Search

The loss of the regulatory function of tumor suppression genes and mutations in Proto-oncogene are the common underlying mechanisms for uncontrolled tumor growth in the varied complex of disorders known as cancer. Oncogene can be curable by means of diagnosing and treating the possibilities of Proto-oncogene at earlier stages. Recently, machine learning approaches helps to focus and provide information about the possibilities of Proto-oncogene that may change into oncogene in different cancer types. This study helps to diagnose the possibilities of Proto-oncogene which are possible to change oncogenes at earlier stage. Thus, this present study proposed an efficient unique predictor of Protooncogene with the help of Bi-Directional Long Short Term Memory added with attention concept. This approach also find the probability of Proto-oncogene to oncogene using statistical moments, position based amino-acid composition representation and deep features extracted from the sequence. Consequently, this study suggests that using a K-Nearest Neighbor classifier it is possible to find probability of changing from Proto-oncogene to cancerous oncogene.

The structure and function of dietary proteins, as well as their subcellular prediction, are critical for designing and developing new drug compositions and understanding the pathophysiology of certain diseases. As a remedy, we provide a subcellular localization method based on feature fusion and clustering for dietary proteins. Additionally, an enhanced PseAAC (Pseudo-amino acid composition) method is suggested, which builds upon the conventional PseAAC. The study initially builds a novel model of representing the food protein sequence by integrating autocorrelation, chi density, and improved PseAAC to better convey information about the food protein sequence. After that, the dimensionality of the fused feature vectors is reduced by using principal component analysis. With prediction accuracies of 99.24% in the Gram-positive dataset and 95.33% in the Gram-negative dataset, respectively, the experimental findings demonstrate the practicability and efficacy of the proposed approach. This paper is basically exploring pseudo-amino acid composition of not any clinical aspect but exploring a pharmaceutical aspect for drug repositioning. • Accurately predicting dietary protein subcellular composition using machine learning methods remains a challenging scientific inquiry. • This study provides a feature-fusion and clustering-based subcellular localization method for dietary proteins. • The construction of food protein feature expression models involves the use of autocorrelation and chi-density approaches. • An enhanced PseAAC (Pseudo-amino Acid Composition) method is suggested, which builds upon the conventional PseAAC. • Prediction accuracies of 99.24% on the Gram-positive dataset and 95.33% on the Gram-negative dataset, respectively, is observed. [ABSTRACT FROM AUTHOR]

In the biological systems, Acetylation is a crucial post-translational modification, prevalent in various physiological functions and pathological conditions like carcinoma and malignancies. To better understand serine acetylation, the first step is the efficient identification of the same. Although multiple large-scale in-vivo, ex-vivo, and in-vitro methods have been applied to detect serine acetylation biomarkers, these experimental methods are time-consuming and labor-intensive. This research aims to develop an in-silico solution to supplement wetlab experiments for efficient detection of serine acetylation sites by combining Chou’s Pseudo Amino Acid Composition (PseAAC) with deep neural networks (DNNs). By employing well-known DNNs for feature learning and classification of peptide sequences, our approach obsoletes the need to separately perform costly and cumbersome feature learning process. Based on performance evaluation using standard evaluation metrics, CNN and FCN based models, for AcetylSerine site identification, surpassed previously reported predictors which shows the efficacy of proposed approach.

Abstract Background Amyloids are insoluble fibrillar aggregates that are highly associated with complex human diseases, such as Alzheimer’s disease, Parkinson’s disease, and type II diabetes. Recently, many studies reported that some specific regions of amino acid sequences may be responsible for the amyloidosis of proteins. It has become very important for elucidating the mechanism of amyloids that identifying the amyloidogenic regions. Accordingly, several computational methods have been put forward to discover amyloidogenic regions. The majority of these methods predicted amyloidogenic regions based on the physicochemical properties of amino acids. In fact, position, order, and correlation of amino acids may also influence the amyloidosis of proteins, which should be also considered in detecting amyloidogenic regions. Results To address this problem, we proposed a novel machine-learning approach for predicting amyloidogenic regions, called ReRF-Pred. Firstly, the pseudo amino acid composition (PseAAC) was exploited to characterize physicochemical properties and correlation of amino acids. Secondly, tripeptides composition (TPC) was employed to represent the order and position of amino acids. To improve the distinguishability of TPC, all possible tripeptides were analyzed by the binomial distribution method, and only those which have significantly different distribution between positive and negative samples remained. Finally, all samples were characterized by PseAAC and TPC of their amino acid sequence, and a random forest-based amyloidogenic regions predictor was trained on these samples. It was proved by validation experiments that the feature set consisted of PseAAC and TPC is the most distinguishable one for detecting amyloidosis. Meanwhile, random forest is superior to other concerned classifiers on almost all metrics. To validate the effectiveness of our model, ReRF-Pred is compared with a series of gold-standard methods on two datasets: Pep-251 and Reg33. The results suggested our method has the best overall performance and makes significant improvements in discovering amyloidogenic regions. Conclusions The advantages of our method are mainly attributed to that PseAAC and TPC can describe the differences between amyloids and other proteins successfully. The ReRF-Pred server can be accessed at http://106.12.83.135:8080/ReRF-Pred/.

