An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity

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

1 Citation (Scopus)

Abstract

Disease processes are usually driven by several genes interacting in molecular modules or pathways leading to the disease. The identification of such modules in gene or protein networks is at the core of several analysis methods in biomedical research. However, there is still a need to develop a generic framework to uncover biologically relevant modules for different types of networks. With this pretext in mind, the Disease Module Identification DREAM Challenge was initiated as an effort to systematically assess module identification methods on a panel of 6 diverse state-of-the-art genomic networks. Methods: In this paper, we propose a generic refinement method based on ideas of merging and splitting the hierarchical tree obtained from any community detection technique for constrained disease module identification in biological networks. The only constraint for a module to be considered as a candidate disease module was size of the community to be: 3 ≤ community size ≤ 100. Here, we propose a novel quality metric, called F-score, computed from several unsupervised quality metrics like modularity, conductance and connectivity to determine the quality of a graph partition at a given level of hierarchy. We also propose a quality metric, namely Inverse Confidence, which ranks and prune insignificant modules to obtain a curated list of candidate disease modules for a given biological network. The predicted modules are then evaluated on the basis of the total number of unique candidate modules that are associated with complex traits and diseases from over 200 genome-wide association study (GWAS) datasets. Results: We stood 9th out of a total of 42 teams in the competition at the offical FDR cut-off of 0.05 for identifying statistically significant disease associated modules in the 6 benchmark networks. Our proposed approach detected a total of 44 disease modules in the 6 benchmark networks in comparison to 60 for the winner of the DREAM Challenge. For several benchmark networks we were better or competitive with the winner.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2282-2284
Number of pages3
Volume2017-January
ISBN (Electronic)9781509030491
DOIs
Publication statusPublished - 15 Dec 2017
Event2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 - Kansas City, United States
Duration: 13 Nov 201716 Nov 2017

Other

Other2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017
CountryUnited States
CityKansas City
Period13/11/1716/11/17

Fingerprint

Benchmarking
Genes
Genome-Wide Association Study
Merging
Biomedical Research
Proteins

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Cite this

Mall, R., Ullah, E., Kunji, K., Bensmail, H., & Ceccarelli, M. (2017). An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity. In Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017 (Vol. 2017-January, pp. 2282-2284). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2017.8218027

An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity. / Mall, RaghvenPhDa; Ullah, Ehsan; Kunji, Khalid; Bensmail, Halima; Ceccarelli, Michele.

Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 2282-2284.

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

Mall, R, Ullah, E, Kunji, K, Bensmail, H & Ceccarelli, M 2017, An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity. in Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 2282-2284, 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017, Kansas City, United States, 13/11/17. https://doi.org/10.1109/BIBM.2017.8218027
Mall R, Ullah E, Kunji K, Bensmail H, Ceccarelli M. An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity. In Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2282-2284 https://doi.org/10.1109/BIBM.2017.8218027
Mall, RaghvenPhDa ; Ullah, Ehsan ; Kunji, Khalid ; Bensmail, Halima ; Ceccarelli, Michele. / An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity. Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2282-2284
@inproceedings{87bb8b637b064f2b8de558e0e1dc3ea8,
title = "An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity",
abstract = "Disease processes are usually driven by several genes interacting in molecular modules or pathways leading to the disease. The identification of such modules in gene or protein networks is at the core of several analysis methods in biomedical research. However, there is still a need to develop a generic framework to uncover biologically relevant modules for different types of networks. With this pretext in mind, the Disease Module Identification DREAM Challenge was initiated as an effort to systematically assess module identification methods on a panel of 6 diverse state-of-the-art genomic networks. Methods: In this paper, we propose a generic refinement method based on ideas of merging and splitting the hierarchical tree obtained from any community detection technique for constrained disease module identification in biological networks. The only constraint for a module to be considered as a candidate disease module was size of the community to be: 3 ≤ community size ≤ 100. Here, we propose a novel quality metric, called F-score, computed from several unsupervised quality metrics like modularity, conductance and connectivity to determine the quality of a graph partition at a given level of hierarchy. We also propose a quality metric, namely Inverse Confidence, which ranks and prune insignificant modules to obtain a curated list of candidate disease modules for a given biological network. The predicted modules are then evaluated on the basis of the total number of unique candidate modules that are associated with complex traits and diseases from over 200 genome-wide association study (GWAS) datasets. Results: We stood 9th out of a total of 42 teams in the competition at the offical FDR cut-off of 0.05 for identifying statistically significant disease associated modules in the 6 benchmark networks. Our proposed approach detected a total of 44 disease modules in the 6 benchmark networks in comparison to 60 for the winner of the DREAM Challenge. For several benchmark networks we were better or competitive with the winner.",
author = "RaghvenPhDa Mall and Ehsan Ullah and Khalid Kunji and Halima Bensmail and Michele Ceccarelli",
year = "2017",
month = "12",
day = "15",
doi = "10.1109/BIBM.2017.8218027",
language = "English",
volume = "2017-January",
pages = "2282--2284",
booktitle = "Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - An adaptive refinement for community detection methods for disease module identification in biological networks using novel metric based on connectivity, conductance & modularity

