ijms-20-04414.pdf (4.91 MB)
Download file

Independent Component Analysis for Unraveling the Complexity of Cancer Omics Datasets.

Download (4.91 MB)
journal contribution
posted on 25.10.2019, 08:36 by N Sompairac, PV Nazarov, U Czerwinska, L Cantini, A Biton, A Molkenov, Z Zhumadilov, E Barillot, F Radvanyi, A Gorban, U Kairov, A Zinovyev
Independent component analysis (ICA) is a matrix factorization approach where the signals captured by each individual matrix factors are optimized to become as mutually independent as possible. Initially suggested for solving source blind separation problems in various fields, ICA was shown to be successful in analyzing functional magnetic resonance imaging (fMRI) and other types of biomedical data. In the last twenty years, ICA became a part of the standard machine learning toolbox, together with other matrix factorization methods such as principal component analysis (PCA) and non-negative matrix factorization (NMF). Here, we review a number of recent works where ICA was shown to be a useful tool for unraveling the complexity of cancer biology from the analysis of different types of omics data, mainly collected for tumoral samples. Such works highlight the use of ICA in dimensionality reduction, deconvolution, data pre-processing, meta-analysis, and others applied to different data types (transcriptome, methylome, proteome, single-cell data). We particularly focus on the technical aspects of ICA application in omics studies such as using different protocols, determining the optimal number of components, assessing and improving reproducibility of the ICA results, and comparison with other popular matrix factorization techniques. We discuss the emerging ICA applications to the integrative analysis of multi-level omics datasets and introduce a conceptual view on ICA as a tool for defining functional subsystems of a complex biological system and their interactions under various conditions. Our review is accompanied by a Jupyter notebook which illustrates the discussed concepts and provides a practical tool for applying ICA to the analysis of cancer omics datasets.

Funding

This work was partially supported by the grant research projects “Pan-cancer deconvolution of omics data using Independent Component Analysis” (IRN: AP05135430) and “Investigation of esophageal cancer tissue gene expression derived from Kazakhstan patients by next-generation sequencing technology” (IRN: AP05134722) of the Ministry of Education and Science of the Republic of Kazakhstan, by the Ministry of Science and Higher Education of the Russian Federation (Project No. 14.Y26.31.0022), the European Union’s Horizon 2020 program (grant No. 826121, iPC project), by the European IMI IMMUCAN project, and by Luxembourg National Research Fund (C17/BM/11664971/DEMICS).

History

Citation

International Journal of Molecular Sciences, 2019, 20 (18)

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Mathematics

Version

VoR (Version of Record)

Published in

International Journal of Molecular Sciences

Publisher

MDPI

eissn

1422-0067

Acceptance date

04/09/2019

Copyright date

2019

Available date

25/10/2019

Publisher version

https://www.mdpi.com/1422-0067/20/18/4414

Language

en