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. [ABSTRACT FROM AUTHOR]

Proto-oncogenes are the genes that have the potential to transform normal cells into cancer cells as a result of mutations. They usually contain encoding of proteins whose function is to inhibit cell differentiation, stimulate cell division, and prevent the death of cells. While the prognosis regarding proto-oncogene may occur at varying phases of cancer, the accuracy of the identification method is always questionable. The standard procedure for detecting these genes involves in-vitro experimentations but it proves to be very costly, time taking, and laborious. This problem is addressed by the use of computer-aided approaches established in studies encompassing methods in computational biology and bioinformatics. Early diagnosis of cancer is crucial for the full recovery of the patient. Proto-oncogene proteins are an important biomarker that helps identify the onset of a specific type of cancer. Keeping this in mind, this study proposes an efficient methodology for in-silico identification of proto-oncogenes. The predictor proposed in this study computes position and composition relevant statistical features incorporated into the pseudo-amino-acid composition (PseAAC) based on Chou’s 5-step rules. Subsequently, the study finds that the use of a random forest classifier performs the most accurate prediction of proto-oncogene proteins. The method was validated using the 10 folds cross-validation, Jackknife testing, Self-Consistency, and Independent set testing, giving 95.44%, 97.17%, 99.8%, and 96.41% accurate results, respectively. These results imply that the proposed model can play a key role in the early prognosis of cancer and aid scientists in the discovery of mechanisms against cancer.

In biological systems, Nitration is a crucial post-translational modification which occurs on various amino acids. Nitration of Tyrosine is regarded as nitorsative stress biomarker resulting in the formation of peroxynitrite and other reactive and harmful nitrogen species. NitroTyrosine is closely related to Carcinogenesis, tumor growth progression and other major pathological conditions including systemic autoimmune diseases, inflammation, neurodegeneration and cardiovascular disorders. Additionally, the alteration in Nitrotyrosine profile occurs well before appearance of any symptoms of aforementioned diseases making nitrotyrosine a biomarker and potential target for early prognosis of aforementioned diseases. The wet lab identification of potential nitrotyrosine sites is laborious, time-taking and costly due to challenges of in vitro, ex vivo and in vivo identification processes. To supplement wet lab identification of nitrotyrosine, we proposed, implemented and evaluated a different approach to develop tyrosine nitration site predictors using pseudo amino acid compositions (PseAAC) and deep neural networks (DNNs). Proposed approach does not require any feature extraction and uses DNNs for learning a feature representation of peptide sequences and classification thereof. Validation of proposed approach is done using well-known model evaluation measures. Among different deep neural networks, convolutional neural network-based predictor achieved best scores on independent dataset with accuracy of 87.2%, matthew’s correlation coefficient score of 0.74 and AuC score of 0.91 which outperforms the previous reported scores of Nitrotyrosine predictors.

Background: Amyloids are insoluble fibrillar aggregates that are highly associated with complex human diseases, such as Alzheimer's disease, Parkinson's disease, and type II diabetes. Recently, many studies reported that some specific regions of amino acid sequences may be responsible for the amyloidosis of proteins. It has become very important for elucidating the mechanism of amyloids that identifying the amyloidogenic regions. Accordingly, several computational methods have been put forward to discover amyloidogenic regions. The majority of these methods predicted amyloidogenic regions based on the physicochemical properties of amino acids. In fact, position, order, and correlation of amino acids may also influence the amyloidosis of proteins, which should be also considered in detecting amyloidogenic regions. Results: To address this problem, we proposed a novel machine-learning approach for predicting amyloidogenic regions, called ReRF-Pred. Firstly, the pseudo amino acid composition (PseAAC) was exploited to characterize physicochemical properties and correlation of amino acids. Secondly, tripeptides composition (TPC) was employed to represent the order and position of amino acids. To improve the distinguishability of TPC, all possible tripeptides were analyzed by the binomial distribution method, and only those which have significantly different distribution between positive and negative samples remained. Finally, all samples were characterized by PseAAC and TPC of their amino acid sequence, and a random forest-based amyloidogenic regions predictor was trained on these samples. It was proved by validation experiments that the feature set consisted of PseAAC and TPC is the most distinguishable one for detecting amyloidosis. Meanwhile, random forest is superior to other concerned classifiers on almost all metrics. To validate the effectiveness of our model, ReRF-Pred is compared with a series of gold-standard methods on two datasets: Pep-251 and Reg33. The results suggested our method has the best overall performance and makes significant improvements in discovering amyloidogenic regions. Conclusions: The advantages of our method are mainly attributed to that PseAAC and TPC can describe the differences between amyloids and other proteins successfully. The ReRF-Pred server can be accessed at http://106.12.83.135:8080/ReRF-Pred/. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

