Cargando…

Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention

A limitation of current deep learning (DL) approaches for single-cell RNA sequencing (scRNAseq) analysis is the lack of interpretability. Moreover, existing pipelines are designed and trained for specific tasks used disjointly for different stages of analysis. We present scANNA, a novel interpretabl...

Descripción completa

Detalles Bibliográficos
Autores principales: Davalos, Oscar A., Heydari, A. Ali, Fertig, Elana J., Sindi, Suzanne S., Hoyer, Katrina K.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Cold Spring Harbor Laboratory 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10312486/
https://www.ncbi.nlm.nih.gov/pubmed/37398136
http://dx.doi.org/10.1101/2023.05.29.542760
_version_ 1785066938403127296
author Davalos, Oscar A.
Heydari, A. Ali
Fertig, Elana J.
Sindi, Suzanne S.
Hoyer, Katrina K.
author_facet Davalos, Oscar A.
Heydari, A. Ali
Fertig, Elana J.
Sindi, Suzanne S.
Hoyer, Katrina K.
author_sort Davalos, Oscar A.
collection PubMed
description A limitation of current deep learning (DL) approaches for single-cell RNA sequencing (scRNAseq) analysis is the lack of interpretability. Moreover, existing pipelines are designed and trained for specific tasks used disjointly for different stages of analysis. We present scANNA, a novel interpretable DL model for scRNAseq studies that leverages neural attention to learn gene associations. After training, the learned gene importance (interpretability) is used to perform downstream analyses (e.g., global marker selection and cell-type classification) without retraining. ScANNA’s performance is comparable to or better than state-of-the-art methods designed and trained for specific standard scRNAseq analyses even though scANNA was not trained for these tasks explicitly. ScANNA enables researchers to discover meaningful results without extensive prior knowledge or training separate task-specific models, saving time and enhancing scRNAseq analyses.
format Online
Article
Text
id pubmed-10312486
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Cold Spring Harbor Laboratory
record_format MEDLINE/PubMed
spelling pubmed-103124862023-07-01 Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention Davalos, Oscar A. Heydari, A. Ali Fertig, Elana J. Sindi, Suzanne S. Hoyer, Katrina K. bioRxiv Article A limitation of current deep learning (DL) approaches for single-cell RNA sequencing (scRNAseq) analysis is the lack of interpretability. Moreover, existing pipelines are designed and trained for specific tasks used disjointly for different stages of analysis. We present scANNA, a novel interpretable DL model for scRNAseq studies that leverages neural attention to learn gene associations. After training, the learned gene importance (interpretability) is used to perform downstream analyses (e.g., global marker selection and cell-type classification) without retraining. ScANNA’s performance is comparable to or better than state-of-the-art methods designed and trained for specific standard scRNAseq analyses even though scANNA was not trained for these tasks explicitly. ScANNA enables researchers to discover meaningful results without extensive prior knowledge or training separate task-specific models, saving time and enhancing scRNAseq analyses. Cold Spring Harbor Laboratory 2023-06-01 /pmc/articles/PMC10312486/ /pubmed/37398136 http://dx.doi.org/10.1101/2023.05.29.542760 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
Davalos, Oscar A.
Heydari, A. Ali
Fertig, Elana J.
Sindi, Suzanne S.
Hoyer, Katrina K.
Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention
title Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention
title_full Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention
title_fullStr Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention
title_full_unstemmed Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention
title_short Boosting Single-Cell RNA Sequencing Analysis with Simple Neural Attention
title_sort boosting single-cell rna sequencing analysis with simple neural attention
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10312486/
https://www.ncbi.nlm.nih.gov/pubmed/37398136
http://dx.doi.org/10.1101/2023.05.29.542760
work_keys_str_mv AT davalososcara boostingsinglecellrnasequencinganalysiswithsimpleneuralattention
AT heydariaali boostingsinglecellrnasequencinganalysiswithsimpleneuralattention
AT fertigelanaj boostingsinglecellrnasequencinganalysiswithsimpleneuralattention
AT sindisuzannes boostingsinglecellrnasequencinganalysiswithsimpleneuralattention
AT hoyerkatrinak boostingsinglecellrnasequencinganalysiswithsimpleneuralattention