Cargando…

OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data

SIMPLE SUMMARY: OmiEmbed is a unified multi-task deep learning framework for multi-omics data, supporting dimensionality reduction, multi-omics integration, tumour type classification, phenotypic feature reconstruction and survival prediction. The framework is comprised of deep embedding and downstr...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Xiaoyu, Xing, Yuting, Sun, Kai, Guo, Yike
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8235477/
https://www.ncbi.nlm.nih.gov/pubmed/34207255
http://dx.doi.org/10.3390/cancers13123047
_version_ 1783714327737401344
author Zhang, Xiaoyu
Xing, Yuting
Sun, Kai
Guo, Yike
author_facet Zhang, Xiaoyu
Xing, Yuting
Sun, Kai
Guo, Yike
author_sort Zhang, Xiaoyu
collection PubMed
description SIMPLE SUMMARY: OmiEmbed is a unified multi-task deep learning framework for multi-omics data, supporting dimensionality reduction, multi-omics integration, tumour type classification, phenotypic feature reconstruction and survival prediction. The framework is comprised of deep embedding and downstream task modules to capture biomedical information from high-dimensional omics data. OmiEmbed outperformed state-of-the-art methods on all three types of downstream tasks: classification, regression and survival prediction. Better performance was achieved using the multi-task training strategy compared to training each downstream task individually. With the multi-task strategy, OmiEmbed learnt a comprehensive omics embedding containing information from multiple tasks. OmiEmbed is open source, well-organised and convenient to be extended to other customised input data, network structures and downstream tasks, which has promising potential to facilitate more accurate and personalised clinical decision making. ABSTRACT: High-dimensional omics data contain intrinsic biomedical information that is crucial for personalised medicine. Nevertheless, it is challenging to capture them from the genome-wide data, due to the large number of molecular features and small number of available samples, which is also called “the curse of dimensionality” in machine learning. To tackle this problem and pave the way for machine learning-aided precision medicine, we proposed a unified multi-task deep learning framework named OmiEmbed to capture biomedical information from high-dimensional omics data with the deep embedding and downstream task modules. The deep embedding module learnt an omics embedding that mapped multiple omics data types into a latent space with lower dimensionality. Based on the new representation of multi-omics data, different downstream task modules were trained simultaneously and efficiently with the multi-task strategy to predict the comprehensive phenotype profile of each sample. OmiEmbed supports multiple tasks for omics data including dimensionality reduction, tumour type classification, multi-omics integration, demographic and clinical feature reconstruction, and survival prediction. The framework outperformed other methods on all three types of downstream tasks and achieved better performance with the multi-task strategy compared to training them individually. OmiEmbed is a powerful and unified framework that can be widely adapted to various applications of high-dimensional omics data and has great potential to facilitate more accurate and personalised clinical decision making.
format Online
Article
Text
id pubmed-8235477
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-82354772021-06-27 OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data Zhang, Xiaoyu Xing, Yuting Sun, Kai Guo, Yike Cancers (Basel) Article SIMPLE SUMMARY: OmiEmbed is a unified multi-task deep learning framework for multi-omics data, supporting dimensionality reduction, multi-omics integration, tumour type classification, phenotypic feature reconstruction and survival prediction. The framework is comprised of deep embedding and downstream task modules to capture biomedical information from high-dimensional omics data. OmiEmbed outperformed state-of-the-art methods on all three types of downstream tasks: classification, regression and survival prediction. Better performance was achieved using the multi-task training strategy compared to training each downstream task individually. With the multi-task strategy, OmiEmbed learnt a comprehensive omics embedding containing information from multiple tasks. OmiEmbed is open source, well-organised and convenient to be extended to other customised input data, network structures and downstream tasks, which has promising potential to facilitate more accurate and personalised clinical decision making. ABSTRACT: High-dimensional omics data contain intrinsic biomedical information that is crucial for personalised medicine. Nevertheless, it is challenging to capture them from the genome-wide data, due to the large number of molecular features and small number of available samples, which is also called “the curse of dimensionality” in machine learning. To tackle this problem and pave the way for machine learning-aided precision medicine, we proposed a unified multi-task deep learning framework named OmiEmbed to capture biomedical information from high-dimensional omics data with the deep embedding and downstream task modules. The deep embedding module learnt an omics embedding that mapped multiple omics data types into a latent space with lower dimensionality. Based on the new representation of multi-omics data, different downstream task modules were trained simultaneously and efficiently with the multi-task strategy to predict the comprehensive phenotype profile of each sample. OmiEmbed supports multiple tasks for omics data including dimensionality reduction, tumour type classification, multi-omics integration, demographic and clinical feature reconstruction, and survival prediction. The framework outperformed other methods on all three types of downstream tasks and achieved better performance with the multi-task strategy compared to training them individually. OmiEmbed is a powerful and unified framework that can be widely adapted to various applications of high-dimensional omics data and has great potential to facilitate more accurate and personalised clinical decision making. MDPI 2021-06-18 /pmc/articles/PMC8235477/ /pubmed/34207255 http://dx.doi.org/10.3390/cancers13123047 Text en © 2021 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 Article
Zhang, Xiaoyu
Xing, Yuting
Sun, Kai
Guo, Yike
OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
title OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
title_full OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
title_fullStr OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
title_full_unstemmed OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
title_short OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
title_sort omiembed: a unified multi-task deep learning framework for multi-omics data
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8235477/
https://www.ncbi.nlm.nih.gov/pubmed/34207255
http://dx.doi.org/10.3390/cancers13123047
work_keys_str_mv AT zhangxiaoyu omiembedaunifiedmultitaskdeeplearningframeworkformultiomicsdata
AT xingyuting omiembedaunifiedmultitaskdeeplearningframeworkformultiomicsdata
AT sunkai omiembedaunifiedmultitaskdeeplearningframeworkformultiomicsdata
AT guoyike omiembedaunifiedmultitaskdeeplearningframeworkformultiomicsdata