DNA replication is one of the specific processes to be considered in all the living organisms, specifically eukaryotes. The prevalence of DNA replication is significant for an evolutionary transition at the beginning of life. DNA replication proteins are those proteins which support the process of replication and are also reported to be important in drug design and discovery. This information depicts that DNA replication proteins have a very important role in human bodies, however, to study their mechanism, their identification is necessary. Thus, it is a very important task but, in any case, an experimental identification is time-consuming, highly-costly and laborious. To cope with this issue, a computational methodology is required for prediction of these proteins, however, no prior method exists. This study comprehends the construction of novel prediction model to serve the proposed purpose. The prediction model is developed based on the artificial neural network by integrating the position relative features and sequence statistical moments in PseAAC for training neural networks. Highest overall accuracy has been achieved through tenfold cross-validation and Jackknife testing that was computed to be 96.22% and 98.56%, respectively. Our astonishing experimental results demonstrated that the proposed predictor surpass the existing models that can be served as a time and cost-effective stratagem for designing novel drugs to strike the contemporary bacterial infection. [ABSTRACT FROM AUTHOR]

Redox-sensitive cysteine (RSC) thiol contributes to many biological processes. The identification of RSC plays an important role in clarifying some mechanisms of redox-sensitive factors; nonetheless, experimental investigation of RSCs is expensive and time-consuming. The computational approaches that quickly and accurately identify candidate RSCs using the sequence information are urgently needed. Herein, an improved and robust computational predictor named IRC-Fuse was developed to identify the RSC by fusing of multiple feature representations. To enhance the performance of our model, we integrated the probability scores evaluated by the random forest models implementing different encoding schemes. Cross-validation results exhibited that the IRC-Fuse achieved accuracy and AUC of 0.741 and 0.807, respectively. The IRC-Fuse outperformed exiting methods with improvement of 10% and 13% on accuracy and MCC, respectively, over independent test data. Comparative analysis suggested that the IRC-Fuse was more effective and promising than the existing predictors. For the convenience of experimental scientists, the IRC-Fuse online web server was implemented and publicly accessible at http://kurata14.bio.kyutech.ac.jp/IRC-Fuse/. [ABSTRACT FROM AUTHOR]

Background: A large number of allergens are derived from plant and animal proteins. A major challenge for researchers is to study the possible allergenic properties of proteins. The aim of this study was in silico analysis and comparison of several physiochemical and structural features of plant- and animal-derived allergen proteins, as well as classifying these proteins based on Chou's pseudo-amino acid composition (PseAAC) concept combined with bioinformatics algorithms. Methods: The physiochemical properties and secondary structure of plant and animal allergens were studied. The classification of the sequences was done using the PseAAC concept incorporated with the deep learning algorithm. Conserved motifs of plant and animal proteins were discovered using the MEME tool. B-cell and T-cell epitopes of the proteins were predicted in conserved motifs. Allergenicity and amino acid composition of epitopes were also analyzed via bioinformatics servers. Results: In comparison of physiochemical features of animal and plant allergens, extinction coefficient was different significantly. Secondary structure prediction showed more random coiled structure in plant allergen proteins compared with animal proteins. Classification of proteins based on PseAAC achieved 88.24% accuracy. The amino acid composition study of predicted B- and T-cell epitopes revealed more aliphatic index in plant-derived epitopes. Conclusions: The results indicated that bioinformatics-based studies could be useful in comparing plant and animal allergens. [ABSTRACT FROM AUTHOR]

Identification of the sites of post-translational modifications (PTMs) in protein, RNA, and DNA sequences is currently a very hot topic. This is because the information thus obtained is very useful for in-depth understanding the biological processes at the cellular level and for developing effective drugs against major diseases including cancers as well. Although this can be done by means of various experimental techniques, it is both time-consuming and costly to determine the PTM sites purely based on experiments. With the avalanche of biological sequences generated in the post-genomic age, it is highly desired to develop bioinformatics tools for rapidly and effectively identifying the PTM sites. In the last few years, many efforts have been made in this regard, and considerable progresses have been achieved. This review is focused on those prediction methods that have the following two features. (1) They have been developed by strictly observing the 5-steps rule so that they each have a user-friendly web-server for the majority of experimental scientists to easily get their desired data without the need to go through the detailed mathematics involved. (2) Their cornerstones have been based on Pseudo Amino Acid Composition (PseAAC) or Pseudo K-tuple Nucleotide Composition (PseKNC), and hence the prediction quality is generally higher than most of the other PTM prediction methods. [ABSTRACT FROM AUTHOR]

Facing the explosive growth of biological sequences unearthed in the post-genomic age, one of the most important but also most difficult problems in computational biology is how to express a biological sequence with a discrete model or a vector, but still keep it with considerable sequence-order information or its special pattern. To deal with such a challenging problem, the ideas of "pseudo amino acid components" and "pseudo K-tuple nucleotide composition" have been proposed. The ideas and their approaches have further stimulated the birth for "distorted key theory", "wenxing diagram", and substantially strengthening the power in treating the multi-label systems, as well as the establishment of the famous "5-steps rule". All these logic developments are quite natural that are very useful not only for theoretical scientists but also for experimental scientists in conducting genetics/genomics analysis and drug development. Presented in this review paper are also their future perspectives; i.e., their impacts will become even more significant and propounding. [ABSTRACT FROM AUTHOR]

