Cargando…

HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development

The prediction of response to drugs before initiating therapy based on transcriptome data is a major challenge. However, identifying effective drug response label data costs time and resources. Methods available often predict poorly and fail to identify robust biomarkers due to the curse of dimensio...

Descripción completa

Detalles Bibliográficos
Autores principales: Huang, Yue, Rong, Zhiwei, Zhang, Liuchao, Xu, Zhenyi, Ji, Jianxin, He, Jia, Liu, Weisha, Hou, Yan, Li, Kang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9909422/
https://www.ncbi.nlm.nih.gov/pubmed/36776339
http://dx.doi.org/10.3389/fonc.2023.1047556
_version_ 1784884573705863168
author Huang, Yue
Rong, Zhiwei
Zhang, Liuchao
Xu, Zhenyi
Ji, Jianxin
He, Jia
Liu, Weisha
Hou, Yan
Li, Kang
author_facet Huang, Yue
Rong, Zhiwei
Zhang, Liuchao
Xu, Zhenyi
Ji, Jianxin
He, Jia
Liu, Weisha
Hou, Yan
Li, Kang
author_sort Huang, Yue
collection PubMed
description The prediction of response to drugs before initiating therapy based on transcriptome data is a major challenge. However, identifying effective drug response label data costs time and resources. Methods available often predict poorly and fail to identify robust biomarkers due to the curse of dimensionality: high dimensionality and low sample size. Therefore, this necessitates the development of predictive models to effectively predict the response to drugs using limited labeled data while being interpretable. In this study, we report a novel Hierarchical Graph Random Neural Networks (HiRAND) framework to predict the drug response using transcriptome data of few labeled data and additional unlabeled data. HiRAND completes the information integration of the gene graph and sample graph by graph convolutional network (GCN). The innovation of our model is leveraging data augmentation strategy to solve the dilemma of limited labeled data and using consistency regularization to optimize the prediction consistency of unlabeled data across different data augmentations. The results showed that HiRAND achieved better performance than competitive methods in various prediction scenarios, including both simulation data and multiple drug response data. We found that the prediction ability of HiRAND in the drug vorinostat showed the best results across all 62 drugs. In addition, HiRAND was interpreted to identify the key genes most important to vorinostat response, highlighting critical roles for ribosomal protein-related genes in the response to histone deacetylase inhibition. Our HiRAND could be utilized as an efficient framework for improving the drug response prediction performance using few labeled data.
format Online
Article
Text
id pubmed-9909422
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-99094222023-02-10 HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development Huang, Yue Rong, Zhiwei Zhang, Liuchao Xu, Zhenyi Ji, Jianxin He, Jia Liu, Weisha Hou, Yan Li, Kang Front Oncol Oncology The prediction of response to drugs before initiating therapy based on transcriptome data is a major challenge. However, identifying effective drug response label data costs time and resources. Methods available often predict poorly and fail to identify robust biomarkers due to the curse of dimensionality: high dimensionality and low sample size. Therefore, this necessitates the development of predictive models to effectively predict the response to drugs using limited labeled data while being interpretable. In this study, we report a novel Hierarchical Graph Random Neural Networks (HiRAND) framework to predict the drug response using transcriptome data of few labeled data and additional unlabeled data. HiRAND completes the information integration of the gene graph and sample graph by graph convolutional network (GCN). The innovation of our model is leveraging data augmentation strategy to solve the dilemma of limited labeled data and using consistency regularization to optimize the prediction consistency of unlabeled data across different data augmentations. The results showed that HiRAND achieved better performance than competitive methods in various prediction scenarios, including both simulation data and multiple drug response data. We found that the prediction ability of HiRAND in the drug vorinostat showed the best results across all 62 drugs. In addition, HiRAND was interpreted to identify the key genes most important to vorinostat response, highlighting critical roles for ribosomal protein-related genes in the response to histone deacetylase inhibition. Our HiRAND could be utilized as an efficient framework for improving the drug response prediction performance using few labeled data. Frontiers Media S.A. 2023-01-26 /pmc/articles/PMC9909422/ /pubmed/36776339 http://dx.doi.org/10.3389/fonc.2023.1047556 Text en Copyright © 2023 Huang, Rong, Zhang, Xu, Ji, He, Liu, Hou and Li https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Huang, Yue
Rong, Zhiwei
Zhang, Liuchao
Xu, Zhenyi
Ji, Jianxin
He, Jia
Liu, Weisha
Hou, Yan
Li, Kang
HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development
title HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development
title_full HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development
title_fullStr HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development
title_full_unstemmed HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development
title_short HiRAND: A novel GCN semi-supervised deep learning-based framework for classification and feature selection in drug research and development
title_sort hirand: a novel gcn semi-supervised deep learning-based framework for classification and feature selection in drug research and development
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9909422/
https://www.ncbi.nlm.nih.gov/pubmed/36776339
http://dx.doi.org/10.3389/fonc.2023.1047556
work_keys_str_mv AT huangyue hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT rongzhiwei hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT zhangliuchao hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT xuzhenyi hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT jijianxin hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT hejia hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT liuweisha hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT houyan hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment
AT likang hirandanovelgcnsemisuperviseddeeplearningbasedframeworkforclassificationandfeatureselectionindrugresearchanddevelopment