Skip to main content


Fig. 1 | BMC Medical Genomics

Fig. 1

From: Deconvolution of transcriptomes and miRNomes by independent component analysis provides insights into biological processes and clinical outcomes of melanoma patients

Fig. 1

Visualization of the approach taken to data analysis. A large discovery dataset and a small investigation dataset from patients (both mRNA) were concatenated and analysed together by ICA. As a result, two matrices were obtained: S (metagenes), containing contribution of the genes to each component, and M (metasamples), presenting the weights of the components in the samples. S provides gene signatures for each of the components, which could be linked to cellular processes by standard functional annotation or enrichment analysis. M can be linked to clinical data and used to predict classes of new patients and their survival

Back to article page