Advertisement

Molecular Biology Reports

, Volume 46, Issue 2, pp 2259–2272 | Cite as

Employing a novel 2-gram subgroup intra pattern (2GSIP) with stacked auto encoder for membrane protein classification

  • K. JayapriyaEmail author
  • N. Ani Brown Mary
Original Article
  • 26 Downloads

Abstract

Cell membrane proteins play an essentially significant function in manipulating the behaviour of cells. Examination of amino acid sequences can put forward useful insights into the tertiary structures of proteins and their biological functions. One of the important problems in amino acid analysis is the uncertainty to establish a digital coding system to better reflect the properties of amino acids and their degeneracy. In order to overcome the demerits, the proposed method is a novel representation of protein sequences that incorporates a new feature named 2-gram subgroup intra pattern. The functional types of membrane protein classification will be supportive to explain the biological functions of membrane proteins. For classification, Stacked Auto Encoder Deep learning method is applied. The performance of the proposed method is evaluated on two benchmark data sets. The results were experimented using the Self-consistency test, Accuracy, Specificity, Sensitivity, Mathew’s correlation coefficient, Jackknife test and Independent data set are the tests in which the proposed method outperformed other existing techniques generally used in literatures.

Keywords

Membrane protein Classification Deep learning Stacked auto encoder 

Notes

References

  1. 1.
    Chou K-C, Elrod DW (1999) Prediction of membrane protein types and sub cellular locations. PROTEINS Struct Funct Genet 34:137–153CrossRefGoogle Scholar
  2. 2.
    Wan S, Maka M-W, Kungb S-Y (2016) Mem-ADSVM: a two-layer multi-label predictor for identifying multi-functional types of membrane proteins. J Theor Biol.  https://doi.org/10.1016/j.jtbi.2016.03.013 Google Scholar
  3. 3.
    Chou K-C, Shen H-B (2007) MemType-2L: a web server for predicting membrane proteins and their types by incorporating evolution information through Pse-PSSM”. Elsevier Biochem Biophys Res Commun 360:339–345CrossRefGoogle Scholar
  4. 4.
    Wan S, Mak M-W, Kung S-Y (2015) Mem-mEN: predicting multi-functional types of membrane proteins by interpretable elastic nets. IEEE/ACM Trans Comput Biol Inform 13:706–718Google Scholar
  5. 5.
    Ani Brown Mary N, Dharma D, 2018, Coral reef image/video classification employing novel octa-angled pattern for triangular sub region and pulse coupled convolutional neural network (PCCNN). Multimed Tools Appl.  https://doi.org/10.1007/s11042-018-6148-5, pp 1–35. Print-ISSN: 13807501, E-ISSN: 14321882
  6. 6.
    Wang Y-B, You Z-H, Li X, Jiang T-H, Chen X, Zhoua X, Wanga L, 2017, ‘Predicting protein–protein interactions from protein sequences by a stacked sparse autoencoder deep neural network’ 13:1336–1344Google Scholar
  7. 7.
    Chou K-C (2001) Prediction of protein cellular attributes using pseudo-amino acid composition. PROTEINS: Struct Funct Genet 44:60CrossRefGoogle Scholar
  8. 8.
    Chou K-C, Cai Y-D (2005) Prediction of membrane protein types by incorporating amphipathic effects. J Chem Inf Model Vol 45:407–413CrossRefGoogle Scholar
  9. 9.
    Golmohammadi SK, Kurgan L, Crowley B, Reformat M (2008) Amino acid sequence based method for prediction of cell membrane protein types. Int J Hybrid Inf Technol 1:1Google Scholar
  10. 10.
    Hayat M, Khan A (2012) Mem-PHybrid: hybrid features-based prediction system for classifying membrane protein types. Anal Biochem 424:35–44CrossRefGoogle Scholar
  11. 11.
    Liu H, Yang J, Wang M, Xue L, Chou K-C (2005) Using Fourier spectrum analysis and pseudo amino acid composition for prediction of membrane protein types. Protein J 24(6):385–389.  https://doi.org/10.1007/s10930-005-7592-4 CrossRefGoogle Scholar
  12. 12.
    Xiao X, Zou H-L, Lin W-Z (2015) iMem-Seq: a multi-label learning classifier for predicting membrane proteins types. J Membr Biol.  https://doi.org/10.1007/s00232-015-9787-8 Google Scholar
  13. 13.
    Zaki N, El-Hajj W (2010) Predicting membrane protein type using inter-domain linker knowledge. In: BIOCOMP, pp 209–214Google Scholar
  14. 14.
    Mahdavi A, Jahandideh S (2011) Application of density similarities to predict membrane protein types based on pseudo-amino acid composition. J Theor Biol 276:132–137CrossRefGoogle Scholar
  15. 15.
    Golmohammadi SK, Kurgan L, Crowley B, Reformat M (2007) Classification of cell membrane proteins. Front Converg Biosci Inf TechnolGoogle Scholar
  16. 16.
    Wan S, Mak M-W, Kung S-Y (2016) Benchmark data for identifying multi-functional types of membrane proteins. Data Brief 8:105–107CrossRefGoogle Scholar
  17. 17.
    Wang M, Yang J, Liu G-P, Xu Z-J, Chou K-C (2004) Weighted-support vector machines for predicting membrane protein types based on pseudo-amino acid composition. Protein Eng Des Sel 17(6):509–516CrossRefGoogle Scholar
  18. 18.
    Xiao X, Chou K-C (2007) Digital coding of amino acids based on hydrophobic index. Protein Pept Lett 14:871–875CrossRefGoogle Scholar
  19. 19.
    Liu H, Wang M, Chou K-C (2005) Low-frequency Fourier spectrum for predicting membrane protein types. Biochem Biophys Res Commun 336:737–739CrossRefGoogle Scholar
  20. 20.
    Cai Y-D, Zhou G-P, Chou K-C (2003) Support vector machines for predicting membrane protein types by using functional domain composition. Biophys J 84:257–3263CrossRefGoogle Scholar
  21. 21.
    Chou PY (1989) “Prediction of protein structural classes from amino acid composition. In: Fasman GD (ed) Prediction of protein structure and the principles of protein conformation. New York: Plenum Press, pp 549–586CrossRefGoogle Scholar
  22. 22.
    Siva Sankariand E, Manimegalai D (2017) Predicting membrane protein types using various decision tree classifiers based on various modes of general PseAAC for imbalanced datasets. J Theor Biol 435:208–217CrossRefGoogle Scholar
  23. 23.
    Nanni L, Lumini A (2008) An ensemble of support vector machines for predictingthe membrane protein type directly from the amino acid sequence. Amino Acids 35:573–580CrossRefGoogle Scholar
  24. 24.
    Shen H, Chou K-C (2005) Using optimized evidence-theoretic K-nearest neighbor classifier and pseudo-amino acid composition to predict membraneprotein types. Biochem Biophys Res Commun 334:288–292CrossRefGoogle Scholar
  25. 25.
    Huang C, Yuan J-Q (2013) A multilabel model based on Chou’s pseudo–amino acid composition for identifying membrane proteins with both single and multiple functional types. J Membr Biol 246:327–334.  https://doi.org/10.1007/s00232-013-9536-9 CrossRefGoogle Scholar
  26. 26.
    Shenand H-B, Chou K-C (2007) Using ensemble classifier to identify membrane protein types. Amino Acids 32:483–488CrossRefGoogle Scholar
  27. 27.
    Cai Y-D, Ricardo P-W, Jen C-H, Kuo-Chen, Cho (2004) Application of SVM to predict membrane protein types. J Theor Biol 226:373–376CrossRefGoogle Scholar
  28. 28.
    Nanni L, Lumini A (2006) MppS: an ensemble of support vector machine based on multiple physico chemical properties of amino acids. Neuro Comput 69:1688–1690Google Scholar
  29. 29.
    Han G-S, Yu Z-G, Anh V (2014) A two-stage SVM method to predict membrane protein types by incorporating amino acid classifications and physico chemical properties into a general form of Chou’s PseAAC. J Theor Biol 344:31–39CrossRefGoogle Scholar
  30. 30.
    Cedano J, Aloy P, Perez-Pons JA, Querol E (1997) Relation between amino acid composition and cellular location of proteins. J Mol Biol 266:594–600CrossRefGoogle Scholar
  31. 31.
    Shen H-B, Yang J, Chou K-C (2006) Fuzzy KNN for predicting membrane protein types from pseudo-amino acid composition. J Theor Biol 240:9–13CrossRefGoogle Scholar
  32. 32.
    Nanni L, Lumini A (2006) An ensemble of K-local hyperplanes for predicting protein–protein interactions. Bioinform Discov Note 22(10):1207–1210.  https://doi.org/10.1093/bioinformatics/btl055 CrossRefGoogle Scholar
  33. 33.
    Xiao X, Shao S, Ding Y, Huang Z, Chou K-C (2006) Using cellular automata images and pseudo amino acid composition to predict protein sub cellular location. Springer Amino Acids 30:49–54.  https://doi.org/10.1007/s00726-005-0225-6 CrossRefGoogle Scholar