Amidation is an important post translational modification where a peptide ends with an amide group (–NH2) rather than carboxyl group (–COOH). These amidated peptides are less sensitive to proteolytic degradation with extended half-life in the bloodstream. Amides are used in different industries like pharmaceuticals, natural products, and biologically active compounds. The in-vivo, ex-vivo, and in-vitro identification of amidation sites is a costly and time-consuming but important task to study the physiochemical properties of amidated peptides. A less costly and efficient alternative is to supplement wet lab experiments with accurate computational models. Hence, an urgent need exists for efficient and accurate computational models to easily identify amidated sites in peptides. In this study, we present a new predictor, based on deep neural networks (DNN) and Pseudo Amino Acid Compositions (PseAAC), to learn efficient, task-specific, and effective representations for valine amidation site identification. Well-known DNN architectures are used in this contribution to learn peptide sequence representations and classify peptide chains. Of all the different DNN based predictors developed in this study, Convolutional neural network-based model showed the best performance surpassing all other DNN based models and reported literature contributions. The proposed model will supplement in-vivo methods and help scientists to determine valine amidation very efficiently and accurately, which in turn will enhance understanding of the valine amidation in different biological processes.

• Antioxidant proteins are considered crucial in the areas of research on life sciences and pharmacology. • Herein, we report a predictor for identification of antioxidant proteins. • Chou's pseudo amino acid composition (PseAAC), statistical moments and various position based features have been used. • Our proposed system has achieved better accuracy than state-of-art systems in the identification of antioxidant proteins. • The proposed predictor can help in predicting the antioxidant proteins in an efficient and accurate way. Antioxidant proteins are considered crucial in the areas of research on life sciences and pharmacology. They prevent damage to cells and DNA which are caused by free radicals. The role of antioxidants in the ageing process makes them more significant in their accurate identification. Disease preventions through antioxidant protein have also been the area of study in recent past. The existing process to identify and test every single antioxidant protein in order to obtain its properties is inefficient and expensive. Due to this nature, many pharmaceutical agents have reflected antioxidant proteins as attractive targets. Approaches based on computational methodologies have appeared to be as a highly desirable resource in the annotation and determination process of antioxidant proteins. In this study, we have developed a method that is built on computation intelligence and statistical moments based features for prediction. Our proposed system has achieved better accuracy than state-of-art systems in the prediction of antioxidant proteins from non-antioxidant proteins using 10-fold-cross-validation tests. These outcomes suggest that the use of statistical moments with a multilayer neural network could bear more effective and efficient results. [ABSTRACT FROM AUTHOR]

Highlights • We propose a 2-tier predictor namely SPrenylC-PseAAC for S-prenylation sites. • At first level, identification of prenylation and non-prenylation sites is performed. • 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. • The SPrenylC-PseAAC is available at (biopred.org/prenyl). Abstract 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). [ABSTRACT FROM AUTHOR]

An antigen is a protein capable of triggering an effective immune system response. Protective antigens are the ones that can invoke specific and enhanced adaptive immune response to subsequent exposure to the specific pathogen or related organisms. Such proteins are therefore of immense importance in vaccine preparation and drug design. However, the laboratory experiments to isolate and identify antigens from a microbial pathogen are expensive, time consuming and often unsuccessful. This is why Reverse Vaccinology has become the modern trend of vaccine search, where computational methods are first applied to predict protective antigens or their determinants, known as epitopes. In this paper, we propose a novel, accurate computational model to identify protective antigens efficiently. Our model extracts features directly from the protein sequences, without any dependence on functional domain or structural information. After relevant features are extracted, we have used Random Forest algorithm to rank the features. Then Recursive Feature Elimination (RFE) and minimum redundancy maximum relevance (mRMR) criterion were applied to extract an optimal set of features. The learning model was trained using Random Forest algorithm. Named as Antigenic, our proposed model demonstrates superior performance compared to the state-of-the-art predictors on a benchmark dataset. Antigenic achieves accuracy, sensitivity and specificity values of 78.04%, 78.99% and 77.08% in 10-fold cross-validation testing respectively. In jackknife cross-validation, the corresponding scores are 80.03%, 80.90% and 79.16% respectively. The source code of Antigenic, along with relevant dataset and detailed experimental results, can be found at https://github.com/srautonu/AntigenPredictor. A publicly accessible web interface has also been established at: http://antigenic.research.buet.ac.bd. [ABSTRACT FROM AUTHOR]

Protein phosphorylation is one of the most fundamental types of post-translational modifications and it plays a vital role in various cellular processes of eukaryotes. Among three types of phosphorylation i.e. serine, threonine and tyrosine phosphorylation, tyrosine phosphorylation is one of the most frequent and it is important for mediation of signal transduction in eukaryotic cells. Site-directed mutagenesis and mass spectrometry help in the experimental determination of cellular signalling networks, however, these techniques are costly, time taking and labour associated. Thus, efficient and accurate prediction of these sites through computational approaches can be beneficial to reduce cost and time. Here, we present a more accurate and efficient sequence-based computational method for prediction of phosphotyrosine (PhosY) sites by incorporation of statistical moments into PseAAC. The study is carried out based on Chou’s 5-step rule, and various position-composition relative features are used to train a neural network for the prediction purpose. Validation of results through Jackknife testing is performed to validate the results of the proposed prediction method. Overall accuracy validated through Jackknife testing was calculated 93.9%. These results suggest that the proposed prediction model can play a fundamental role in the prediction of PhosY sites in an accurate and efficient way. [ABSTRACT FROM AUTHOR]

