Genetically modified Wnt signaling data analysed using machine learning

Signaling pathways are vital for the development of organisms, orchestrating a plethora of biological processes. Pathways failing to function properly can cause numerous disorders, including neurodegenerative diseases and malignant tumors. Only a handful of highly conserved signaling pathways are able to specify cell fates during development. Wnt signaling is one of those and it is known to be involved in development, tissue maintenance and homeostasis. Wnt signalling’s importance is underlined by its conserved presence in almost all mammalian organisms. Mis-regulation of Wnt signaling can result in numerous diseases. We used previously published Rna-seq datasets, deriving from gene edited Hek293T cell lines. Those cells lines lack major components of the Wnt signalling pathway. Here, we are combining machine learning together with traditional statistical analysis methods, in order to analyze the RNA-seq data, but also to compare the robustness of machine learning versus traditional statistical analysis methods. In addition, enrichment analysis based both on machine learning and statistical analysis, is been introduced. Finally, we reveal numerous genes, which are potentially linked to diseases for the first time, utilizing our A.I. analysis.