AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders
Motivation: The emergence of single-cell RNA sequencing (scRNA-seq) technology has paved the way for measuring RNA levels at single-cell resolution to study precise biological functions. However, the presence of a large number of missing values in its data will affect downstream analysis. This paper...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-09-01
|
| Series: | Frontiers in Genetics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fgene.2021.739677/full |
| _version_ | 1818588688264724480 |
|---|---|
| author | Li Xu Li Xu Yin Xu Tong Xue Xinyu Zhang Jin Li |
| author_facet | Li Xu Li Xu Yin Xu Tong Xue Xinyu Zhang Jin Li |
| author_sort | Li Xu |
| collection | DOAJ |
| description | Motivation: The emergence of single-cell RNA sequencing (scRNA-seq) technology has paved the way for measuring RNA levels at single-cell resolution to study precise biological functions. However, the presence of a large number of missing values in its data will affect downstream analysis. This paper presents AdImpute: an imputation method based on semi-supervised autoencoders. The method uses another imputation method (DrImpute is used as an example) to fill the results as imputation weights of the autoencoder, and applies the cost function with imputation weights to learn the latent information in the data to achieve more accurate imputation.Results: As shown in clustering experiments with the simulated data sets and the real data sets, AdImpute is more accurate than other four publicly available scRNA-seq imputation methods, and minimally modifies the biologically silent genes. Overall, AdImpute is an accurate and robust imputation method. |
| first_indexed | 2024-12-16T09:28:44Z |
| format | Article |
| id | doaj.art-31b84bd11ee34053a8db454dbc37f8f2 |
| institution | Directory Open Access Journal |
| issn | 1664-8021 |
| language | English |
| last_indexed | 2024-12-16T09:28:44Z |
| publishDate | 2021-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Genetics |
| spelling | doaj.art-31b84bd11ee34053a8db454dbc37f8f22022-12-21T22:36:35ZengFrontiers Media S.A.Frontiers in Genetics1664-80212021-09-011210.3389/fgene.2021.739677739677AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised AutoencodersLi Xu0Li Xu1Yin Xu2Tong Xue3Xinyu Zhang4Jin Li5College of Computer Science and Technology, Harbin Engineering University, Harbin, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, ChinaSchool of Mathematics, Harbin Institute of Technology, Harbin, ChinaCollege of Computer Science and Technology, Harbin Engineering University, Harbin, ChinaCollege of Computer Science and Technology, Harbin Engineering University, Harbin, ChinaCollege of Computer Science and Technology, Harbin Engineering University, Harbin, ChinaMotivation: The emergence of single-cell RNA sequencing (scRNA-seq) technology has paved the way for measuring RNA levels at single-cell resolution to study precise biological functions. However, the presence of a large number of missing values in its data will affect downstream analysis. This paper presents AdImpute: an imputation method based on semi-supervised autoencoders. The method uses another imputation method (DrImpute is used as an example) to fill the results as imputation weights of the autoencoder, and applies the cost function with imputation weights to learn the latent information in the data to achieve more accurate imputation.Results: As shown in clustering experiments with the simulated data sets and the real data sets, AdImpute is more accurate than other four publicly available scRNA-seq imputation methods, and minimally modifies the biologically silent genes. Overall, AdImpute is an accurate and robust imputation method.https://www.frontiersin.org/articles/10.3389/fgene.2021.739677/fullscRNA-seqmissing value fillingsemi-supervised learningautoencoderimputation method |
| spellingShingle | Li Xu Li Xu Yin Xu Tong Xue Xinyu Zhang Jin Li AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders Frontiers in Genetics scRNA-seq missing value filling semi-supervised learning autoencoder imputation method |
| title | AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders |
| title_full | AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders |
| title_fullStr | AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders |
| title_full_unstemmed | AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders |
| title_short | AdImpute: An Imputation Method for Single-Cell RNA-Seq Data Based on Semi-Supervised Autoencoders |
| title_sort | adimpute an imputation method for single cell rna seq data based on semi supervised autoencoders |
| topic | scRNA-seq missing value filling semi-supervised learning autoencoder imputation method |
| url | https://www.frontiersin.org/articles/10.3389/fgene.2021.739677/full |
| work_keys_str_mv | AT lixu adimputeanimputationmethodforsinglecellrnaseqdatabasedonsemisupervisedautoencoders AT lixu adimputeanimputationmethodforsinglecellrnaseqdatabasedonsemisupervisedautoencoders AT yinxu adimputeanimputationmethodforsinglecellrnaseqdatabasedonsemisupervisedautoencoders AT tongxue adimputeanimputationmethodforsinglecellrnaseqdatabasedonsemisupervisedautoencoders AT xinyuzhang adimputeanimputationmethodforsinglecellrnaseqdatabasedonsemisupervisedautoencoders AT jinli adimputeanimputationmethodforsinglecellrnaseqdatabasedonsemisupervisedautoencoders |