A DNA-binding protein (DNA-BP) is a protein that can bind and interact with a DNA. Identification of DNA-BPs using experimental methods is expensive as well as time consuming. As such, fast and accurate computational methods are sought for predicting whether a protein can bind with a DNA or not. In this paper, we focus on building a new computational model to identify DNA-BPs in an efficient and accurate way. Our model extracts meaningful information directly from the protein sequences, without any dependence on functional domain or structural information. After feature extraction, we have employed Random Forest (RF) model to rank the features. Afterwards, we have used Recursive Feature Elimination (RFE) method to extract an optimal set of features and trained a prediction model using Support Vector Machine (SVM) with linear kernel. Our proposed method, named as DNA-binding Protein Prediction model using Chou’s general PseAAC (DPP-PseAAC) , demonstrates superior performance compared to the state-of-the-art predictors on standard benchmark dataset. DPP-PseAAC achieves accuracy values of 93.21%, 95.91% and 77.42% for 10-fold cross-validation test, jackknife test and independent test respectively. The source code of DPP-PseAAC, along with relevant dataset and detailed experimental results, can be found at https://github.com/srautonu/DNABinding . A publicly accessible web interface has also been established at: http://77.68.43.135:8080/DPP-PseAAC/ . [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

DNA methylation is an important biochemical process, and it has a close connection with many types of cancer. Research about DNA methylation can help us to understand the regulation mechanism and epigenetic reprogramming. Therefore, it becomes very important to recognize the methylation sites in the DNA sequence. In the past several decades, many computational methods—especially machine learning methods—have been developed since the high-throughout sequencing technology became widely used in research and industry. In order to accurately identify whether or not a nucleotide residue is methylated under the specific DNA sequence context, we propose a novel method that overcomes the shortcomings of previous methods for predicting methylation sites. We use k-gram, multivariate mutual information, discrete wavelet transform, and pseudo amino acid composition to extract features, and train a sparse Bayesian learning model to do DNA methylation prediction. Five criteria—area under the receiver operating characteristic curve (AUC), Matthew’s correlation coefficient (MCC), accuracy (ACC), sensitivity (SN), and specificity—are used to evaluate the prediction results of our method. On the benchmark dataset, we could reach 0.8632 on AUC, 0.8017 on ACC, 0.5558 on MCC, and 0.7268 on SN. Additionally, the best results on two scBS-seq profiled mouse embryonic stem cells datasets were 0.8896 and 0.9511 by AUC, respectively. When compared with other outstanding methods, our method surpassed them on the accuracy of prediction. The improvement of AUC by our method compared to other methods was at least 0.0399. For the convenience of other researchers, our code has been uploaded to a file hosting service, and can be downloaded from: https://figshare.com/s/0697b692d802861282d3. [ABSTRACT FROM AUTHOR]

Predicting protein subcellular location with support vector machine has been a popular research area recently because of the dramatic explosion of bioinformation. Though substantial achievements have been obtained, few researchers considered the problem of data imbalance before classification, which will lead to low accuracy for some categories. So in this work, we combined oversampling method with SVM to deal with the protein subcellular localization of unbalanced data sets. To capture valuable information of a protein, a PseAAC (Pseudo Amino Acid Composition) has been extracted from PSSM(Position-Specific Scoring Matrix) as a feature vector, and then be selected by principal component analysis (PCA). Next, samples which are treated by oversampling method to eliminate the imbalance of sample numbers in different classes are fed into support vector machine to predict the protein subcellular location. To evaluate the performance of proposed method, Jackknife tests are performed on three benchmark datasets (ZD98, CL317 and ZW225). Results of SVM experiments with and without oversampling gained by Jackknife tests show that oversampling methods have successfully decrease the imbalance of data sets, and the prediction accuracy of each class in each dataset is higher than 88.9%. With comparison with other protein subcellular localization methods, the method in this work reaches the best performance. The overall accuracies of ZD98, CL317 and ZW225 are 93.2%, 96.00% and 92.15% respectively, which are 2.4%, 8.0% and 8.2% higher than the best methods in the comparison. The excellent overall accuracy gained by the proposed method indicates that the feature representation and selection capture useful information of protein sequence and oversampling methods successfully solve the imbalance of sample numbers in SVM classification. [ABSTRACT FROM AUTHOR]

Many efforts have been made in predicting the subcellular localization of eukaryotic proteins, but most of the existing methods have the following two limitations: (1) their coverage scope is less than ten locations and hence many organelles in an eukaryotic cell cannot be covered, and (2) they can only be used to deal with single-label systems in which each of the constituent proteins has one and only one location. Actually, proteins with multiple locations are particularly interesting since they may have some exceptional functions very important for in-depth understanding the biological process in a cell and for selecting drug target as well. Although several predictors (such as “Euk-mPLoc”, “Euk-PLoc 2.0” and “iLoc-Euk”) can cover up to 22 different location sites, and they also have the function to treat multi-labeled proteins, further efforts are needed to improve their prediction quality, particularly in enhancing the absolute true rate and in reducing the absolute false rate. Here we propose a new predictor called “pLoc-mEuk” by extracting the key GO (Gene Ontology) information into the general PseAAC (Pseudo Amino Acid Composition). Rigorous cross-validations on a high-quality and stringent benchmark dataset have indicated that the proposed pLoc-mEuk predictor is remarkably superior to iLoc-Euk, the best of the aforementioned three predictors. To maximize the convenience of most experimental scientists, a user-friendly web-server for the new predictor has been established at http://www.jci-bioinfo.cn/pLoc-mEuk/ , by which users can easily get their desired results without the need to go through the complicated mathematics involved. [ABSTRACT FROM AUTHOR]

This data article contains the benchmark dataset for training and testing iRNA-Methyl, a web-server predictor for identifying N6-methyladenosine sites in RNA (Chen et al., 2015 [15]). It can also be used to develop other predictors for identifying N6-methyladenosine sites in the Saccharomyces cerevisiae genome.

Research on cytokine recognition is of great significance in the medical field due to the fact cytokines benefit the diagnosis and treatment of diseases, but the current methods for cytokine recognition have many shortcomings, such as low sensitivity and low F-score. Therefore, this paper proposes a new method on the basis of feature combination. The features are extracted from compositions of amino acids, physicochemical properties, secondary structures, and evolutionary information. The classifier used in this paper is SVM. Experiments show that our method is better than other methods in terms of accuracy, sensitivity, specificity, F-score and Matthew’s correlation coefficient.

Extracellular Matrix (ECM) proteins are the vital type of proteins that are secreted by resident cells. ECM proteins perform several significant functions including adhesion, differentiation, cell migration and proliferation. In addition, ECM proteins regulate angiogenesis process, embryonic development, tumor growth and gene expression. Due to tremendous biological significance of the ECM proteins and rapidly increases of protein sequences in databases, it is indispensable to introduce a new high throughput computation model that can accurately identify ECM proteins. Various traditional models have been developed, but they are laborious and tedious. In this work, an effective and high throughput computational classification model is proposed for discrimination of ECM proteins. In this model, protein sequences are formulated using amino acid composition, pseudo amino acid composition (PseAAC) and di-peptide composition (DPC) techniques. Further, various combination of feature extraction techniques are fused to form hybrid feature spaces. Several classifiers were employed. Among these classifiers, K-Nearest Neighbor obtained outstanding performance in combination with the hybrid feature space of PseAAC and DPC. The obtained accuracy of our proposed model is 96.76%, which the highest success rate has been reported in the literature so far. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Succinylation is a posttranslational modification (PTM) where a succinyl group is added to a Lys (K) residue of a protein molecule. Lysine succinylation plays an important role in orchestrating various biological processes, but it is also associated with some diseases. Therefore, we are challenged by the following problem from both basic research and drug development: given an uncharacterized protein sequence containing many Lys residues, which one of them can be succinylated, and which one cannot? With the avalanche of protein sequences generated in the postgenomic age, the answer to the problem has become even more urgent. Fortunately, the statistical significance experimental data for succinylated sites in proteins have become available very recently, an indispensable prerequisite for developing a computational method to address this problem. By incorporating the sequence-coupling effects into the general pseudo amino acid composition and using KNNC ( K -nearest neighbors cleaning) treatment and IHTS (inserting hypothetical training samples) treatment to optimize the training dataset, a predictor called iSuc-PseOpt has been developed. Rigorous cross-validations indicated that it remarkably outperformed the existing method. A user-friendly web-server for iSuc-PseOpt has been established at http://www.jci-bioinfo.cn/iSuc-PseOpt , where users can easily get their desired results without needing to go through the complicated mathematical equations involved. [ABSTRACT FROM AUTHOR]

With the rapid growth of RNA sequences generated in the postgenomic age, it is highly desired to develop a flexible method that can generate various kinds of vectors to represent these sequences by focusing on their different features. This is because nearly all the existing machine-learning methods, such as SVM (support vector machine) and KNN ( k-nearest neighbor), can only handle vectors but not sequences. To meet the increasing demands and speed up the genome analyses, we have developed a new web server, called 'representations of RNA sequences' (repRNA). Compared with the existing methods, repRNA is much more comprehensive, flexible and powerful, as reflected by the following facts: (1) it can generate 11 different modes of feature vectors for users to choose according to their investigation purposes; (2) it allows users to select the features from 22 built-in physicochemical properties and even those defined by users' own; (3) the resultant feature vectors and the secondary structures of the corresponding RNA sequences can be visualized. The repRNA web server is freely accessible to the public at . [ABSTRACT FROM AUTHOR]

