Sequence based Prediction of Membrane Protein Types using Machine Learning methods

9 Pages Posted: 21 Jan 2021

See all articles by AnjnaJayant Deen

AnjnaJayant Deen

Maulana Azad National Institute of Technology Bhopal

Manasi Gyanchandani

Maulana Azad National Institute of Technology, Bhopal

Date Written: January 20, 2021

Abstract

Membrane proteins perform an essential protein function, which are cell receptors, channels, and energy transducers. These functions work to keep the survival of the cell. The membrane protein is an integral part of body structure. Therefore, it is necessary to build up machine learning methods to correct identifying membrane protein types to recognize protein function for finding cell life cycle, gene interaction, cell signals, disease occurrence, drug design, and many more. Detection of a membrane protein from sequence length encoding based feature is a key task. The predictor GBDT and Ensemble Adaboost classifiers used to predict a membrane protein, with sequence length, encodes single descriptor value to encodes multilabel feature types. This proposed method has identified the types of the membrane without sequence information loss, and machine Learning classifiers handle the protein datasets well.

Keywords: Membrane Protein; GBDT; AdaBoost; RUSBoost; Random Forest; Sequence length

Suggested Citation

Deen, AnjnaJayant and Gyanchandani, Manasi, Sequence based Prediction of Membrane Protein Types using Machine Learning methods (January 20, 2021). ICICNIS 2020, Available at SSRN: https://ssrn.com/abstract=3769836 or http://dx.doi.org/10.2139/ssrn.3769836

AnjnaJayant Deen (Contact Author)

Maulana Azad National Institute of Technology Bhopal ( email )

Bhopal

Manasi Gyanchandani

Maulana Azad National Institute of Technology, Bhopal ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
10
Abstract Views
86
PlumX Metrics