  34. 34.
    Baek K (2015) Learning deep architectures for protein structure prediction. In: Proceedings of the 7th international conference on bioinformatics and computational biology, BICOBGoogle Scholar
  35. 35.
    Basu S, Karki M, DiBiano R, Mukhopadhyay S, Ganguly S, Nemani R, Gayaka S (2016) A theoretical analysis of deep neural networks for texture classification. In: International joint conference on neural networks, IJCNNGoogle Scholar
  36. 36.
    Andrearczyk V, Whelan PF (2017) Deep learning for biomedical texture image analysis. In: Irish machine vision and image processing conferenceGoogle Scholar
  37. 37.
    Da C, Zhang H, Sang Y (2015) Brain CT image classification with deep neural networks. In: Proceedings of the 18th Asia Pacific symposium on intelligent and evolutionary systems. 1:653–662.  https://doi.org/10.1007/978-3-319-13359-1_50
  38. 38.
    Jo T, Hou J, Eickholt J, Cheng J (2015) Improving protein fold recognition by deep learning networks. Sci Rep 5, Article number: 1757Google Scholar
  39. 39.
    Wang S, Peng J, Ma J, Xu J (2016) Protein secondary structure prediction using deep convolutional neural fields. Sci Rep 6, Article number: 18962Google Scholar
  40. 40.
    Bai L, Yang L, (2017) A unified deep learning model for protein structure prediction. In: 3rd IEEE international conference on cybernetics (CYBCONF).  https://doi.org/10.1109/CYBConf.2017.7985752
  41. 41.
    Chou K-C, Shen H-B (2007) Recent progress in protein subcellular location prediction. Anal Biochem 370:1–16CrossRefGoogle Scholar
  42. 42.
    Liu Z, Zhang W, Lin S, Quek TQS (2017) Heterogeneous sensor data fusion by deep multimodal encoding. IEEE J Sel Top Signal Process.  https://doi.org/10.1109/JSTSP.2017.2679538 Google Scholar
  43. 43.
    Liu G, Bao H, Han B (2018) A stacked autoencoder-based deep neural network for achieving gearbox fault diagnosis’, Hindawi. Math Probl Eng.  https://doi.org/10.1155/2018/5105709 Google Scholar
  44. 44.
    Li X, Peng L, Hu Y, Shao J, Chi T (2016) Deep learning architecture for air quality predictions. Environ Sci Pollut Res.  https://doi.org/10.1007/s11356-016-7812-9 Google Scholar
  45. 45.
    Xiao X, Shao S, Ding Y, Huang Z, Huang Y, Chou K-C (2005) “Using complexity measure factor to predict protein sub cellular location”. Amino Acids 2:57–61.  https://doi.org/10.1007/s00726-004-0148-7 CrossRefGoogle Scholar
  46. 46.
    Gao Q-B, Ye X-F, Jin Z-C, He J (2010) Improving discrimination of outer membrane proteins by fusing different forms of pseudo amino acid composition. Anal Biochem 398:52–59CrossRefGoogle Scholar
  47. 47.
    Le N-Q-K, Ho Q-T, Ou Y-Y (2018) Classifying the molecular functions of Rab GTPases in membrane trafficking using deep convolutional neural networks. Anal Biochem 555:33–41CrossRefGoogle Scholar
  48. 48.
    Ju Z, Jun-Zhe C (2017) Prediction of protein N-formylation using the composition of k-spaced amino acid pairs. Anal Biochem.  https://doi.org/10.1016/j.ab.2017.07.011 Google Scholar
  49. 49.
    López Y, Dehzangi A, Lal SP, Taherzadeh G, Michaelson J, Sattar A, Tsunoda T, Sharma A (2017) SucStruct: prediction of succinylated lysine residues by using structural properties of amino acids. Anal Biochem.  https://doi.org/10.1016/j.ab.2017.03.021 Google Scholar
  50. 50.
    Nakashima H, Nishikawa K, Ooi T (1986) The folding type of a protein is relevant to the amino acid composition. J Biochem 99:152–162CrossRefGoogle Scholar
  51. 51.
    Chen Y-K, Li K-B (2013) Predicting membrane protein types by incorporating protein topology, domains, signal peptides, and physic chemical properties into the general form of Chou’s pseudo amino acid composition. J Theor Biol 318:1–12CrossRefGoogle Scholar
  52. 52.
    Chou KC (2001) Prediction of protein cellular attributes using pseudo amino acid composition. PROTEINS: Struct Funct Genet (Erratum: ibid., 2001, Vol. 44, 60), 43:246–255Google Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  1. 1.Vin SolutionsTirunelveliIndia
  2. 2.Anna UniversityTirunelveliIndia

Personalised recommendations