Classifying protein complexes from candidate subgraphs using fuzzy machine learning model

Bo Xu, Hongfei Lin, Zhihao Yang, Kavishwar B. Wagholikar, Hongfang D Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Many computational methods have been applied to identify protein complexes from experimentally obtained protein-protein interaction (PPI) networks. Because of the presence of unreliable interactions in PPI networks, multi-functionality of proteins, and complex connectivity of the PPI network, the task is very challenging. In this study, we tackle the presence of unreliable interactions in protein complex using Genetic-Algorithm Fuzzy Naïve Bayes (GAFNB) which takes unreliability into consideration. Many existing methods can provide lots of candidate subgraphs. So we focused on how to classify the protein complexes from the subgraphs by considering the fuzzy attribute of PPI. We experimented with two datasets of size 10,371 and 986, each containing 493 positive protein complexes from MIPS and TAP-MS datasets. We compared the performance of GAFNB with Naïve Bayes (NB). Results show that GAFNB performed better which indicates that a fuzzy model is more suitable when unreliability is present. It is necessary to consider the unreliability in identifying protein complexes.

Original languageEnglish (US)
Title of host publicationProceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012
Pages640-647
Number of pages8
DOIs
StatePublished - 2012
Event2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012 - Philadelphia, PA, United States
Duration: Oct 4 2012Oct 7 2012

Other

Other2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012
CountryUnited States
CityPhiladelphia, PA
Period10/4/1210/7/12

Fingerprint

Learning systems
Proteins
Protein Interaction Maps
Genetic algorithms
Machine Learning
Computational methods

Keywords

  • Machine Learning
  • Naïve Bayes
  • Protein complexes

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Cite this

Xu, B., Lin, H., Yang, Z., Wagholikar, K. B., & Liu, H. D. (2012). Classifying protein complexes from candidate subgraphs using fuzzy machine learning model. In Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012 (pp. 640-647). [6470213] https://doi.org/10.1109/BIBMW.2012.6470213

Classifying protein complexes from candidate subgraphs using fuzzy machine learning model. / Xu, Bo; Lin, Hongfei; Yang, Zhihao; Wagholikar, Kavishwar B.; Liu, Hongfang D.

Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012. 2012. p. 640-647 6470213.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xu, B, Lin, H, Yang, Z, Wagholikar, KB & Liu, HD 2012, Classifying protein complexes from candidate subgraphs using fuzzy machine learning model. in Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012., 6470213, pp. 640-647, 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012, Philadelphia, PA, United States, 10/4/12. https://doi.org/10.1109/BIBMW.2012.6470213
Xu B, Lin H, Yang Z, Wagholikar KB, Liu HD. Classifying protein complexes from candidate subgraphs using fuzzy machine learning model. In Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012. 2012. p. 640-647. 6470213 https://doi.org/10.1109/BIBMW.2012.6470213
Xu, Bo ; Lin, Hongfei ; Yang, Zhihao ; Wagholikar, Kavishwar B. ; Liu, Hongfang D. / Classifying protein complexes from candidate subgraphs using fuzzy machine learning model. Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012. 2012. pp. 640-647
@inproceedings{20313907c22c428dae4145696886a7ad,
title = "Classifying protein complexes from candidate subgraphs using fuzzy machine learning model",
abstract = "Many computational methods have been applied to identify protein complexes from experimentally obtained protein-protein interaction (PPI) networks. Because of the presence of unreliable interactions in PPI networks, multi-functionality of proteins, and complex connectivity of the PPI network, the task is very challenging. In this study, we tackle the presence of unreliable interactions in protein complex using Genetic-Algorithm Fuzzy Na{\"i}ve Bayes (GAFNB) which takes unreliability into consideration. Many existing methods can provide lots of candidate subgraphs. So we focused on how to classify the protein complexes from the subgraphs by considering the fuzzy attribute of PPI. We experimented with two datasets of size 10,371 and 986, each containing 493 positive protein complexes from MIPS and TAP-MS datasets. We compared the performance of GAFNB with Na{\"i}ve Bayes (NB). Results show that GAFNB performed better which indicates that a fuzzy model is more suitable when unreliability is present. It is necessary to consider the unreliability in identifying protein complexes.",
keywords = "Machine Learning, Na{\"i}ve Bayes, Protein complexes",
author = "Bo Xu and Hongfei Lin and Zhihao Yang and Wagholikar, {Kavishwar B.} and Liu, {Hongfang D}",
year = "2012",
doi = "10.1109/BIBMW.2012.6470213",
language = "English (US)",
isbn = "9781467327466",
pages = "640--647",
booktitle = "Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012",

}

TY - GEN

T1 - Classifying protein complexes from candidate subgraphs using fuzzy machine learning model

AU - Xu, Bo

AU - Lin, Hongfei

AU - Yang, Zhihao

AU - Wagholikar, Kavishwar B.

AU - Liu, Hongfang D

PY - 2012

Y1 - 2012

N2 - Many computational methods have been applied to identify protein complexes from experimentally obtained protein-protein interaction (PPI) networks. Because of the presence of unreliable interactions in PPI networks, multi-functionality of proteins, and complex connectivity of the PPI network, the task is very challenging. In this study, we tackle the presence of unreliable interactions in protein complex using Genetic-Algorithm Fuzzy Naïve Bayes (GAFNB) which takes unreliability into consideration. Many existing methods can provide lots of candidate subgraphs. So we focused on how to classify the protein complexes from the subgraphs by considering the fuzzy attribute of PPI. We experimented with two datasets of size 10,371 and 986, each containing 493 positive protein complexes from MIPS and TAP-MS datasets. We compared the performance of GAFNB with Naïve Bayes (NB). Results show that GAFNB performed better which indicates that a fuzzy model is more suitable when unreliability is present. It is necessary to consider the unreliability in identifying protein complexes.

AB - Many computational methods have been applied to identify protein complexes from experimentally obtained protein-protein interaction (PPI) networks. Because of the presence of unreliable interactions in PPI networks, multi-functionality of proteins, and complex connectivity of the PPI network, the task is very challenging. In this study, we tackle the presence of unreliable interactions in protein complex using Genetic-Algorithm Fuzzy Naïve Bayes (GAFNB) which takes unreliability into consideration. Many existing methods can provide lots of candidate subgraphs. So we focused on how to classify the protein complexes from the subgraphs by considering the fuzzy attribute of PPI. We experimented with two datasets of size 10,371 and 986, each containing 493 positive protein complexes from MIPS and TAP-MS datasets. We compared the performance of GAFNB with Naïve Bayes (NB). Results show that GAFNB performed better which indicates that a fuzzy model is more suitable when unreliability is present. It is necessary to consider the unreliability in identifying protein complexes.

KW - Machine Learning

KW - Naïve Bayes

KW - Protein complexes

UR - http://www.scopus.com/inward/record.url?scp=84875590936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875590936&partnerID=8YFLogxK

U2 - 10.1109/BIBMW.2012.6470213

DO - 10.1109/BIBMW.2012.6470213

M3 - Conference contribution

AN - SCOPUS:84875590936

SN - 9781467327466

SP - 640

EP - 647

BT - Proceedings - 2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops, BIBMW 2012

ER -