

Immunoglobulins, also called antibodies, are a group of cell surface proteins which are produced by the immune system in response to the presence of a foreign substance (called antigen). They play key roles in many medical, diagnostic and biotechnological applications. Correct identification of immunoglobulins is crucial to the comprehension of humoral immune function. With the avalanche of protein sequences identified in postgenomic age, it is highly desirable to develop computational methods to timely identify immunoglobulins. In view of this, we designed a predictor called "IGPred" by formulating protein sequences with the pseudo amino acid composition into which nine physiochemical properties of amino acids were incorporated. Jackknife cross-validated results showed that 96.3% of immunoglobulins and 97.5% of non-immunoglobulins can be correctly predicted, indicating that IGPred holds very high potential to become a useful tool for antibody analysis. For the convenience of most experimental scientists, a web-server for IGPred was established at http://lin.uestc.edu.cn/server/IGPred. We believe that the web-server will become a powerful tool to study immunoglobulins and to guide related experimental validations.

Predicting protein-protein interactions by weighted pseudo amino acid composition

Protein-protein interactions hold very important roles in biological processes. Prediction of PPIs is important for understanding these processes. In this context, substantive representations of proteins are needed during the process of interaction prediction in order to achieve higher prediction accuracy. In this paper, a new feature representation method, based on the concept of Chou's pseudo amino acid composition, was introduced. It is composed of the weighted amino acid composition information and the correlation factors of the protein. Finally, an SVM classification model was constructed for predicting PPIs. Experimental results exhibit that our method precedes those previously published in the literature.