Independent component analysis provides clinically relevant insights into the biology of melanoma patients

Abstract

The integration of publicly available and new patient-derived transcriptomic datasets is not straightforward and requires specialized approaches to deal with heterogeneity at technical and biological levels. Here we present a methodology that can overcome technical biases, predict clinically relevant outcomes and identify tumour-related biological processes in patients using previously collected large reference datasets. The approach is based on independent component analysis (ICA) -an unsupervised method of signal deconvolution. We developed parallel consensus ICA that robustly decomposes merged new and reference datasets into signals with minimal mutual dependency. By applying the method to a small cohort of primary melanoma and control samples combined with a large public melanoma dataset, we demonstrate that our method distinguishes celltype specific signals from technical biases and allows to predict clinically relevant patient characteristics. Cancer subtypes, patient survival and activity of key tumour-related processes such as immune response, angiogenesis and cell proliferation were characterized. Additionally, through integration of transcriptomes and miRNomes, the method identified biological functions of miRNAs, which would otherwise not be possible. RNA-seq and miRNA-seq of investigation set:GDC data portal: https://portal.gdc.cancer.gov/ Expression data of validation set:Array Express: https://www.ebi.ac.uk/arrayexpress/experiments/E-GEOD-19234/ New expression data of investigation set:The sequencing data for 3 primary melanoma tumours and 2 controls are freely available under the GEO accession number GSE116111. Data for miRNAs are in the Supplementary Table S5. Tools: Consensus parallel ICA: https://gitlab.com/biomodlih/consica R/Bioconductor v.3.4.3 with packages fastICA, doMC, doSNOW, topGO, randomForest, survival https://cran.r-project.org/ Enrichr ACKNOWLEDGEMENT We would like to thank the patients for providing clinical material and the clinical staff of the Dermatology Unit at the University of Freiburg for professionally taking and handling all the samples. Bioinformatics analyses presented in this paper were partly carried out using the high-performance computing facilities of the University of Luxembourg (http://hpc.uni.lu). Furthermore, we thank Demetra Philippidou and Dr. Susanne Reinsbach for processing clinical samples and NHEM cells forming the investigation dataset. We acknowledge Dr. Aurélien Ginolhac and Cristina Maximo for critically reading the manuscript and for valuable input.

Independent Component Analysis for Unraveling the Complexity of Cancer Omics Datasets

“…Furthermore, in several studies it was found that stabilized or consensus independent components have better characteristics in terms of generalization and interpretation [34,38,39,40,41]. By stabilization one usually means re-computing ICA using multiple random initialization with subsequent clustering of the resulting components [40,41].…”

“…Another component frequently identified in the analysis of transcriptomic data is related to GC-content, which might reflect the influence of GC-content on the RNA amplification step common for both microarray-based and sequencing-based methodologies. In Reference [39], a small dataset of three primary melanoma tumors and two matched controls, characterized at the level of transcriptome and miRNA, were merged together with a large reference melanoma dataset from the Cancer Genome Atlas. The ICA decomposition was performed for the merged transcriptomic and miRNA data separately.…”

“…Independent components can be then computed for each data type separately and then the identified components can be compared by computing correlations between the corresponding a k vectors (metasamples). Such an approach was recently applied in Reference [39] to a set of melanoma bulk samples, profiled at the level of transcriptome and microRNA expression. Similarly, in a recent study [90], 77 breast and 84 ovarian cancer samples, profiled simultaneously at transcriptome and proteome level, were analyzed using stabilized ICA, followed by integrating the discovered associations with clinical data and molecular pathways.…”

Detection of Mental Stress through EEG Signal in Virtual Reality Environment

“…ICA is a technique for unsupervised exploration of multichannel data widely used in many areas of science. The use of ICA can be found, for example, in biology and medicine [63][64][65][66][67], chemistry [68][69][70], astronomy [71,72], financial analysis [73,74], marketing [75], engineering [76], etc. ICA is also often used to preprocess data obtained from EEG [77][78][79][80].…”

Complex Analysis of Fluorescence Intensity Fluctuations of Molecular Compounds

“…Tasks of this kind are solved using data mining algorithms such as data dimensionality reduction and cluster analysis [10,13,14]. Dimensionality reduction algorithms allow switching to a low-dimensional space without losing the essence of information [15,16]. Cluster analysis algorithms make it possible to determine clusters of data specifi ed in varying degrees of similarity, the number of which may be associated with aggregates of molecular compounds.…”