Stability-based validation of clustering solutions - PubMed (original) (raw)
Comparative Study
. 2004 Jun;16(6):1299-323.
doi: 10.1162/089976604773717621.
Affiliations
- PMID: 15130251
- DOI: 10.1162/089976604773717621
Comparative Study
Stability-based validation of clustering solutions
Tilman Lange et al. Neural Comput. 2004 Jun.
Abstract
Data clustering describes a set of frequently employed techniques in exploratory data analysis to extract "natural" group structure in data. Such groupings need to be validated to separate the signal in the data from spurious structure. In this context, finding an appropriate number of clusters is a particularly important model selection question. We introduce a measure of cluster stability to assess the validity of a cluster model. This stability measure quantifies the reproducibility of clustering solutions on a second sample, and it can be interpreted as a classification risk with regard to class labels produced by a clustering algorithm. The preferred number of clusters is determined by minimizing this classification risk as a function of the number of clusters. Convincing results are achieved on simulated as well as gene expression data sets. Comparisons to other methods demonstrate the competitive performance of our method and its suitability as a general validation tool for clustering solutions in real-world problems.
Similar articles
- Weighted rank aggregation of cluster validation measures: a Monte Carlo cross-entropy approach.
Pihur V, Datta S, Datta S. Pihur V, et al. Bioinformatics. 2007 Jul 1;23(13):1607-15. doi: 10.1093/bioinformatics/btm158. Epub 2007 May 5. Bioinformatics. 2007. PMID: 17483500 - Clustering of change patterns using Fourier coefficients.
Kim J, Kim H. Kim J, et al. Bioinformatics. 2008 Jan 15;24(2):184-91. doi: 10.1093/bioinformatics/btm568. Epub 2007 Nov 19. Bioinformatics. 2008. PMID: 18025003 - Graph-based consensus clustering for class discovery from gene expression data.
Yu Z, Wong HS, Wang H. Yu Z, et al. Bioinformatics. 2007 Nov 1;23(21):2888-96. doi: 10.1093/bioinformatics/btm463. Epub 2007 Sep 14. Bioinformatics. 2007. PMID: 17872912 - Comparing algorithms for clustering of expression data: how to assess gene clusters.
Yona G, Dirks W, Rahman S. Yona G, et al. Methods Mol Biol. 2009;541:479-509. doi: 10.1007/978-1-59745-243-4_21. Methods Mol Biol. 2009. PMID: 19381534 Review. - Gene expression profiling--Clusters of possibilities.
Bergkvist A, Rusnakova V, Sindelka R, Garda JM, Sjögreen B, Lindh D, Forootan A, Kubista M. Bergkvist A, et al. Methods. 2010 Apr;50(4):323-35. doi: 10.1016/j.ymeth.2010.01.009. Epub 2010 Jan 15. Methods. 2010. PMID: 20079843 Review.
Cited by
- A 3D approach to understanding heterogeneity in early developing autisms.
Mandelli V, Severino I, Eyler L, Pierce K, Courchesne E, Lombardo MV. Mandelli V, et al. Mol Autism. 2024 Sep 30;15(1):41. doi: 10.1186/s13229-024-00613-5. Mol Autism. 2024. PMID: 39350293 Free PMC article. - Biopsychosocial phenotypes in people with HIV in the CHARTER cohort.
Tang B, Ellis RJ, Vaida F, Umlauf A, Franklin DR, Dastgheyb R, Rubin LH, Riggs PK, Iudicello JE, Clifford DB, Moore DJ, Heaton RK, Letendre SL. Tang B, et al. Brain Commun. 2024 Jul 29;6(4):fcae224. doi: 10.1093/braincomms/fcae224. eCollection 2024. Brain Commun. 2024. PMID: 39077377 Free PMC article. - Three distinct patterns of mental health response following accidents in mountain sports: a follow-up study of individuals treated at a tertiary trauma center.
Salvotti HV, Tymoszuk P, Ströhle M, Paal P, Brugger H, Faulhaber M, Kugler N, Beck T, Sperner-Unterweger B, Hüfner K. Salvotti HV, et al. Eur Arch Psychiatry Clin Neurosci. 2024 Sep;274(6):1289-1310. doi: 10.1007/s00406-024-01807-x. Epub 2024 May 10. Eur Arch Psychiatry Clin Neurosci. 2024. PMID: 38727827 Free PMC article. - Dynamical models reveal anatomically reliable attractor landscapes embedded in resting state brain networks.
Chen R, Singh M, Braver TS, Ching S. Chen R, et al. bioRxiv [Preprint]. 2024 Jan 16:2024.01.15.575745. doi: 10.1101/2024.01.15.575745. bioRxiv. 2024. PMID: 38293124 Free PMC article. Preprint. - Individual connectivity-based parcellations reflect functional properties of human auditory cortex.
Hakonen M, Dahmani L, Lankinen K, Ren J, Barbaro J, Blazejewska A, Cui W, Kotlarz P, Li M, Polimeni JR, Turpin T, Uluç I, Wang D, Liu H, Ahveninen J. Hakonen M, et al. bioRxiv [Preprint]. 2024 May 14:2024.01.20.576475. doi: 10.1101/2024.01.20.576475. bioRxiv. 2024. PMID: 38293021 Free PMC article. Preprint.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources