A Treatise to Computational Approaches Towards Prediction of Membrane Protein and Its Subtypes

Abstract

Membrane proteins are vital mediating molecules responsible for the interaction of a cell with its surroundings. These proteins are involved in different functionalities such as ferrying of molecules and nutrients across membrane, recognizing foreign bodies, receiving outside signals and translating them into the cell. Membrane proteins play significant role in drug interaction as nearly 50% of the drug targets are membrane proteins. Due to the momentous role of membrane protein in cell activity, computational models able to predict membrane protein with accurate measures bears indispensable importance. The conventional experimental methods used for annotating membrane proteins are time-consuming and costly and in some cases impossible. Computationally intelligent techniques have emerged to be as a useful resource in the automation of prediction and hence the annotation process. In this study, various techniques have been reviewed that are based on different computational intelligence models used for prediction process. These techniques were formulated by different researchers and were further evaluated to provide a comparative analysis. Analysis shows that the usage of support vector machine-based prediction techniques bears more assiduous results.

Prediction of N-linked glycosylation sites using position relative features and statistical moments

“…The accuracy of the predictive model is 99.9% by aggregating the positive and negative results of 10-fold cross validation. Some of the existing glycosylation prediction models have also used the cross validation approach to define accuracy of their proposed model [ 9 , 11 , 31 , 35 ]. A comparison of their outcomes based on the cross validation test along with the result of the proposed model is depicted in Table 3 .…”

“…Researchers have made numerous contributions in developing several computational models to predict an attribute of a protein [ 8 ]. Studies showed that attributes of a protein are reliant not only on the composition of amino acids but also on the sequence in which amino acids occur in the polypeptide chain [ 9 ]. The recent work in [ 10 ] reviews design of effective feature extraction techniques based upon composition as well as the sequence of component amino acids.…”

Efficient Prediction of Liver Disease using Selected Attributes

“…It also helps the system to work more efficiently with less computation time and early decision making. The results are following: Different classifiers have been used on two different datasets that are; whole attribute dataset and selected attribute dataset [11,12]. Both datasets give different results of classifiers with evaluation measures (accuracy and computation).…”

Image Processing Architectures

“…Processing elements have interrelated by permutation system that can execute most promising permutations to move data within the elements that are being processed. Consideration of substituting network is also important for rearranging because, if the structure is organized as autonomous SIMD processors or a set of it, transmission of data for one SIMD processor does not affect with those of another [16,17].…”