Accurate Classification of Membrane Protein Types Based on Sequence and Evolutionary Information Using Deep Learning

Overview

Journal BMC Bioinformatics

Publisher Biomed Central

Specialty Biology

Date 2019 Dec 26

PMID 31874615

Citations 12

Authors

Lei Guo

Shunfang Wang

Mingyuan Li

Zicheng Cao

Affiliations

Soon will be listed here.

Abstract

Background: Membrane proteins play an important role in the life activities of organisms. Knowing membrane protein types provides clues for understanding the structure and function of proteins. Though various computational methods for predicting membrane protein types have been developed, the results still do not meet the expectations of researchers.

Results: We propose two deep learning models to process sequence information and evolutionary information, respectively. Both models obtained better results than traditional machine learning models. Furthermore, to improve the performance of the sequence information model, we also provide a new vector representation method to replace the one-hot encoding, whose overall success rate improved by 3.81% and 6.55% on two datasets. Finally, a more effective model is obtained by fusing the above two models, whose overall success rate reached 95.68% and 92.98% on two datasets.

Conclusion: The final experimental results show that our method is more effective than existing methods for predicting membrane protein types, which can help laboratory researchers to identify the type of novel membrane proteins.

Citing Articles

Protein engineering in the deep learning era.

Zhou B, Tan Y, Hu Y, Zheng L, Zhong B, Hong L mLife. 2025; 3(4):477-491.

PMID: 39744096 PMC: 11685842. DOI: 10.1002/mlf2.12157.

Hybrid framework for membrane protein type prediction based on the PSSM.

Ruan X, Xia S, Li S, Su Z, Yang J Sci Rep. 2024; 14(1):17156.

PMID: 39060345 PMC: 11282086. DOI: 10.1038/s41598-024-68163-7.

CAT-CBAM-Net: An Automatic Scoring Method for Sow Body Condition Based on CNN and Transformer.

Xue H, Sun Y, Chen J, Tian H, Liu Z, Shen M Sensors (Basel). 2023; 23(18).

PMID: 37765975 PMC: 10535612. DOI: 10.3390/s23187919.

Artificial intelligence-based HDX (AI-HDX) prediction reveals fundamental characteristics to protein dynamics: Mechanisms on SARS-CoV-2 immune escape.

Yu J, Uzuner U, Long B, Wang Z, Yuan J, Dai S iScience. 2023; 26(4):106282.

PMID: 36910327 PMC: 9968663. DOI: 10.1016/j.isci.2023.106282.

Is a Long Non-Coding RNA Necessary for CTCL Cell Growth.

Rassek K, Izykowska K, Zurawek M, Pieniawska M, Nowicka K, Zhao X Int J Mol Sci. 2023; 24(4).

PMID: 36834942 PMC: 9963807. DOI: 10.3390/ijms24043531.

References

Shen Z, Bao W, Huang D . Recurrent Neural Network for Predicting Transcription Factor Binding Sites. Sci Rep. 2018; 8(1):15270. PMC: 6189047. DOI: 10.1038/s41598-018-33321-1. View

Deng S, Huang D . SFAPS: an R package for structure/function analysis of protein sequences based on informational spectrum method. Methods. 2014; 69(3):207-12. DOI: 10.1016/j.ymeth.2014.08.004. View

Wan S, Mak M, Kung S . Mem-ADSVM: A two-layer multi-label predictor for identifying multi-functional types of membrane proteins. J Theor Biol. 2016; 398:32-42. DOI: 10.1016/j.jtbi.2016.03.013. View

Huang D, Zhang L, Han K, Deng S, Yang K, Zhang H . Prediction of protein-protein interactions based on protein-protein correlation using least squares regression. Curr Protein Pept Sci. 2014; 15(6):553-60. DOI: 10.2174/1389203715666140724084019. View

Zou Q, Xing P, Wei L, Liu B . Gene2vec: gene subsequence embedding for prediction of mammalian -methyladenosine sites from mRNA. RNA. 2018; 25(2):205-218. PMC: 6348985. DOI: 10.1261/rna.069112.118. View

You Z, Yin Z, Han K, Huang D, Zhou X . A semi-supervised learning approach to predict synthetic genetic interactions by combining functional and topological properties of functional gene network. BMC Bioinformatics. 2010; 11:343. PMC: 2909217. DOI: 10.1186/1471-2105-11-343. View

Ali F, Hayat M . Classification of membrane protein types using Voting Feature Interval in combination with Chou's Pseudo Amino Acid Composition. J Theor Biol. 2015; 384:78-83. DOI: 10.1016/j.jtbi.2015.07.034. View

Han G, Yu Z, Anh V . A two-stage SVM method to predict membrane protein types by incorporating amino acid classifications and physicochemical properties into a general form of Chou's PseAAC. J Theor Biol. 2013; 344:31-9. DOI: 10.1016/j.jtbi.2013.11.017. View

Nanni L, Lumini A . An ensemble of support vector machines for predicting the membrane protein type directly from the amino acid sequence. Amino Acids. 2008; 35(3):573-80. DOI: 10.1007/s00726-008-0083-0. View

10.

Jones D . Protein secondary structure prediction based on position-specific scoring matrices. J Mol Biol. 1999; 292(2):195-202. DOI: 10.1006/jmbi.1999.3091. View

11.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

12.

Sankari E, Manimegalai D . Predicting membrane protein types using various decision tree classifiers based on various modes of general PseAAC for imbalanced datasets. J Theor Biol. 2017; 435:208-217. DOI: 10.1016/j.jtbi.2017.09.018. View

13.

Anishetty S, Pennathur G, Anishetty R . Tripeptide analysis of protein structures. BMC Struct Biol. 2002; 2:9. PMC: 140318. DOI: 10.1186/1472-6807-2-9. View

14.

Xia J, Zhao X, Huang D . Predicting protein-protein interactions from protein sequences using meta predictor. Amino Acids. 2010; 39(5):1595-9. DOI: 10.1007/s00726-010-0588-1. View

15.

Wang S, Yue Y . Protein subnuclear localization based on a new effective representation and intelligent kernel linear discriminant analysis by dichotomous greedy genetic algorithm. PLoS One. 2018; 13(4):e0195636. PMC: 5896989. DOI: 10.1371/journal.pone.0195636. View

16.

Luo F, Wang M, Liu Y, Zhao X, Li A . DeepPhos: prediction of protein phosphorylation sites with deep learning. Bioinformatics. 2019; 35(16):2766-2773. PMC: 6691328. DOI: 10.1093/bioinformatics/bty1051. View

17.

Wan S, Mak M, Kung S . Benchmark data for identifying multi-functional types of membrane proteins. Data Brief. 2016; 8:105-7. PMC: 4889873. DOI: 10.1016/j.dib.2016.05.024. View

18.

Sun S, Wu Q, Peng Z, Yang J . Enhanced prediction of RNA solvent accessibility with long short-term memory neural networks and improved sequence profiles. Bioinformatics. 2018; 35(10):1686-1691. DOI: 10.1093/bioinformatics/bty876. View

19.

Xia J, Han K, Huang D . Sequence-based prediction of protein-protein interactions by means of rotation forest and autocorrelation descriptor. Protein Pept Lett. 2010; 17(1):137-45. DOI: 10.2174/092986610789909403. View

20.

Hayat M, Khan A . Predicting membrane protein types by fusing composite protein sequence features into pseudo amino acid composition. J Theor Biol. 2010; 271(1):10-7. DOI: 10.1016/j.jtbi.2010.11.017. View