DeepLINK: Deep learning inference using knockoffs with applications to genomics

Although practically attractive with high prediction and classification power, complicated learning methods often lack interpretability and reproducibility, limiting their scientific usage. A useful remedy is to select truly important variables contributing to the response of interest. We develop a method for deep learning inference using knockoffs, DeepLINK, to achieve the goal of variable selection with controlled error rate in deep learning models. We show that DeepLINK can also have high power in variable selection with a broad class of model designs. We then apply DeepLINK to three real datasets and produce statistical inference results with both reproducibility and biological meanings, demonstrating its promising usage to a broad range of scientific applications. Software data have been deposited in GitHub (). Preprocessed data matrices for the four publicly available data sets can be downloaded with the corresponding link: Zeller microbiome ([67][1]), Yu microbiome ([68][2]), murine scRNA-seq ([69][3]), and human scRNA-seq ([70][4]). [1]: #ref-67 [2]: #ref-68 [3]: #ref-69 [4]: #ref-70