Detecting protein complexes from noisy protein interaction data

Dmitry Efimov; Nazar Zaki; Jose Berengueres

doi:10.1145/2350176.2350177

Detecting protein complexes from noisy protein interaction data

Dmitry Efimov, Nazar Zaki, Jose Berengueres

Department of Computer Science and Software Engineering

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

4 Citations (Scopus)

Abstract

High-throughput experimental techniques have made available large datasets of experimentally detected protein-protein interactions. However, experimentally determined protein complexes datasets are not exhaustive nor reliable. A protein complex plays a key role in disease development. Therefore, the identification and characterization of protein complexes involved is crucial to the understanding of the molecular events under normal and abnormal physiological conditions. In this paper, we propose a novel graph mining algorithm to identify protein complexes. The algorithm first checks the quality of the interaction data, then predicts protein complexes based on the concept of weighted clustering coefficient. To demonstrate the effectiveness of our proposed method, we present experimental results on yeast protein interaction data. The level of accuracy achieved is a strong argument in favor of the proposed method. Novel protein complexes were also predicted to assist biologists in their search for protein complexes. The datasets and programs are freely available from http://faculty.uaeu.ac.ae/nzaki/PE-WCC. htm.

Original language	English
Title of host publication	Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12
Pages	1-7
Number of pages	7
DOIs	https://doi.org/10.1145/2350176.2350177
Publication status	Published - 2012
Event	11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12 - Beijing, China Duration: Aug 12 2012 → Aug 12 2012

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Other

Other	11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12
Country/Territory	China
City	Beijing
Period	8/12/12 → 8/12/12

Keywords

Clustering coefficient
Detecting protein complexes
Interaction reliability
Protein complex
Protein-protein interaction network

ASJC Scopus subject areas

Software
Information Systems

Access to Document

10.1145/2350176.2350177

Cite this

Efimov, D., Zaki, N., & Berengueres, J. (2012). Detecting protein complexes from noisy protein interaction data. In Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12 (pp. 1-7). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). https://doi.org/10.1145/2350176.2350177

Detecting protein complexes from noisy protein interaction data. / Efimov, Dmitry; Zaki, Nazar ; Berengueres, Jose.
Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. 2012. p. 1-7 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

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

Efimov, D, Zaki, N & Berengueres, J 2012, Detecting protein complexes from noisy protein interaction data. in Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1-7, 11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12, Beijing, China, 8/12/12. https://doi.org/10.1145/2350176.2350177

Efimov D, Zaki N , Berengueres J. Detecting protein complexes from noisy protein interaction data. In Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. 2012. p. 1-7. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/2350176.2350177

Efimov, Dmitry ; Zaki, Nazar ; Berengueres, Jose. / Detecting protein complexes from noisy protein interaction data. Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12. 2012. pp. 1-7 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{98bdc5b0d679410080874d53860f5ccb,

title = "Detecting protein complexes from noisy protein interaction data",

abstract = "High-throughput experimental techniques have made available large datasets of experimentally detected protein-protein interactions. However, experimentally determined protein complexes datasets are not exhaustive nor reliable. A protein complex plays a key role in disease development. Therefore, the identification and characterization of protein complexes involved is crucial to the understanding of the molecular events under normal and abnormal physiological conditions. In this paper, we propose a novel graph mining algorithm to identify protein complexes. The algorithm first checks the quality of the interaction data, then predicts protein complexes based on the concept of weighted clustering coefficient. To demonstrate the effectiveness of our proposed method, we present experimental results on yeast protein interaction data. The level of accuracy achieved is a strong argument in favor of the proposed method. Novel protein complexes were also predicted to assist biologists in their search for protein complexes. The datasets and programs are freely available from http://faculty.uaeu.ac.ae/nzaki/PE-WCC. htm.",

keywords = "Clustering coefficient, Detecting protein complexes, Interaction reliability, Protein complex, Protein-protein interaction network",

author = "Dmitry Efimov and Nazar Zaki and Jose Berengueres",

year = "2012",

doi = "10.1145/2350176.2350177",

language = "English",

isbn = "9781450315524",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

pages = "1--7",

booktitle = "Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12",

note = "11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12 ; Conference date: 12-08-2012 Through 12-08-2012",

}

TY - GEN

T1 - Detecting protein complexes from noisy protein interaction data

AU - Efimov, Dmitry

AU - Zaki, Nazar

AU - Berengueres, Jose

PY - 2012

Y1 - 2012

N2 - High-throughput experimental techniques have made available large datasets of experimentally detected protein-protein interactions. However, experimentally determined protein complexes datasets are not exhaustive nor reliable. A protein complex plays a key role in disease development. Therefore, the identification and characterization of protein complexes involved is crucial to the understanding of the molecular events under normal and abnormal physiological conditions. In this paper, we propose a novel graph mining algorithm to identify protein complexes. The algorithm first checks the quality of the interaction data, then predicts protein complexes based on the concept of weighted clustering coefficient. To demonstrate the effectiveness of our proposed method, we present experimental results on yeast protein interaction data. The level of accuracy achieved is a strong argument in favor of the proposed method. Novel protein complexes were also predicted to assist biologists in their search for protein complexes. The datasets and programs are freely available from http://faculty.uaeu.ac.ae/nzaki/PE-WCC. htm.

AB - High-throughput experimental techniques have made available large datasets of experimentally detected protein-protein interactions. However, experimentally determined protein complexes datasets are not exhaustive nor reliable. A protein complex plays a key role in disease development. Therefore, the identification and characterization of protein complexes involved is crucial to the understanding of the molecular events under normal and abnormal physiological conditions. In this paper, we propose a novel graph mining algorithm to identify protein complexes. The algorithm first checks the quality of the interaction data, then predicts protein complexes based on the concept of weighted clustering coefficient. To demonstrate the effectiveness of our proposed method, we present experimental results on yeast protein interaction data. The level of accuracy achieved is a strong argument in favor of the proposed method. Novel protein complexes were also predicted to assist biologists in their search for protein complexes. The datasets and programs are freely available from http://faculty.uaeu.ac.ae/nzaki/PE-WCC. htm.

KW - Clustering coefficient

KW - Detecting protein complexes

KW - Interaction reliability

KW - Protein complex

KW - Protein-protein interaction network

UR - http://www.scopus.com/inward/record.url?scp=84866603595&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866603595&partnerID=8YFLogxK

U2 - 10.1145/2350176.2350177

DO - 10.1145/2350176.2350177

M3 - Conference contribution

AN - SCOPUS:84866603595

SN - 9781450315524

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 1

EP - 7

BT - Proc. of the 11th Int. Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD Int. Conference on Knowledge Discovery and Data Mining, SIGKDD'12

T2 - 11th International Workshop on Data Mining in Bioinformatics, BIOKDD 2012 - Held in Conjunction with the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, SIGKDD'12

Y2 - 12 August 2012 through 12 August 2012

ER -

Detecting protein complexes from noisy protein interaction data

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this