Classification of Membrane Protein Types by Using Machine Learning Approach
Keywords:
Multilabel Classification, Membrane Protein Type, Machine LearningAbstract
The Membrane proteins are performing different cellular processes and important functions, which are based on the protein types. Each membrane protein have different roles at the same time this is called multi class classification. A general form of multi class classification is Multi-label classification. Each membrane proteins are lies in different classes at the same time that is known as multi label classification. The main feature of multilabel problem is that the instance can be assigned to any number of classes. Our proposed method is a multi label classification of membrane proteins by implementing machine learning algorithm like Logistic Regression Classification, Random Forest Classification and Neural Network Classification. An essential set of features are extracted from the homo-sapiens dataset S1 which are used for the proposed method, and it was revealed an accuracy of 89. 176%, whereas existing methods are revealed an accuracy is 58. 923%, 40. 769% for the Decision tree and Support vector machine respectively. Both accuracy wise and complexity wise, the proposed method seems to be better than the existing method.
References
- Lei GUO1, Shunfang WANG 1, Zhenfeng LEI 2, AND XUEREN WANG3” Prediction for Membrane Protein Types Based on Effective Fusion Representation and MIC-GA Feature Selection”
- NijilRajNandT. Mahalekshmi, ”MultilabelClassificationOf “MembraneProtein in Human byDecision Tree(DT)Approach. ”Biomedical&PharmacologyJournalVol. 11(1), 113-121(2018)
- M. S. Alme´n, K. J. Nordstro¨ m, R. Fredriksson, and H. B. Schio¨ th, “Mapping the human membrane proteome: a majority of the human membrane proteins can be classified according to function and evolutionary origin, ” BMC biology, 7(1): p. 1: (2009).
- J. P. Overington, B. Al-Lazikani, and A. L. Hopkins, ``How many drug targetsare there?'' Nature Rev. Drug Discovery, vol. 5, no. 12, pp. 993_996, Dec. 2006
- H. Lodish, D. Baltimore, A. Berk, S. L. Zipursky, P. Matsudaira, and J. Darnell, Molecular cell biology. Scientific American Books New York, 3; (1995).
- J. P. Overington, B. Al-Lazikani, and A. L. Hopkins, “How many drug targets are there?” Nature reviews Drug discovery, 5(12): 993–996 (2006).
- M. Hayat and A. Khan, ``MemHyb: Predicting membrane protein types byhybridizing SAAC and PSSM, '' J. Theor. Biol. , vol. 292, no. 1, pp. 93_102, Jan. 2012
- A. Garg, M. Bhasin, and G. P. Raghava, “Support vector machine-based method for subcellular localization of human proteins using amino acid compositions, their order, and simi- larity search, ” Journal of biological Chemistry, 280(15): 14 427–14 432: (2005).
- A. Bairoch and R. Apweiler, “The swiss-prot protein sequence database and its supplement trembl in 2000, ” Nucleic acids research, 28(1): 45–48 (2000).
- P. Jia, Z. Qian, K. Feng, Yu-Dong W. Lu, Y. Li, and Y. Cai, “Prediction of membrane protein types in a hybrid space, ” Journal of proteome research, 7(3), : 1131–1137 (2008).
- B. Boeckmann, A. Bairoch, R. Apweiler, M. -C. Blatter, A. Estreicher, E. Gasteiger, M. J. Martin, K. Michoud, C. O’Donovan, I. Phan et al. , “The swiss-prot protein knowl- edgebase and its supplement trembl in 2003, ” Nucleic acids research, 31(1): 365–370 : (2003).
- L. Wang, Z. Yuan, X. Chen, and Z. Zhou “The prediction of membrane protein types with npe, ” IEICE Electronics Express, 7(6): 397–402: (2010).
- K. -C. Chou and Y. -D. Cai, ``Using GO-PseAA predictor to identifymembrane proteins and their types, '' Biochem. Biophys. Res. Commun. , vol. 327, no. 3, pp. 845_847, Feb. 2005.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRSET
This work is licensed under a Creative Commons Attribution 4.0 International License.