Knowledge of protein-protein interactions and their binding sites is indispensable for in-depth understanding of the networks in living cells. With the avalanche of protein sequences generated in the postgenomic age, it is critical to develop computational methods for identifying in a timely fashion the protein-protein binding sites (PPBSs) based on the sequence information alone because the information obtained by this way can be used for both biomedical research and drug development. To address such a challenge, we have proposed a new predictor, called iPPBS-Opt, in which we have used: (1) the K-Nearest Neighbors Cleaning (KNNC) and Inserting Hypothetical Training Samples (IHTS) treatments to optimize the training dataset; (2) the ensemble voting approach to select the most relevant features; and (3) the stationary wavelet transform to formulate the statistical samples. Cross-validation tests by targeting the experiment-confirmed results have demonstrated that the new predictor is very promising, implying that the aforementioned practices are indeed very effective. Particularly, the approach of using the wavelets to express protein/peptide sequences might be the key in grasping the problem's essence, fully consistent with the findings that many important biological functions of proteins can be elucidated with their low-frequency internal motions. To maximize the convenience of most experimental scientists, we have provided a step-by-step guide on how to use the predictor's web server (http://www.jci-bioinfo.cn/iPPBS-Opt) to get the desired results without the need to go through the complicated mathematical equations involved. [ABSTRACT FROM AUTHOR]

Abstract: The pseudo oligonucleotide composition, or pseudo K-tuple nucleotide composition (PseKNC), can be used to represent a DNA or RNA sequence with a discrete model or vector yet still keep considerable sequence order information, particularly the global or long-range sequence order information, via the physicochemical properties of its constituent oligonucleotides. Therefore, the PseKNC approach may hold very high potential for enhancing the power in dealing with many problems in computational genomics and genome sequence analysis. However, dealing with different DNA or RNA problems may need different kinds of PseKNC. Here, we present a flexible and user-friendly web server for PseKNC (at http://lin.uestc.edu.cn/pseknc/default.aspx) by which users can easily generate many different modes of PseKNC according to their need by selecting various parameters and physicochemical properties. Furthermore, for the convenience of the vast majority of experimental scientists, a step-by-step guide is provided on how to use the current web server to generate their desired PseKNC without the need to follow the complicated mathematical equations, which are presented in this article just for the integrity of PseKNC formulation and its development. It is anticipated that the PseKNC web server will become a very useful tool in computational genomics and genome sequence analysis. [Copyright &y& Elsevier]

Post-translational modifications (PTMs) play crucial roles in various cell functions and biological processes. Protein hydroxylation is one type of PTM that usually occurs at the sites of proline and lysine. Given an uncharacterized protein sequence, which site of its Pro (or Lys) can be hydroxylated and which site cannot? This is a challenging problem, not only for in-depth understanding of the hydroxylation mechanism, but also for drug development, because protein hydroxylation is closely relevant to major diseases, such as stomach and lung cancers. With the avalanche of protein sequences generated in the post-genomic age, it is highly desired to develop computational methods to address this problem. In view of this, a new predictor called "iHyd-PseAAC" (identify hydroxylation by pseudo amino acid composition) was proposed by incorporating the dipeptide position-specific propensity into the general form of pseudo amino acid composition. It was demonstrated by rigorous cross-validation tests on stringent benchmark datasets that the new predictor is quite promising and may become a useful high throughput tool in this area. A user-friendly web-server for iHyd-PseAAC is accessible at http://app.aporc.org/iHyd-PseAAC/. Furthermore, for the convenience of the majority of experimental scientists, a step-by-step guide on how to use the web-server is given. Users can easily obtain their desired results by following these steps without the need of understanding the complicated mathematical equations presented in this paper just for its integrity. [ABSTRACT FROM AUTHOR]

Abstract: Heat shock proteins (HSPs) are a type of functionally related proteins present in all living organisms, both prokaryotes and eukaryotes. They play essential roles in protein–protein interactions such as folding and assisting in the establishment of proper protein conformation and prevention of unwanted protein aggregation. Their dysfunction may cause various life-threatening disorders, such as Parkinson’s, Alzheimer’s, and cardiovascular diseases. Based on their functions, HSPs are usually classified into six families: (i) HSP20 or sHSP, (ii) HSP40 or J-class proteins, (iii) HSP60 or GroEL/ES, (iv) HSP70, (v) HSP90, and (vi) HSP100. Although considerable progress has been achieved in discriminating HSPs from other proteins, it is still a big challenge to identify HSPs among their six different functional types according to their sequence information alone. With the avalanche of protein sequences generated in the post-genomic age, it is highly desirable to develop a high-throughput computational tool in this regard. To take up such a challenge, a predictor called iHSP-PseRAAAC has been developed by incorporating the reduced amino acid alphabet information into the general form of pseudo amino acid composition. One of the remarkable advantages of introducing the reduced amino acid alphabet is being able to avoid the notorious dimension disaster or overfitting problem in statistical prediction. It was observed that the overall success rate achieved by iHSP-PseRAAAC in identifying the functional types of HSPs among the aforementioned six types was more than 87%, which was derived by the jackknife test on a stringent benchmark dataset in which none of HSPs included has ⩾40% pairwise sequence identity to any other in the same subset. It has not escaped our notice that the reduced amino acid alphabet approach can also be used to investigate other protein classification problems. As a user-friendly web server, iHSP-PseRAAAC is accessible to the public at http://lin.uestc.edu.cn/server/iHSP-PseRAAAC. [Copyright &y& Elsevier]

