Universal nature of drug treatment responses in drug-tissue-wide model-animal experiments using tensor decomposition-based unsupervised feature extraction

摘要: ABSTRACT Gene expression profiles of tissues treated with drugs have recently been used to infer clinical outcomes. Although this method is often successful from the application point view, gene altered by rarely analyzed in detail, because extremely large number genes involved. Here, we applied tensor decomposition (TD)-based unsupervised feature extraction (FE) 24 mouse 15 drugs. TD-based FE enabled identification common effects including an interesting universal feature: these affect a gene-group-wide manner and were dependent on three tissue types (neuronal, muscular, gastroenterological). For each group, few tens hundreds affected drug treatment. These are distinctly expressed between treatments controls as well individual groups other tissues. We also validated assignment using multiple enrichment analyses. conclude that promising for integrated analysis completely manner.