VEGA is an interpretable generative model for inferring biological network activity in single-cell transcriptomics
Developing interpretable models is a major challenge in single cell deep learning. Here we show that the VEGA variational autoencoder model, whose decoder wiring mirrors gene modules, can provide direct interpretability to the latent space further enabling the inference of biological module activity...
Guardado en:
Autores principales: | Lucas Seninge, Ioannis Anastopoulos, Hongxu Ding, Joshua Stuart |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/ed3aa6f7d98748388fc0f47ff767569f |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Towards inferring nanopore sequencing ionic currents from nucleotide chemical structures
por: Hongxu Ding, et al.
Publicado: (2021) -
Biological process activity transformation of single cell gene expression for cross-species alignment
por: Hongxu Ding, et al.
Publicado: (2019) -
Interpretable dimensionality reduction of single cell transcriptome data with deep generative models
por: Jiarui Ding, et al.
Publicado: (2018) -
Perturbation biology: inferring signaling networks in cellular systems.
por: Evan J Molinelli, et al.
Publicado: (2013) -
Inference of differentiation time for single cell transcriptomes using cell population reference data
por: Na Sun, et al.
Publicado: (2017)