Mitochondrial protein of Plasmodium falciparum is an important target for anti-malarial drugs. Experi-mental approaches for detecting mitochondrial proteins are costly and time consuming. Therefore, MitProt-Pred is developed that utilizes Bi-profile Bayes, Pseudo Average Chemical Shift, Split Amino Acid Composition, and Pseudo Amino Acid Composition based features of the protein sequences. Hybrid feature space is also developed by combining different individual feature spaces. These feature spaces are learned and exploited through SVM based ensemble. MitProt-Pred achieved significantly improved prediction performance for two standard datasets. We also developed the score level ensemble, which outperforms the feature level ensemble. [ABSTRACT FROM AUTHOR]

Abstract: With the accomplishment of human genome sequencing, the number of sequence-known proteins has increased explosively. In contrast, the pace is much slower in determining their biological attributes. As a consequence, the gap between sequence-known proteins and attribute-known proteins has become increasingly large. The unbalanced situation, which has critically limited our ability to timely utilize the newly discovered proteins for basic research and drug development, has called for developing computational methods or high-throughput automated tools for fast and reliably identifying various attributes of uncharacterized proteins based on their sequence information alone. Actually, during the last two decades or so, many methods in this regard have been established in hope to bridge such a gap. In the course of developing these methods, the following things were often needed to consider: (1) benchmark dataset construction, (2) protein sample formulation, (3) operating algorithm (or engine), (4) anticipated accuracy, and (5) web-server establishment. In this review, we are to discuss each of the five procedures, with a special focus on the introduction of pseudo amino acid composition (PseAAC), its different modes and applications as well as its recent development, particularly in how to use the general formulation of PseAAC to reflect the core and essential features that are deeply hidden in complicated protein sequences. [Copyright &y& Elsevier]

One of the main challenges faced by biological applications is to predict protein subcellular localization in an automatic fashion accurately. To achieve this in these applications, a wide variety of machine learning methods have been proposed in recent years. Most of them focus on finding the optimal classification scheme and less of them take the simplifying the complexity of biological system into account. Traditionally such bio-data are analyzed by first performing a feature selection before classification. Motivated by CS (Compressive Sensing), we propose a method which performs locality preserving projection with a sparseness criterion such that the feature selection and dimension reduction are merged into one analysis. The proposed sparse method decreases the complexity of biological system, while increases protein subcellular localization accuracy. Experimental results are quite encouraging, indicating that the aforementioned sparse method is quite promising in dealing with complicated biological problems, such as predicting the subcellular localization of Gram-negative bacterial proteins. [ABSTRACT FROM AUTHOR]

Lysine glutarylation is a post-translation modification which plays an important regulatory role in a variety of physiological and enzymatic processes including mitochondrial functions and metabolic processes both in eukaryotic and prokaryotic cells. This post-translational modification influences chromatin structure and thereby results in global regulation of transcription, defects in cell-cycle progression, DNA damage repair, and telomere silencing. To better understand the mechanism of lysine glutarylation, its identification in a protein is necessary, however, experimental methods are time-consuming and labor-intensive. Herein, we propose a new computational prediction approach to supplement experimental methods for identification of lysine glutarylation site prediction by deep neural networks and Chou's Pseudo Amino Acid Composition (PseAAC). We employed well-known deep neural networks for feature representation learning and classification of peptide sequences. Our approach opts raw pseudo amino acid compositions and obsoletes the need to separately perform costly and cumbersome feature extraction and selection. Among the developed deep learning-based predictors, the standard neural network-based predictor demonstrated highest scores in terms of accuracy and all other performance evaluation measures and outperforms majority of previously reported predictors without requiring expensive feature extraction process. iGluK-Deep:Computational Identification of lysine glutarylationsites using deep neural networks with general Pseudo Amino Acid Compositions Sheraz Naseer, Rao Faizan Ali, Yaser Daanial Khan, P.D.D DominicCommunicated by Ramaswamy H. Sarma.

Amidation is an important post translational modification where a peptide ends with an amide group (–NH2) rather than carboxyl group (–COOH). These amidated peptides are less sensitive to proteolytic degradation with extended half-life in the bloodstream. Amides are used in different industries like pharmaceuticals, natural products, and biologically active compounds. The in-vivo, ex-vivo, and in-vitro identification of amidation sites is a costly and time-consuming but important task to study the physiochemical properties of amidated peptides. A less costly and efficient alternative is to supplement wet lab experiments with accurate computational models. Hence, an urgent need exists for efficient and accurate computational models to easily identify amidated sites in peptides. In this study, we present a new predictor, based on deep neural networks (DNN) and Pseudo Amino Acid Compositions (PseAAC), to learn efficient, task-specific, and effective representations for valine amidation site identification. Well-known DNN architectures are used in this contribution to learn peptide sequence representations and classify peptide chains. Of all the different DNN based predictors developed in this study, Convolutional neural network-based model showed the best performance surpassing all other DNN based models and reported literature contributions. The proposed model will supplement in-vivo methods and help scientists to determine valine amidation very efficiently and accurately, which in turn will enhance understanding of the valine amidation in different biological processes. [ABSTRACT FROM AUTHOR]