DeepLINK: Deep learning inference using knockoffs with applications to genomics.
Proc Natl Acad Sci U S A
; 118(36)2021 09 07.
Article
em En
| MEDLINE
| ID: mdl-34480002
ABSTRACT
We propose a deep learning-based knockoffs inference framework, DeepLINK, that guarantees the false discovery rate (FDR) control in high-dimensional settings. DeepLINK is applicable to a broad class of covariate distributions described by the possibly nonlinear latent factor models. It consists of two major parts an autoencoder network for the knockoff variable construction and a multilayer perceptron network for feature selection with the FDR control. The empirical performance of DeepLINK is investigated through extensive simulation studies, where it is shown to achieve FDR control in feature selection with both high selection power and high prediction accuracy. We also apply DeepLINK to three real data applications to demonstrate its practical utility.
Palavras-chave
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Biologia Computacional
/
Genômica
/
Aprendizado Profundo
Tipo de estudo:
Prognostic_studies
Idioma:
En
Revista:
Proc Natl Acad Sci U S A
Ano de publicação:
2021
Tipo de documento:
Article