Abstract
This study aims to develop new classifiers that can effectively integrate and analyze biomedical data obtained from various sources through high-throughput technologies. The use of explainable models is particularly important as they offer insights into the relationships and patterns within the data, which leads to a better understanding of the underlying processes.
The objective of this research is to examine the effectiveness of decision trees combined with Relative eXpression Analysis (RXA) for classifying multi-omics data. Several concepts for integrating separated data are verified, based on different pair relationships between the features. Within the study, we propose a multi-test approach that combines linked top-scoring pairs from different omics in each internal node of the hierarchical classification model. To address the significant computational challenges raised by RXA, the most time-consuming aspects are parallelized using a GPU. The proposed solution was experimentally validated using single and multi-omics datasets. The results show that the proposed concept generates more accurate and interpretable predictions than commonly used tree-based solutions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, X., Wang, M., Zhang, H.: The use of classification trees in bioinformatics. Wiley Interdisciplinary Reviews: Data Mining and Knowledge 55–63 (2011)
Cohen, WW.: Fast effective rule induction. In: ICML95, San Francisco, CA, USA, pp. 115–123. Morgan Kaufmann (1995)
Czajkowski, M., Kretowski, M.: Top scoring pair decision tree for gene expression data analysis. Adv. Exp. Med. Biol. 696, 27–35 (2011)
Czajkowski, M., Kretowski, M.: Decision tree underfitting in mining of gene expression data. An evolutionary multi-test tree approach. Expert Syst. Appl. 137, 392–404 (2019)
Czajkowski, M., Jurczuk, K., Kretowski, M.: Relative expression classification tree. A preliminary GPU-based implementation. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K. (eds.) PPAM 2019. LNCS, vol. 12043, pp. 359–369. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-43229-4_31
Demsar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Eddy, J.A., Sung, J., Geman, D., Price, N.D.: Relative expression analysis for molecular cancer diagnosis and prognosis. Technol. Cancer Res. Treat. 9(2), 149–159 (2010)
Frank, E., Hall, M.A., Witten, I.H.: The WEKA Workbench. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann (2016)
Geman, D., d’Avignon, C., Naiman, DQ., Winslow, RL.: Classifying gene expression profiles from pairwise mRNA comparisons. Stat. Appl. Genet. Mol. Biol. 3(19) (2004)
Huang, S., Chaudhary, K., Garmire, L.X.: More is better: recent progress in multi-omics data integration methods. Front. Genet. 8 (2017)
Kotsiantis, S.B.: Decision trees: a recent overview. Artif. Intell. Rev. 39(4), 261–283 (2013)
Multi-Omics Cancer Benchmark TCGA Preprocessed Data repository. http://acgt.cs.tau.ac.il/multiomic_benchmark/download.html
Robnik-Sikonja, M., Kononenko, I.: Theoretical and empirical analysis of ReliefF and RReliefF. Mach. Learn. 53(1–2), 23–69 (2003)
Quinlan, R.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)
Wu, C., Zhou, F., et al.: A selective review of multi-level omics data integration using variable selection. High-Throughput 8(1), 4 (2019)
Acknowledgments
This project was funded by the Polish National Science Centre and allocated on the basis of decision 2019/33/B/ST6/02386 from BUT founded by Polish Ministry of Science and Higher Education (first and second author). The third author was supported by the grant WZ/WI-IIT/4/2023 from BUT founded by Polish Ministry of Science and Higher Education.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Czajkowski, M., Jurczuk, K., Kretowski, M. (2023). Hierarchical Relative Expression Analysis in Multi-omics Data Classification. In: Mikyška, J., de Mulatier, C., Paszynski, M., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M. (eds) Computational Science – ICCS 2023. ICCS 2023. Lecture Notes in Computer Science, vol 14074. Springer, Cham. https://doi.org/10.1007/978-3-031-36021-3_69
Download citation
DOI: https://doi.org/10.1007/978-3-031-36021-3_69
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36020-6
Online ISBN: 978-3-031-36021-3
eBook Packages: Computer ScienceComputer Science (R0)