A framework for stability‐based module detection in correlation graphs
Statistical Analysis and Data Mining: The ASA Data Science Journal · 2021-04 · 14 (2) · 129-143
DOI: 10.1002/sam.11495 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Analysis and Data Mining: The ASA Data Science Journal, online erschienen am 08.01.2021. Verfasst von Mingmei Tian und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics State University of New York at Buffalo Buffalo New York USA. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NCI NIH HHS, NIEHS NIH HHS, The National Cancer Institute.
Abstract (Originalsprache)
Graphs can be used to represent the direct and indirect relationships between variables, and elucidate complex relationships and interdependencies. Detecting structure within a graph is a challenging problem. This problem is studied over a range of fields and is sometimes termed community detection, module detection, or graph partitioning. A popular class of algorithms for module detection relies on optimizing a function of modularity to identify the structure. In practice, graphs are often learned from the data, and thus prone to uncertainty. In these settings, the uncertainty of the network structure can become exaggerated by giving unreliable estimates of the module structure. In this work, we begin to address this challenge through the use of a nonparametric bootstrap approach to assessing the stability of module detection in a graph. Estimates of stability are presented at the level of the individual node, the inferred modules, and as an overall measure of performance for module detection in a given graph. Furthermore, bootstrap stability estimates are derived for complexity parameter selection that ultimately defines a graph from data in a way that optimizes stability. This approach is utilized in connection with correlation graphs but is generalizable to other graphs that are defined through the use of dissimilarity measures. We demonstrate our approach using a broad range of simulations and on a metabolomics dataset from the Beijing Olympics Air Pollution study. These approaches are implemented using bootcluster package that is available in the R programming language.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biostatistics State University of New York at Buffalo Buffalo New York USA.
- Department of Epidemiology and Environmental Health State University of New York at Buffalo Buffalo New York USA.
- Department of Biotechnical and Clinical Laboratory Sciences State University of New York at Buffalo Buffalo New York USA.
- Department of Biostatistics and Bioinformatics Roswell Park Comprehensive Cancer Center Buffalo New York USA.
ORCID-Profile: Han Yu
Förderung
- NCI NIH HHS
- NIEHS NIH HHS
- The National Cancer Institute
- National Institute of Environmental Health Sciences
Zitieren
APA
Tian, M., Blair, R. H., Mu, L., Bonner, M., Browne, R., & Yu, H. (2021). A framework for stability‐based module detection in correlation graphs. Statistical Analysis and Data Mining: The ASA Data Science Journal, 14(2), 129-143. https://doi.org/10.1002/sam.11495
Vancouver
Tian M, Blair RH, Mu L, Bonner M, Browne R, Yu H. A framework for stability‐based module detection in correlation graphs. Statistical Analysis and Data Mining: The ASA Data Science Journal. 2021;14(2):129-143. doi:10.1002/sam.11495
BibTeX
@article{Tian2021,
author = {Tian, Mingmei and Blair, Rachael Hageman and Mu, Lina and Bonner, Matthew and Browne, Richard and Yu, Han},
title = {A framework for stability‐based module detection in correlation graphs},
journal = {Statistical Analysis and Data Mining: The ASA Data Science Journal},
year = {2021},
volume = {14},
number = {2},
pages = {129--143},
doi = {10.1002/sam.11495}
}
EUVIMED