Figure 1 - uploaded by Nazar M Zaki
Content may be subject to copyright.
![Schematic illustration to show the eight types of membrane proteins: (1) type I transmembrane, (2) type II, (3) type III, (4) type IV, (5) multipass transmembrane, (6) lipid- chain-anchored membrane, (7) GPI-anchored membrane, and (8) peripheral membrane [6].](profile/Nazar-Zaki/publication/221051742/figure/fig1/AS:305524190007296@1449854051192/Schematic-illustration-to-show-the-eight-types-of-membrane-proteins-1-type-I.png)
Schematic illustration to show the eight types of membrane proteins: (1) type I transmembrane, (2) type II, (3) type III, (4) type IV, (5) multipass transmembrane, (6) lipid- chain-anchored membrane, (7) GPI-anchored membrane, and (8) peripheral membrane [6].
Context in source publication
Context 1
... membrane protein; inter-domain linkers; support vector machines A membrane protein is a protein molecule that is attached to, or associated with the membrane of a cell or an organelle. Membrane proteins play key roles in controlling the processes of life. Given the importance of membrane proteins in various cellular processes, the roles they play in diseases and their potential as drug targets, it is imperative that the types of proteins be better studied [1]. The determination of function for new membrane proteins can be expedited significantly if we can find an effective scheme and algorithm to predict their types. The types of the membrane proteins are shown in Fig. 1. The function of a membrane protein is closely correlated with the type it belongs to. With the rapid increment of the number of protein sequences entering into public data banks; it would be both time-consuming and costly to rely on completely experimental work to predict membrane types. This is why the development of computational tools that are capable of predicting the types of membrane proteins is growing. Hence, computational approaches remain essential to assist in design and validation of the experimental studies. As a result, a vast set of impressive computational methods have been developed. However, most of the recent state-of –the-art computational methods (e.g. [2]-[6]) have one common drawback. They are either based on amino acid composition knowledge or considering all sequence-order effects by using pseudo amino acid composition. Predicting membrane protein types using amino acid composition is simple and provides information about the supplementary or complementary value of proteins. Nevertheless, a serious weakness is that using amino acid composition does not take into account the bioavailability of the amino acids and their structural relationships. Very little work is done to use protein structural knowledge to represent membrane protein sequences. In this paper, we utilize the structural knowledge as a way to represent the membrane protein sample. We introduced a novel technique to efficiently extract the protein functional domain using inter-domain linkers regions as a way to incorporate structural knowledge. The identification of protein functional domains plays an important role in protein structure comparison. The comparison of membrane protein structures allows one to peer back farther into evolutionary time, based on the concept that a form or structure remains similar long after membrane sequence similarity has become undetectable [7]-[10]. Once the membrane protein is represented, a novel matching algorithm is introduced to measure the sensitivity of the extracted protein domains to the membrane protein sequence. A protein domain is a part of protein sequence and structure that can evolve, function, and exist independently of the rest of the protein chain. Each domain usually forms a compact three-dimensional structure and often can be independently stable and folded. Many proteins consist of several structural domains. One domain may appear in a variety of evolutionarily related membrane protein sequences. A powerful machine learning algorithm such as support vector machine (SVM) is then utilized to discriminate between eight membrane protein types. The algorithm for predicting membrane protein types based on functional dom ain mat ching (DomMat) consists of two major ...
Similar publications
Citations
... For protein membrane classification several specialized classification methods are also used. This database gives comprehensive information, diagrams and web tools for G protein-coupled receptors [8]. Protein structures contains amino acid classifications and physicochemical properties. ...
... Nazar et al. [8] have proposed a technique named DomMat to predict membrane protein types. This technique is used to extract functional domains by eliminating all the consequent inter-domain linkers from the membrane protein sequence. ...
Membrane proteins provide a significant part in cellular activities. The role of membrane proteins is inevitable in drug interactions and in all living organisms. Membrane protein classification is used to identify the relationships between proteins. With the help of amino acid composition, proteins get classified. A novel protein classification scheme is proposed using Tri-code Embedding vector. This proposed method forms triplet subgroups which are assigned with unique code words. Then a triplet subgroup is formed from the amino acid subgroup which is provided as input to the Bidirectional Long Short-Term Memory (BiLSTM) and SoftMax layer for classification. Two data sets are utilized and classified, with 7582 membrane proteins and 4684 membrane proteins. The results are investigated applying the self-consistency test, the Mathew’s correlation coefficient and the independent data set. Moreover, the proposed method shows its improvement in protein classification process in terms of accuracy, specificity, sensitivity, precision, recall and fmeasure. Thus, the proposed scheme provides an effective protein classification scheme that incorporates the optimistic features of deep learning. The results depict that overall accuracy obtained for data set1 is 99.48% and for data set2 is 99.87%. The proposed method achieves the highest overall classification accuracy with minimum execution time when compared to the other methods.
... Nazar et al. [13] have proposed DomMat which is a method to predict membrane protein types. In this technique functional domains are extracted by eliminating all the consequent inter-domain linkers from the membrane protein sequence. ...
Cell membrane proteins play an essentially significant function in manipulating the behaviour of cells. Examination of amino acid sequences can put forward useful insights into the tertiary structures of proteins and their biological functions. One of the important problems in amino acid analysis is the uncertainty to establish a digital coding system to better reflect the properties of amino acids and their degeneracy. In order to overcome the demerits, the proposed method is a novel representation of protein sequences that incorporates a new feature named 2-gram subgroup intra pattern. The functional types of membrane protein classification will be supportive to explain the biological functions of membrane proteins. For classification, Stacked Auto Encoder Deep learning method is applied. The performance of the proposed method is evaluated on two benchmark data sets. The results were experimented using the Self-consistency test, Accuracy, Specificity, Sensitivity, Mathew’s correlation coefficient, Jackknife test and Independent data set are the tests in which the proposed method outperformed other existing techniques generally used in literatures.
... In this study, the benchmark dataset consisting of 7582 membrane proteins was collected and taken from Shibiao et al. (2016 ) and used in various papers ( Chen and Li, 2013;Hayat et al., 2012;Mahdavi and Jahandideh,2011;Nanni and Lumini, 2008;Zaki and El -Hajj, 2010;Wang et al., 2008Wang et al., , 2010bWang et al., , 2012. Dataset for all the eight types of proteins were collected by the authors and a redundancy cut off is applied to avoid redundancy among the sequences. ...
Predicting membrane protein types is an important and challenging research area in bioinformatics and proteomics. Traditional biophysical methods are used to classify membrane protein types. Due to large exploration of uncharacterized protein sequences in databases, traditional methods are very time consuming, expensive and susceptible to errors. Hence, it is highly desirable to develop a robust, reliable, and efficient method to predict membrane protein types. Imbalanced datasets and large datasets are often handled well by decision tree classifiers. Since imbalanced datasets are taken, the performance of various decision tree classifiers such as Decision Tree (DT), Classification And Regression Tree (CART), C4.5, Random tree, REP (Reduced Error Pruning) tree, ensemble methods such as Adaboost, RUS (Random Under Sampling) boost, Rotation forest and Random forest are analysed. Among the various decision tree classifiers Random forest performs well in less time with good accuracy of 96.35%. Another inference is RUS boost decision tree classifier is able to classify one or two samples in the class with very less samples while the other classifiers such as DT, Adaboost, Rotation forest and Random forest are not sensitive for the classes with fewer samples. Also the performance of decision tree classifiers is compared with SVM (Support Vector Machine ) and Naive Bayes classifier.
Membrane proteins provide a significant part in cellular activities. The role of membrane proteins is inevitable in drug interactions and in all living organisms. Membrane protein classification is used to identify the relationships between proteins. With the help of amino acid composition, proteins get classified. A novel protein classification scheme is proposed using Tri-code Embedding vector. The results are investigated applying the self-consistency test, the Mathew’s correlation coefficient and the independent data set. Moreover, the proposed method shows its improvement in protein classification process in terms of accuracy, specificity and sensitivity. Thus, the proposed scheme provides an effective protein classification scheme that incorporates the optimistic features of deep learning.
