Cargando…

Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data

Building an accurate disease risk prediction model is an essential step in the modern quest for precision medicine. While high-dimensional genomic data provides valuable data resources for the investigations of disease risk, their huge amount of noise and complex relationships between predictors and...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Long, Meng, Qingyu, Weng, Cherry, Lu, Qing, Wang, Tong, Wen, Yalu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9328574/
https://www.ncbi.nlm.nih.gov/pubmed/35839250
http://dx.doi.org/10.1371/journal.pcbi.1010328
_version_ 1784757751884283904
author Liu, Long
Meng, Qingyu
Weng, Cherry
Lu, Qing
Wang, Tong
Wen, Yalu
author_facet Liu, Long
Meng, Qingyu
Weng, Cherry
Lu, Qing
Wang, Tong
Wen, Yalu
author_sort Liu, Long
collection PubMed
description Building an accurate disease risk prediction model is an essential step in the modern quest for precision medicine. While high-dimensional genomic data provides valuable data resources for the investigations of disease risk, their huge amount of noise and complex relationships between predictors and outcomes have brought tremendous analytical challenges. Deep learning model is the state-of-the-art methods for many prediction tasks, and it is a promising framework for the analysis of genomic data. However, deep learning models generally suffer from the curse of dimensionality and the lack of biological interpretability, both of which have greatly limited their applications. In this work, we have developed a deep neural network (DNN) based prediction modeling framework. We first proposed a group-wise feature importance score for feature selection, where genes harboring genetic variants with both linear and non-linear effects are efficiently detected. We then designed an explainable transfer-learning based DNN method, which can directly incorporate information from feature selection and accurately capture complex predictive effects. The proposed DNN-framework is biologically interpretable, as it is built based on the selected predictive genes. It is also computationally efficient and can be applied to genome-wide data. Through extensive simulations and real data analyses, we have demonstrated that our proposed method can not only efficiently detect predictive features, but also accurately predict disease risk, as compared to many existing methods.
format Online
Article
Text
id pubmed-9328574
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-93285742022-07-28 Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data Liu, Long Meng, Qingyu Weng, Cherry Lu, Qing Wang, Tong Wen, Yalu PLoS Comput Biol Research Article Building an accurate disease risk prediction model is an essential step in the modern quest for precision medicine. While high-dimensional genomic data provides valuable data resources for the investigations of disease risk, their huge amount of noise and complex relationships between predictors and outcomes have brought tremendous analytical challenges. Deep learning model is the state-of-the-art methods for many prediction tasks, and it is a promising framework for the analysis of genomic data. However, deep learning models generally suffer from the curse of dimensionality and the lack of biological interpretability, both of which have greatly limited their applications. In this work, we have developed a deep neural network (DNN) based prediction modeling framework. We first proposed a group-wise feature importance score for feature selection, where genes harboring genetic variants with both linear and non-linear effects are efficiently detected. We then designed an explainable transfer-learning based DNN method, which can directly incorporate information from feature selection and accurately capture complex predictive effects. The proposed DNN-framework is biologically interpretable, as it is built based on the selected predictive genes. It is also computationally efficient and can be applied to genome-wide data. Through extensive simulations and real data analyses, we have demonstrated that our proposed method can not only efficiently detect predictive features, but also accurately predict disease risk, as compared to many existing methods. Public Library of Science 2022-07-15 /pmc/articles/PMC9328574/ /pubmed/35839250 http://dx.doi.org/10.1371/journal.pcbi.1010328 Text en © 2022 Liu et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Liu, Long
Meng, Qingyu
Weng, Cherry
Lu, Qing
Wang, Tong
Wen, Yalu
Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
title Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
title_full Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
title_fullStr Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
title_full_unstemmed Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
title_short Explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
title_sort explainable deep transfer learning model for disease risk prediction using high-dimensional genomic data
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9328574/
https://www.ncbi.nlm.nih.gov/pubmed/35839250
http://dx.doi.org/10.1371/journal.pcbi.1010328
work_keys_str_mv AT liulong explainabledeeptransferlearningmodelfordiseaseriskpredictionusinghighdimensionalgenomicdata
AT mengqingyu explainabledeeptransferlearningmodelfordiseaseriskpredictionusinghighdimensionalgenomicdata
AT wengcherry explainabledeeptransferlearningmodelfordiseaseriskpredictionusinghighdimensionalgenomicdata
AT luqing explainabledeeptransferlearningmodelfordiseaseriskpredictionusinghighdimensionalgenomicdata
AT wangtong explainabledeeptransferlearningmodelfordiseaseriskpredictionusinghighdimensionalgenomicdata
AT wenyalu explainabledeeptransferlearningmodelfordiseaseriskpredictionusinghighdimensionalgenomicdata