Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction

Satyajit Mahapatra; Anish Kumar; Animesh Sharma; Sitanshu Sekhar Sahu

doi:10.1007/978-981-15-1081-6_1

Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction

Satyajit Mahapatra^*
, Anish Kumar
, Animesh Sharma
, Sitanshu Sekhar Sahu

^*Corresponding author for this work

School of Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

“Large Dimension” of features derived from protein sequences is a major problem in protein–protein interaction (PPI) prediction. Thus, reduction of the feature dimension may increase the classification accuracy. In this paper, particle swarm optimization (PSO) and principal component analysis (PCA) have been used for dimensionality reduction of PPI sequence features. The performance of the algorithm has been assessed using the intraspecies E coli protein–protein interaction database, containing an equal number of positive and negative interacting pairs. Standard sequence-based features such as amino acid composition (AAC), dipeptide composition (Dipep), and conjoint triad composition (CTD) are extracted. From the results, it is seen that the PSO-based dimensionality reduction method provides steady and better performance in terms of accuracy when applied to the features.

Original language	English
Title of host publication	Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018
Editors	Bibudhendu Pati, Chhabi Rani Panigrahi, Rajkumar Buyya, Kuan-Ching Li
Publisher	Springer
Pages	3-12
Number of pages	10
ISBN (Print)	9789811510809
DOIs	https://doi.org/10.1007/978-981-15-1081-6_1
Publication status	Published - 2020
Event	3rd International Conference on Advanced Computing and Intelligent Engineering, ICACIE 2018 - Bhubaneswar, India Duration: 22-12-2018 → 24-12-2018

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1082
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	3rd International Conference on Advanced Computing and Intelligent Engineering, ICACIE 2018
Country/Territory	India
City	Bhubaneswar
Period	22-12-18 → 24-12-18

All Science Journal Classification (ASJC) codes

Control and Systems Engineering
General Computer Science

Access to Document

10.1007/978-981-15-1081-6_1

Cite this

Mahapatra, S., Kumar, A., Sharma, A., & Sahu, S. S. (2020). Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction. In B. Pati, C. R. Panigrahi, R. Buyya, & K.-C. Li (Eds.), Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018 (pp. 3-12). (Advances in Intelligent Systems and Computing; Vol. 1082). Springer. https://doi.org/10.1007/978-981-15-1081-6_1

Mahapatra, Satyajit ; Kumar, Anish ; Sharma, Animesh et al. / Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction. Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018. editor / Bibudhendu Pati ; Chhabi Rani Panigrahi ; Rajkumar Buyya ; Kuan-Ching Li. Springer, 2020. pp. 3-12 (Advances in Intelligent Systems and Computing).

@inproceedings{a878e82a66b54b7383bc1d977c859ba5,

title = "Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction",

abstract = "“Large Dimension” of features derived from protein sequences is a major problem in protein–protein interaction (PPI) prediction. Thus, reduction of the feature dimension may increase the classification accuracy. In this paper, particle swarm optimization (PSO) and principal component analysis (PCA) have been used for dimensionality reduction of PPI sequence features. The performance of the algorithm has been assessed using the intraspecies E coli protein–protein interaction database, containing an equal number of positive and negative interacting pairs. Standard sequence-based features such as amino acid composition (AAC), dipeptide composition (Dipep), and conjoint triad composition (CTD) are extracted. From the results, it is seen that the PSO-based dimensionality reduction method provides steady and better performance in terms of accuracy when applied to the features.",

author = "Satyajit Mahapatra and Anish Kumar and Animesh Sharma and Sahu, \{Sitanshu Sekhar\}",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; 3rd International Conference on Advanced Computing and Intelligent Engineering, ICACIE 2018 ; Conference date: 22-12-2018 Through 24-12-2018",

year = "2020",

doi = "10.1007/978-981-15-1081-6\_1",

language = "English",

isbn = "9789811510809",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "3--12",

editor = "Bibudhendu Pati and Panigrahi, \{Chhabi Rani\} and Rajkumar Buyya and Kuan-Ching Li",

booktitle = "Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018",

address = "Germany",

}

Mahapatra, S, Kumar, A, Sharma, A & Sahu, SS 2020, Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction. in B Pati, CR Panigrahi, R Buyya & K-C Li (eds), Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018. Advances in Intelligent Systems and Computing, vol. 1082, Springer, pp. 3-12, 3rd International Conference on Advanced Computing and Intelligent Engineering, ICACIE 2018, Bhubaneswar, India, 22-12-18. https://doi.org/10.1007/978-981-15-1081-6_1

Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction. / Mahapatra, Satyajit; Kumar, Anish; Sharma, Animesh et al.
Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018. ed. / Bibudhendu Pati; Chhabi Rani Panigrahi; Rajkumar Buyya; Kuan-Ching Li. Springer, 2020. p. 3-12 (Advances in Intelligent Systems and Computing; Vol. 1082).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction

AU - Mahapatra, Satyajit

AU - Kumar, Anish

AU - Sharma, Animesh

AU - Sahu, Sitanshu Sekhar

PY - 2020

Y1 - 2020

N2 - “Large Dimension” of features derived from protein sequences is a major problem in protein–protein interaction (PPI) prediction. Thus, reduction of the feature dimension may increase the classification accuracy. In this paper, particle swarm optimization (PSO) and principal component analysis (PCA) have been used for dimensionality reduction of PPI sequence features. The performance of the algorithm has been assessed using the intraspecies E coli protein–protein interaction database, containing an equal number of positive and negative interacting pairs. Standard sequence-based features such as amino acid composition (AAC), dipeptide composition (Dipep), and conjoint triad composition (CTD) are extracted. From the results, it is seen that the PSO-based dimensionality reduction method provides steady and better performance in terms of accuracy when applied to the features.

AB - “Large Dimension” of features derived from protein sequences is a major problem in protein–protein interaction (PPI) prediction. Thus, reduction of the feature dimension may increase the classification accuracy. In this paper, particle swarm optimization (PSO) and principal component analysis (PCA) have been used for dimensionality reduction of PPI sequence features. The performance of the algorithm has been assessed using the intraspecies E coli protein–protein interaction database, containing an equal number of positive and negative interacting pairs. Standard sequence-based features such as amino acid composition (AAC), dipeptide composition (Dipep), and conjoint triad composition (CTD) are extracted. From the results, it is seen that the PSO-based dimensionality reduction method provides steady and better performance in terms of accuracy when applied to the features.

UR - https://www.scopus.com/pages/publications/85081167275

UR - https://www.scopus.com/pages/publications/85081167275#tab=citedBy

U2 - 10.1007/978-981-15-1081-6_1

DO - 10.1007/978-981-15-1081-6_1

M3 - Conference contribution

AN - SCOPUS:85081167275

SN - 9789811510809

T3 - Advances in Intelligent Systems and Computing

SP - 3

EP - 12

BT - Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018

A2 - Pati, Bibudhendu

A2 - Panigrahi, Chhabi Rani

A2 - Buyya, Rajkumar

A2 - Li, Kuan-Ching

PB - Springer

T2 - 3rd International Conference on Advanced Computing and Intelligent Engineering, ICACIE 2018

Y2 - 22 December 2018 through 24 December 2018

ER -

Mahapatra S, Kumar A, Sharma A, Sahu SS. Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction. In Pati B, Panigrahi CR, Buyya R, Li KC, editors, Advanced Computing and Intelligent Engineering - Proceedings of ICACIE 2018. Springer. 2020. p. 3-12. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-981-15-1081-6_1

Effect of Dimensionality Reduction on Classification Accuracy for Protein–Protein Interaction Prediction

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this