Cargando…

Deep Learning Methods for Omics Data Imputation

SIMPLE SUMMARY: Missing values are common in omics data and can arise from various causes. Imputation approaches offer a different means of handling missing data instead of utilizing only subsets of the dataset. However, the imputation of missing omics data is a challenging task. Advanced imputation...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Lei, Song, Meng, Shen, Hui, Hong, Huixiao, Gong, Ping, Deng, Hong-Wen, Zhang, Chaoyang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10604785/
https://www.ncbi.nlm.nih.gov/pubmed/37887023
http://dx.doi.org/10.3390/biology12101313
_version_ 1785126918290407424
author Huang, Lei
Song, Meng
Shen, Hui
Hong, Huixiao
Gong, Ping
Deng, Hong-Wen
Zhang, Chaoyang
author_facet Huang, Lei
Song, Meng
Shen, Hui
Hong, Huixiao
Gong, Ping
Deng, Hong-Wen
Zhang, Chaoyang
author_sort Huang, Lei
collection PubMed
description SIMPLE SUMMARY: Missing values are common in omics data and can arise from various causes. Imputation approaches offer a different means of handling missing data instead of utilizing only subsets of the dataset. However, the imputation of missing omics data is a challenging task. Advanced imputation methods such as deep learning-based approaches can model complex patterns and relationships in large and high-dimensional omics datasets, making them an increasingly popular choice for imputation. This review provides an overview of deep learning-based methods for omics data imputation, focusing on model architectures and multi-omics data imputation. This review also examines the challenges and opportunities that are associated with deep learning methods in this field. ABSTRACT: One common problem in omics data analysis is missing values, which can arise due to various reasons, such as poor tissue quality and insufficient sample volumes. Instead of discarding missing values and related data, imputation approaches offer an alternative means of handling missing data. However, the imputation of missing omics data is a non-trivial task. Difficulties mainly come from high dimensionality, non-linear or non-monotonic relationships within features, technical variations introduced by sampling methods, sample heterogeneity, and the non-random missingness mechanism. Several advanced imputation methods, including deep learning-based methods, have been proposed to address these challenges. Due to its capability of modeling complex patterns and relationships in large and high-dimensional datasets, many researchers have adopted deep learning models to impute missing omics data. This review provides a comprehensive overview of the currently available deep learning-based methods for omics imputation from the perspective of deep generative model architectures such as autoencoder, variational autoencoder, generative adversarial networks, and Transformer, with an emphasis on multi-omics data imputation. In addition, this review also discusses the opportunities that deep learning brings and the challenges that it might face in this field.
format Online
Article
Text
id pubmed-10604785
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106047852023-10-28 Deep Learning Methods for Omics Data Imputation Huang, Lei Song, Meng Shen, Hui Hong, Huixiao Gong, Ping Deng, Hong-Wen Zhang, Chaoyang Biology (Basel) Review SIMPLE SUMMARY: Missing values are common in omics data and can arise from various causes. Imputation approaches offer a different means of handling missing data instead of utilizing only subsets of the dataset. However, the imputation of missing omics data is a challenging task. Advanced imputation methods such as deep learning-based approaches can model complex patterns and relationships in large and high-dimensional omics datasets, making them an increasingly popular choice for imputation. This review provides an overview of deep learning-based methods for omics data imputation, focusing on model architectures and multi-omics data imputation. This review also examines the challenges and opportunities that are associated with deep learning methods in this field. ABSTRACT: One common problem in omics data analysis is missing values, which can arise due to various reasons, such as poor tissue quality and insufficient sample volumes. Instead of discarding missing values and related data, imputation approaches offer an alternative means of handling missing data. However, the imputation of missing omics data is a non-trivial task. Difficulties mainly come from high dimensionality, non-linear or non-monotonic relationships within features, technical variations introduced by sampling methods, sample heterogeneity, and the non-random missingness mechanism. Several advanced imputation methods, including deep learning-based methods, have been proposed to address these challenges. Due to its capability of modeling complex patterns and relationships in large and high-dimensional datasets, many researchers have adopted deep learning models to impute missing omics data. This review provides a comprehensive overview of the currently available deep learning-based methods for omics imputation from the perspective of deep generative model architectures such as autoencoder, variational autoencoder, generative adversarial networks, and Transformer, with an emphasis on multi-omics data imputation. In addition, this review also discusses the opportunities that deep learning brings and the challenges that it might face in this field. MDPI 2023-10-07 /pmc/articles/PMC10604785/ /pubmed/37887023 http://dx.doi.org/10.3390/biology12101313 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Review
Huang, Lei
Song, Meng
Shen, Hui
Hong, Huixiao
Gong, Ping
Deng, Hong-Wen
Zhang, Chaoyang
Deep Learning Methods for Omics Data Imputation
title Deep Learning Methods for Omics Data Imputation
title_full Deep Learning Methods for Omics Data Imputation
title_fullStr Deep Learning Methods for Omics Data Imputation
title_full_unstemmed Deep Learning Methods for Omics Data Imputation
title_short Deep Learning Methods for Omics Data Imputation
title_sort deep learning methods for omics data imputation
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10604785/
https://www.ncbi.nlm.nih.gov/pubmed/37887023
http://dx.doi.org/10.3390/biology12101313
work_keys_str_mv AT huanglei deeplearningmethodsforomicsdataimputation
AT songmeng deeplearningmethodsforomicsdataimputation
AT shenhui deeplearningmethodsforomicsdataimputation
AT honghuixiao deeplearningmethodsforomicsdataimputation
AT gongping deeplearningmethodsforomicsdataimputation
AT denghongwen deeplearningmethodsforomicsdataimputation
AT zhangchaoyang deeplearningmethodsforomicsdataimputation