Cargando…

Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data

We motivate and present biVI, which combines the variational autoencoder framework of scVI with biophysically motivated, bivariate models for nascent and mature RNA distributions. While previous approaches to integrate bimodal data via the variational autoencoder framework ignore the causal relation...

Descripción completa

Detalles Bibliográficos
Autores principales: Carilli, Maria, Gorin, Gennady, Choi, Yongin, Chari, Tara, Pachter, Lior
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cold Spring Harbor Laboratory 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9882246/
https://www.ncbi.nlm.nih.gov/pubmed/36712140
http://dx.doi.org/10.1101/2023.01.13.523995
_version_ 1784879262028791808
author Carilli, Maria
Gorin, Gennady
Choi, Yongin
Chari, Tara
Pachter, Lior
author_facet Carilli, Maria
Gorin, Gennady
Choi, Yongin
Chari, Tara
Pachter, Lior
author_sort Carilli, Maria
collection PubMed
description We motivate and present biVI, which combines the variational autoencoder framework of scVI with biophysically motivated, bivariate models for nascent and mature RNA distributions. While previous approaches to integrate bimodal data via the variational autoencoder framework ignore the causal relationship between measurements, biVI models the biophysical processes that give rise to observations. We demonstrate through simulated benchmarking that biVI captures cell type structure in a low-dimensional space and accurately recapitulates parameter values and copy number distributions. On biological data, biVI provides a scalable route for identifying the biophysical mechanisms underlying gene expression. This analytical approach outlines a generalizable strategy for treating multimodal datasets generated by high-throughput, single-cell genomic assays.
format Online
Article
Text
id pubmed-9882246
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Cold Spring Harbor Laboratory
record_format MEDLINE/PubMed
spelling pubmed-98822462023-01-28 Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data Carilli, Maria Gorin, Gennady Choi, Yongin Chari, Tara Pachter, Lior bioRxiv Article We motivate and present biVI, which combines the variational autoencoder framework of scVI with biophysically motivated, bivariate models for nascent and mature RNA distributions. While previous approaches to integrate bimodal data via the variational autoencoder framework ignore the causal relationship between measurements, biVI models the biophysical processes that give rise to observations. We demonstrate through simulated benchmarking that biVI captures cell type structure in a low-dimensional space and accurately recapitulates parameter values and copy number distributions. On biological data, biVI provides a scalable route for identifying the biophysical mechanisms underlying gene expression. This analytical approach outlines a generalizable strategy for treating multimodal datasets generated by high-throughput, single-cell genomic assays. Cold Spring Harbor Laboratory 2023-05-02 /pmc/articles/PMC9882246/ /pubmed/36712140 http://dx.doi.org/10.1101/2023.01.13.523995 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/) , which allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use.
spellingShingle Article
Carilli, Maria
Gorin, Gennady
Choi, Yongin
Chari, Tara
Pachter, Lior
Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
title Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
title_full Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
title_fullStr Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
title_full_unstemmed Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
title_short Biophysical modeling with variational autoencoders for bimodal, single-cell RNA sequencing data
title_sort biophysical modeling with variational autoencoders for bimodal, single-cell rna sequencing data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9882246/
https://www.ncbi.nlm.nih.gov/pubmed/36712140
http://dx.doi.org/10.1101/2023.01.13.523995
work_keys_str_mv AT carillimaria biophysicalmodelingwithvariationalautoencodersforbimodalsinglecellrnasequencingdata
AT goringennady biophysicalmodelingwithvariationalautoencodersforbimodalsinglecellrnasequencingdata
AT choiyongin biophysicalmodelingwithvariationalautoencodersforbimodalsinglecellrnasequencingdata
AT charitara biophysicalmodelingwithvariationalautoencodersforbimodalsinglecellrnasequencingdata
AT pachterlior biophysicalmodelingwithvariationalautoencodersforbimodalsinglecellrnasequencingdata