scPDA: denoising protein expression in droplet-based single-cell data

Abstract Droplet-based profiling techniques such as CITE-seq are often contaminated by technical noise. Current computational denoising methods have serious limitations, including a strong reliance on often-unavailable empty droplets or null controls and insufficient efficiency due to ignoring prote...

Full description

Saved in:
Bibliographic Details
Main Authors: Ouyang Zhu, Jun Li
Format: Article
Language:English
Published: BMC 2025-07-01
Series:Genome Biology
Online Access:https://doi.org/10.1186/s13059-025-03686-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849234714823491584
author Ouyang Zhu
Jun Li
author_facet Ouyang Zhu
Jun Li
author_sort Ouyang Zhu
collection DOAJ
description Abstract Droplet-based profiling techniques such as CITE-seq are often contaminated by technical noise. Current computational denoising methods have serious limitations, including a strong reliance on often-unavailable empty droplets or null controls and insufficient efficiency due to ignoring protein-protein interactions. Here, we introduce scPDA, a probabilistic model that employs a variational autoencoder to achieve high computational efficiency. scPDA eliminates the use of empty droplets and shares information across proteins to increase denoising efficiency. Compared to currently available methods, scPDA substantially improves the efficiency of gating-strategy-based cell-type identification, marking a clear advancement in computational denoising of the protein modality.
format Article
id doaj-art-b0db49f2bc6445c19e6f8c3ccb854746
institution Kabale University
issn 1474-760X
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series Genome Biology
spelling doaj-art-b0db49f2bc6445c19e6f8c3ccb8547462025-08-20T04:03:02ZengBMCGenome Biology1474-760X2025-07-0126112410.1186/s13059-025-03686-4scPDA: denoising protein expression in droplet-based single-cell dataOuyang Zhu0Jun Li1Department of Applied and Computational Mathematics and Statistics, University of Notre DameDepartment of Applied and Computational Mathematics and Statistics, University of Notre DameAbstract Droplet-based profiling techniques such as CITE-seq are often contaminated by technical noise. Current computational denoising methods have serious limitations, including a strong reliance on often-unavailable empty droplets or null controls and insufficient efficiency due to ignoring protein-protein interactions. Here, we introduce scPDA, a probabilistic model that employs a variational autoencoder to achieve high computational efficiency. scPDA eliminates the use of empty droplets and shares information across proteins to increase denoising efficiency. Compared to currently available methods, scPDA substantially improves the efficiency of gating-strategy-based cell-type identification, marking a clear advancement in computational denoising of the protein modality.https://doi.org/10.1186/s13059-025-03686-4
spellingShingle Ouyang Zhu
Jun Li
scPDA: denoising protein expression in droplet-based single-cell data
Genome Biology
title scPDA: denoising protein expression in droplet-based single-cell data
title_full scPDA: denoising protein expression in droplet-based single-cell data
title_fullStr scPDA: denoising protein expression in droplet-based single-cell data
title_full_unstemmed scPDA: denoising protein expression in droplet-based single-cell data
title_short scPDA: denoising protein expression in droplet-based single-cell data
title_sort scpda denoising protein expression in droplet based single cell data
url https://doi.org/10.1186/s13059-025-03686-4
work_keys_str_mv AT ouyangzhu scpdadenoisingproteinexpressionindropletbasedsinglecelldata
AT junli scpdadenoisingproteinexpressionindropletbasedsinglecelldata