Looking at our unsupervised attributions shows that while there may be significant enough differences in expression of genes in the “IFN Gamma Signaling” pathway to differentiate stimulated and unstimulated cells, this pathway is not one of the major sources of variation in the dataset, at least when compared to pathways more directly related to IFN- \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta$$\end{document} β signaling.
← all excerpts
PAUSE: principled feature attribution for unsupervised gene expression analysis.
1
—
—