scFSNN: a feature selection method based on neural network for single-cell RNA-seq data
Abstract While single-cell RNA sequencing (scRNA-seq) allows researchers to analyze gene expression in individual cells, its unique characteristics like over-dispersion, zero-inflation, high gene-gene correlation, and large data volume with many features pose challenges for most existing feature sel...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2024-03-01
|
Series: | BMC Genomics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12864-024-10160-1 |
_version_ | 1797266910788714496 |
---|---|
author | Minjiao Peng Baoqin Lin Jun Zhang Yan Zhou Bingqing Lin |
author_facet | Minjiao Peng Baoqin Lin Jun Zhang Yan Zhou Bingqing Lin |
author_sort | Minjiao Peng |
collection | DOAJ |
description | Abstract While single-cell RNA sequencing (scRNA-seq) allows researchers to analyze gene expression in individual cells, its unique characteristics like over-dispersion, zero-inflation, high gene-gene correlation, and large data volume with many features pose challenges for most existing feature selection methods. In this paper, we present a feature selection method based on neural network (scFSNN) to solve classification problem for the scRNA-seq data. scFSNN is an embedded method that can automatically select features (genes) during model training, control the false discovery rate of selected features and adaptively determine the number of features to be eliminated. Extensive simulation and real data studies demonstrate its excellent feature selection ability and predictive performance. |
first_indexed | 2024-04-25T01:08:12Z |
format | Article |
id | doaj.art-7385ee4e8ca7400da02837cc5654519a |
institution | Directory Open Access Journal |
issn | 1471-2164 |
language | English |
last_indexed | 2024-04-25T01:08:12Z |
publishDate | 2024-03-01 |
publisher | BMC |
record_format | Article |
series | BMC Genomics |
spelling | doaj.art-7385ee4e8ca7400da02837cc5654519a2024-03-10T12:06:36ZengBMCBMC Genomics1471-21642024-03-0125111110.1186/s12864-024-10160-1scFSNN: a feature selection method based on neural network for single-cell RNA-seq dataMinjiao Peng0Baoqin Lin1Jun Zhang2Yan Zhou3Bingqing Lin4School of Mathematical Sciences, Shenzhen UniversityExperimental Center, The First Affiliated Hospital of Guangzhou University of Chinese MedicineSchool of Mathematical Sciences, Shenzhen UniversitySchool of Mathematical Sciences, Shenzhen UniversitySchool of Mathematical Sciences, Shenzhen UniversityAbstract While single-cell RNA sequencing (scRNA-seq) allows researchers to analyze gene expression in individual cells, its unique characteristics like over-dispersion, zero-inflation, high gene-gene correlation, and large data volume with many features pose challenges for most existing feature selection methods. In this paper, we present a feature selection method based on neural network (scFSNN) to solve classification problem for the scRNA-seq data. scFSNN is an embedded method that can automatically select features (genes) during model training, control the false discovery rate of selected features and adaptively determine the number of features to be eliminated. Extensive simulation and real data studies demonstrate its excellent feature selection ability and predictive performance.https://doi.org/10.1186/s12864-024-10160-1Feature selectionDeep neural networkFDR control |
spellingShingle | Minjiao Peng Baoqin Lin Jun Zhang Yan Zhou Bingqing Lin scFSNN: a feature selection method based on neural network for single-cell RNA-seq data BMC Genomics Feature selection Deep neural network FDR control |
title | scFSNN: a feature selection method based on neural network for single-cell RNA-seq data |
title_full | scFSNN: a feature selection method based on neural network for single-cell RNA-seq data |
title_fullStr | scFSNN: a feature selection method based on neural network for single-cell RNA-seq data |
title_full_unstemmed | scFSNN: a feature selection method based on neural network for single-cell RNA-seq data |
title_short | scFSNN: a feature selection method based on neural network for single-cell RNA-seq data |
title_sort | scfsnn a feature selection method based on neural network for single cell rna seq data |
topic | Feature selection Deep neural network FDR control |
url | https://doi.org/10.1186/s12864-024-10160-1 |
work_keys_str_mv | AT minjiaopeng scfsnnafeatureselectionmethodbasedonneuralnetworkforsinglecellrnaseqdata AT baoqinlin scfsnnafeatureselectionmethodbasedonneuralnetworkforsinglecellrnaseqdata AT junzhang scfsnnafeatureselectionmethodbasedonneuralnetworkforsinglecellrnaseqdata AT yanzhou scfsnnafeatureselectionmethodbasedonneuralnetworkforsinglecellrnaseqdata AT bingqinglin scfsnnafeatureselectionmethodbasedonneuralnetworkforsinglecellrnaseqdata |