Transfer transcriptomic signatures for infectious diseases.

ABSTRACT: The modulation of the transcriptome is among the earliest responses to infection. However, defining the transcriptomic signatures of disease is challenging because logistic, technical, and cost factors limit the size and representativeness of samples in clinical studies. These limitations lead to a poor performance of signatures when applied to new datasets. Although the study focuses on infection, the central hypothesis of the work is the generalization of sets of signatures across diseases. We use a machine learning approach to identify common elements in datasets and then test empirically whether they are informative about a second dataset from a disease or process distinct from the original dataset. We identify sets of genes, which we name transfer signatures, that are predictive acros

SUBMITTER: di Iulio J 

PROVIDER: S-EPMC8179160 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature