Incorporating post translational modification information for enhancing the predictive performance of membrane transport proteins. (December 2018)

• Record Type: Journal Article
• Authors: Le, Nguyen Quoc Khanh; Sandag, Green Arther; Ou, Yu-Yen
• Is Part Of: Computational biology and chemistry. Volume 77(2018)
• Page Start: 251
• Page End: 260
• Publication Date: 2018-12
• Subjects: Transport protein -- Post translational modification -- Radial basis function neural networks -- Position specific scoring matrix; Chemistry -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; Biochemistry -- Data processing; Biology -- Data processing; Molecular biology -- Data processing; Periodicals; Electronic journals; 542.85
• DOI: 10.1016/j.compbiolchem.2018.10.010
• Languages: English
• ISSNs: 1476-9271

Abstract

Graphical abstract: Highlights: An advanced technique for discriminating membrane transport proteins in different classes and families. The performance is improved with post translational modification information and position specific scoring matrices. Our method performs better than other methods and published works. A powerful model to help biologists understanding better the function of transport proteins. A basis for further research could use PTM information to improve bioinformatics problems. Abstract: Transporters involved in the cellular entry and exit of ions or molecules throughout the membrane proteins and thereby play an essential role in recognizing the immune system and energy transducers. According to their relevance in proteomics, numerous studies have been conducted to analyze the transporters; especially the discrimination of their classes and subfamilies. We realized that post translational modification information had a critical role in the process of transport proteins. Therefore, in this study, we aim to incorporate post translational information with radial basis function networks to improve the predictive performance of transport proteins in major classes (channels/pores, electrochemical transporters, and active transporters) and six different families (α-type channels, β-barrel porins, pore-forming toxins, porters, PP bond hydrolysis-driven transporters, and oxidoreduction-driven transporters). The experiment results by using PSSM profiles combined with PTM information could classify the transporters into three classes and six families with five-fold cross-validation accuracy of 87.6% and 92.5%, respectively. For the independent dataset of 444 proteins, the performance with post translational modification attained the accuracy of 82.13% and 89.34% for classifying three classes and six families, respectively. Compared with the other methods and previous works, our result shows that the predictive performance is better with the accuracy improvement by 12%. We suggest that our study could become a robust model for biologists to discriminate transport proteins with high performance and understand better the function of transport proteins. Further, the contributions of this study could be fundamental for further research that can use PTM information to enhance numerous computational biology problems.