Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.

Clustering high-dimensional data, such as images or biological measurements, is a long-standing problem and has been studied extensively. Recently, Deep Clustering has gained popularity due to its flexibility in fitting the specific peculiarities of complex data. Here we introduce the Mixture-of-Exp...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Andreas Kopf, Vincent Fortuin, Vignesh Ram Somnath, Manfred Claassen
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Biology (General) QH301-705.5
Acceso en línea:	https://doaj.org/article/ce2ae803ad064ff398d2f8cd15512672
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ce2ae803ad064ff398d2f8cd15512672
record_format	dspace
spelling	oai:doaj.org-article:ce2ae803ad064ff398d2f8cd155126722021-11-25T05:40:33ZMixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.1553-734X1553-735810.1371/journal.pcbi.1009086https://doaj.org/article/ce2ae803ad064ff398d2f8cd155126722021-06-01T00:00:00Zhttps://doi.org/10.1371/journal.pcbi.1009086https://doaj.org/toc/1553-734Xhttps://doaj.org/toc/1553-7358Clustering high-dimensional data, such as images or biological measurements, is a long-standing problem and has been studied extensively. Recently, Deep Clustering has gained popularity due to its flexibility in fitting the specific peculiarities of complex data. Here we introduce the Mixture-of-Experts Similarity Variational Autoencoder (MoE-Sim-VAE), a novel generative clustering model. The model can learn multi-modal distributions of high-dimensional data and use these to generate realistic data with high efficacy and efficiency. MoE-Sim-VAE is based on a Variational Autoencoder (VAE), where the decoder consists of a Mixture-of-Experts (MoE) architecture. This specific architecture allows for various modes of the data to be automatically learned by means of the experts. Additionally, we encourage the lower dimensional latent representation of our model to follow a Gaussian mixture distribution and to accurately represent the similarities between the data points. We assess the performance of our model on the MNIST benchmark data set and challenging real-world tasks of clustering mouse organs from single-cell RNA-sequencing measurements and defining cell subpopulations from mass cytometry (CyTOF) measurements on hundreds of different datasets. MoE-Sim-VAE exhibits superior clustering performance on all these tasks in comparison to the baselines as well as competitor methods.Andreas KopfVincent FortuinVignesh Ram SomnathManfred ClaassenPublic Library of Science (PLoS)articleBiology (General)QH301-705.5ENPLoS Computational Biology, Vol 17, Iss 6, p e1009086 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biology (General) QH301-705.5
spellingShingle	Biology (General) QH301-705.5 Andreas Kopf Vincent Fortuin Vignesh Ram Somnath Manfred Claassen Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.
description	Clustering high-dimensional data, such as images or biological measurements, is a long-standing problem and has been studied extensively. Recently, Deep Clustering has gained popularity due to its flexibility in fitting the specific peculiarities of complex data. Here we introduce the Mixture-of-Experts Similarity Variational Autoencoder (MoE-Sim-VAE), a novel generative clustering model. The model can learn multi-modal distributions of high-dimensional data and use these to generate realistic data with high efficacy and efficiency. MoE-Sim-VAE is based on a Variational Autoencoder (VAE), where the decoder consists of a Mixture-of-Experts (MoE) architecture. This specific architecture allows for various modes of the data to be automatically learned by means of the experts. Additionally, we encourage the lower dimensional latent representation of our model to follow a Gaussian mixture distribution and to accurately represent the similarities between the data points. We assess the performance of our model on the MNIST benchmark data set and challenging real-world tasks of clustering mouse organs from single-cell RNA-sequencing measurements and defining cell subpopulations from mass cytometry (CyTOF) measurements on hundreds of different datasets. MoE-Sim-VAE exhibits superior clustering performance on all these tasks in comparison to the baselines as well as competitor methods.
format	article
author	Andreas Kopf Vincent Fortuin Vignesh Ram Somnath Manfred Claassen
author_facet	Andreas Kopf Vincent Fortuin Vignesh Ram Somnath Manfred Claassen
author_sort	Andreas Kopf
title	Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.
title_short	Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.
title_full	Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.
title_fullStr	Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.
title_full_unstemmed	Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.
title_sort	mixture-of-experts variational autoencoder for clustering and generating from similarity-based representations on single cell data.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/ce2ae803ad064ff398d2f8cd15512672
work_keys_str_mv	AT andreaskopf mixtureofexpertsvariationalautoencoderforclusteringandgeneratingfromsimilaritybasedrepresentationsonsinglecelldata AT vincentfortuin mixtureofexpertsvariationalautoencoderforclusteringandgeneratingfromsimilaritybasedrepresentationsonsinglecelldata AT vigneshramsomnath mixtureofexpertsvariationalautoencoderforclusteringandgeneratingfromsimilaritybasedrepresentationsonsinglecelldata AT manfredclaassen mixtureofexpertsvariationalautoencoderforclusteringandgeneratingfromsimilaritybasedrepresentationsonsinglecelldata
_version_	1718414545085530112

Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data.

Ejemplares similares