Cancer profiles by Affinity Propagation

Soria, Daniele; Garibaldi, Jonathan M.; Ambrogi, Federico; Boracchi, Patrizia; Raimondi, E.; Biganzoli, Elia M.

Abstract

The Affinity Propagation algorithm is applied to various problems of breast and cutaneous tumours subtyping using traditional biologic markers. The algorithm provides a procedure to determine the number of profiles to be considered. Well know breast cancer case series and cutaneous melanoma were used to compare the results of the Affinity Propagation with the results obtained with standard algorithms and indexes for the optimal choice of the number of clusters.Results from Affinity Propagation are consistent with the results already obtained having the advantage of providing an indication about the number of clusters.

Citation

Soria, D., Garibaldi, J. M., Ambrogi, F., Boracchi, P., Raimondi, E., & Biganzoli, E. M. (2009). Cancer profiles by Affinity Propagation. International Journal of Knowledge Engineering and Soft Data Paradigms, 1(3), https://doi.org/10.1504/IJKESDP.2009.028814

• Journal Article Type: Article
• Publication Date: Jan 1, 2009
• Deposit Date: Jan 30, 2015
• Publicly Available Date: Jan 30, 2015
• Journal: International Journal of Knowledge Engineering and Soft Data Paradigms
• Print ISSN: 1755-3210
• Electronic ISSN: 1755-3229
• Publisher: Inderscience
• Peer Reviewed: Peer Reviewed
• Volume: 1
• Issue: 3
• DOI: https://doi.org/10.1504/IJKESDP.2009.028814
• Keywords: affinity propagation, clustering algorithms, breast cancer, cutaneous melanoma, cancer profiles, tumours, biological markers, biomarkers
• Public URL: https://nottingham-repository.worktribe.com/output/1014831
• Publisher URL: http://www.inderscience.com/info/inarticle.php?artid=28814
• Additional Information: Copyright InderScience Publishers.