Abstract
Breast cancer is a highly diverse disease. With the state-of-the-art methods of molecular studies, novel subgroups of breast cancer can be revealed. The proper identification of subtypes is crucial for treatment choice. Hence, further investigation of breast cancer subtypes is promising in terms of therapy tailoring. We applied various machine learning approaches to the set of protein level measurements to detect subpopulations of breast cancer patients. Those methods involved various dimensionality reduction techniques combined with clustering. The outcomes of those approaches depended on the algorithms involved and on their parameters. Hence, we proposed the methodology to compare the results of clustering algorithms when the proper number of groups is unknown. The used metrices based on the effect size measurements and allowed for the selection of the best machine learning approach. The values of the proposed pooled d measure varied from 1.6847 for the worst method to 2.0568 for the best one. The highest value was obtained for the custom DiviK approach. Potentially, the metrices can also serve for the proteomic characterization of differences between subtypes and the identification of novel biomarkers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sørlie, T., et al.: Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications. Proc. Natl. Acad. Sci. 98(19), 10869–10874 (2001)
Parker, J.S., et al.: Supervised risk predictor of breast cancer based on intrinsic subtypes. J. Clin. Oncol. 27(8), 1160 (2009)
Berger, A.C., et al.: A comprehensive pan-cancer molecular study of gynecologic and breast cancers. Cancer Cell 33(4), 690–705 (2018)
Koboldt, D.C.F.R., et al.: Comprehensive molecular portraits of human breast tumours. Nature 490(7418), 61–70 (2012)
Leek, J.T., et al.: sva: Surrogate Variable Analysis. R package version 3.38.0. (2020)
Campello, R.J.G.B., Moulavi, D., Sander, J.: Density-based clustering based on hierarchical density estimates. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) PAKDD 2013. LNCS (LNAI), vol. 7819, pp. 160–172. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-37456-2_14
Blondel, V.D., Guillaume, J.L., Lambiotte, R., Lefebvre, E.: Fast unfolding of communities in large networks. J. Stat. Mech: Theory Exp. 2008(10), P10008 (2008)
Mrukwa, G., Polanska, J.: DiviK: divisive intelligent K-means for hands-free unsupervised clustering in biological big data. arXiv preprint arXiv:2009.10706 (2020)
McInnes, L., Healy, J., Melville, J.: Umap: uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)
Marczyk, M., Jaksik, R., Polanski, A., Polanska, J.: Gamred—Adaptive filtering of high-throughput biological data. IEEE/ACM Trans. Comput. Biol. Bioinf. 17(1), 149–157 (2018)
Cohen, J.: Statistical Power Analysis for the Behavioral Sciences. Lawrence Earlbaum Associates, New York (1988)
Sawilowsky, S.S.: New effect size rules of thumb. J. Mod. Appl. Stat. Methods 8(2), 26 (2009)
Kanehisa, M., Furumichi, M., Tanabe, M., Sato, Y., Morishima, K.: KEGG: new perspectives on genomes, pathways, diseases and drugs. Nucleic Acids Res. 45(D1), D353–D361 (2017)
Acknowledgment
This study is supported by European Social Fund grant no. POWR.03.02.00-00-I029 [JT] and Silesian University of Technology grant no. 02/070/BK_22/0033 for Support and Development of Research Potential [JP]. The results published here are based upon data generated by the TCGA Research Network: https://www.cancer.gov/tcga.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Tobiasz, J., Polanska, J. (2022). How to Compare Various Clustering Outcomes? Metrices to Investigate Breast Cancer Patient Subpopulations Based on Proteomic Profiles. In: Rojas, I., Valenzuela, O., Rojas, F., Herrera, L.J., Ortuño, F. (eds) Bioinformatics and Biomedical Engineering. IWBBIO 2022. Lecture Notes in Computer Science(), vol 13347. Springer, Cham. https://doi.org/10.1007/978-3-031-07802-6_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-07802-6_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-07801-9
Online ISBN: 978-3-031-07802-6
eBook Packages: Computer ScienceComputer Science (R0)