Compressing gene expression data using multiple latent space dimensionalities learns complementary biological representations
Abstract Background Unsupervised compression algorithms applied to gene expression data extract latent or hidden signals representing technical and biological sources of variation. However, these algorithms require a user to select a biologically appropriate latent space dimensionality. In practice,...
Main Authors: | Gregory P. Way, Michael Zietz, Vincent Rubinetti, Daniel S. Himmelstein, Casey S. Greene |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-05-01
|
Series: | Genome Biology |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13059-020-02021-3 |
Similar Items
-
Affective Latent Representation of Acoustic and Lexical Features for Emotion Recognition
by: Eesung Kim, et al.
Published: (2020-05-01) -
Generating In-Between Images Through Learned Latent Space Representation Using Variational Autoencoders
by: Paulino Cristovao, et al.
Published: (2020-01-01) -
AEkNN: An AutoEncoder kNN-Based Classifier With Built-in Dimensionality Reduction
by: Francisco J. Pulgar, et al.
Published: (2018-11-01) -
A deep adversarial variational autoencoder model for dimensionality reduction in single-cell RNA sequencing analysis
by: Eugene Lin, et al.
Published: (2020-02-01) -
Descriptor-free unsupervised learning method for local structure identification in particle packings
by: Deng, W., et al.
Published: (2022)