Abstract
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.
Highlights
Cancer research is one of the most important providers of large-scale molecular profiling data, which help in understanding the state of human cells in disease and shed light on the normal physiological processes measurable and detectable in various kinds of omics datasets
We reviewed most of the recent achievements in computational cancer biology research where Independent component analysis (ICA) was used as the main data analysis tool
The same authors further suggested using the BioBombe approach [46], where three matrix factorization methods (PCA, ICA, and negative matrix factorization (NMF)) and two autoencoder-based dimension reduction techniques were systematically compared based on the pancancer The Cancer Genome Atlas (TCGA) datasets comprising 11,069 tumoral samples
Summary
Cancer research is one of the most important providers of large-scale molecular profiling data, which help in understanding the state of human cells in disease and shed light on the normal physiological processes measurable and detectable in various kinds of omics datasets. One of the standard methods in such a toolbox is independent component analysis (ICA) having a long standing history of application to biological data, including the analysis of molecular profiles (mainly, transcriptomic). Independent component analysis and matrix factorization approaches are standard methods in the rapidly growing arsenal of machine learning methods applied to the molecular biology and medical data. Further we will use the term metagene (or metagene weights for the individual elements) to refer to vector sk even when describing application of ICA to various data types. The NMF components contain only non-negative elements, which makes the intuitive picture of the additive action of metagenes simpler to interpret, while in PCA and ICA some metagenes can cancel the action of other metagenes if they are summed up with different signs
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