AU - Mall, RaghvenPhDa

AU - Ullah, Ehsan

AU - Kunji, Khalid

AU - Bensmail, Halima

AU - Ceccarelli, Michele

PY - 2017/12/15

Y1 - 2017/12/15

N2 - Disease processes are usually driven by several genes interacting in molecular modules or pathways leading to the disease. The identification of such modules in gene or protein networks is at the core of several analysis methods in biomedical research. However, there is still a need to develop a generic framework to uncover biologically relevant modules for different types of networks. With this pretext in mind, the Disease Module Identification DREAM Challenge was initiated as an effort to systematically assess module identification methods on a panel of 6 diverse state-of-the-art genomic networks. Methods: In this paper, we propose a generic refinement method based on ideas of merging and splitting the hierarchical tree obtained from any community detection technique for constrained disease module identification in biological networks. The only constraint for a module to be considered as a candidate disease module was size of the community to be: 3 ≤ community size ≤ 100. Here, we propose a novel quality metric, called F-score, computed from several unsupervised quality metrics like modularity, conductance and connectivity to determine the quality of a graph partition at a given level of hierarchy. We also propose a quality metric, namely Inverse Confidence, which ranks and prune insignificant modules to obtain a curated list of candidate disease modules for a given biological network. The predicted modules are then evaluated on the basis of the total number of unique candidate modules that are associated with complex traits and diseases from over 200 genome-wide association study (GWAS) datasets. Results: We stood 9th out of a total of 42 teams in the competition at the offical FDR cut-off of 0.05 for identifying statistically significant disease associated modules in the 6 benchmark networks. Our proposed approach detected a total of 44 disease modules in the 6 benchmark networks in comparison to 60 for the winner of the DREAM Challenge. For several benchmark networks we were better or competitive with the winner.

AB - Disease processes are usually driven by several genes interacting in molecular modules or pathways leading to the disease. The identification of such modules in gene or protein networks is at the core of several analysis methods in biomedical research. However, there is still a need to develop a generic framework to uncover biologically relevant modules for different types of networks. With this pretext in mind, the Disease Module Identification DREAM Challenge was initiated as an effort to systematically assess module identification methods on a panel of 6 diverse state-of-the-art genomic networks. Methods: In this paper, we propose a generic refinement method based on ideas of merging and splitting the hierarchical tree obtained from any community detection technique for constrained disease module identification in biological networks. The only constraint for a module to be considered as a candidate disease module was size of the community to be: 3 ≤ community size ≤ 100. Here, we propose a novel quality metric, called F-score, computed from several unsupervised quality metrics like modularity, conductance and connectivity to determine the quality of a graph partition at a given level of hierarchy. We also propose a quality metric, namely Inverse Confidence, which ranks and prune insignificant modules to obtain a curated list of candidate disease modules for a given biological network. The predicted modules are then evaluated on the basis of the total number of unique candidate modules that are associated with complex traits and diseases from over 200 genome-wide association study (GWAS) datasets. Results: We stood 9th out of a total of 42 teams in the competition at the offical FDR cut-off of 0.05 for identifying statistically significant disease associated modules in the 6 benchmark networks. Our proposed approach detected a total of 44 disease modules in the 6 benchmark networks in comparison to 60 for the winner of the DREAM Challenge. For several benchmark networks we were better or competitive with the winner.

UR - http://www.scopus.com/inward/record.url?scp=85045962593&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045962593&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2017.8218027

DO - 10.1109/BIBM.2017.8218027

M3 - Conference contribution

VL - 2017-January

SP - 2282

EP - 2284

BT - Proceedings - 2017 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -