Cargando…
Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer
BACKGROUND: Contemporary deep learning approaches show cutting-edge performance in a variety of complex prediction tasks. Nonetheless, the application of deep learning in healthcare remains limited since deep learning methods are often considered as non-interpretable black-box models. However, the m...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7953710/ https://www.ncbi.nlm.nih.gov/pubmed/33706810 http://dx.doi.org/10.1186/s13073-021-00845-7 |
_version_ | 1783663969039286272 |
---|---|
author | Chereda, Hryhorii Bleckmann, Annalen Menck, Kerstin Perera-Bel, Júlia Stegmaier, Philip Auer, Florian Kramer, Frank Leha, Andreas Beißbarth, Tim |
author_facet | Chereda, Hryhorii Bleckmann, Annalen Menck, Kerstin Perera-Bel, Júlia Stegmaier, Philip Auer, Florian Kramer, Frank Leha, Andreas Beißbarth, Tim |
author_sort | Chereda, Hryhorii |
collection | PubMed |
description | BACKGROUND: Contemporary deep learning approaches show cutting-edge performance in a variety of complex prediction tasks. Nonetheless, the application of deep learning in healthcare remains limited since deep learning methods are often considered as non-interpretable black-box models. However, the machine learning community made recent elaborations on interpretability methods explaining data point-specific decisions of deep learning techniques. We believe that such explanations can assist the need in personalized precision medicine decisions via explaining patient-specific predictions. METHODS: Layer-wise Relevance Propagation (LRP) is a technique to explain decisions of deep learning methods. It is widely used to interpret Convolutional Neural Networks (CNNs) applied on image data. Recently, CNNs started to extend towards non-Euclidean domains like graphs. Molecular networks are commonly represented as graphs detailing interactions between molecules. Gene expression data can be assigned to the vertices of these graphs. In other words, gene expression data can be structured by utilizing molecular network information as prior knowledge. Graph-CNNs can be applied to structured gene expression data, for example, to predict metastatic events in breast cancer. Therefore, there is a need for explanations showing which part of a molecular network is relevant for predicting an event, e.g., distant metastasis in cancer, for each individual patient. RESULTS: We extended the procedure of LRP to make it available for Graph-CNN and tested its applicability on a large breast cancer dataset. We present Graph Layer-wise Relevance Propagation (GLRP) as a new method to explain the decisions made by Graph-CNNs. We demonstrate a sanity check of the developed GLRP on a hand-written digits dataset and then apply the method on gene expression data. We show that GLRP provides patient-specific molecular subnetworks that largely agree with clinical knowledge and identify common as well as novel, and potentially druggable, drivers of tumor progression. CONCLUSIONS: The developed method could be potentially highly useful on interpreting classification results in the context of different omics data and prior knowledge molecular networks on the individual patient level, as for example in precision medicine approaches or a molecular tumor board. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at (10.1186/s13073-021-00845-7). |
format | Online Article Text |
id | pubmed-7953710 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-79537102021-03-12 Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer Chereda, Hryhorii Bleckmann, Annalen Menck, Kerstin Perera-Bel, Júlia Stegmaier, Philip Auer, Florian Kramer, Frank Leha, Andreas Beißbarth, Tim Genome Med Research BACKGROUND: Contemporary deep learning approaches show cutting-edge performance in a variety of complex prediction tasks. Nonetheless, the application of deep learning in healthcare remains limited since deep learning methods are often considered as non-interpretable black-box models. However, the machine learning community made recent elaborations on interpretability methods explaining data point-specific decisions of deep learning techniques. We believe that such explanations can assist the need in personalized precision medicine decisions via explaining patient-specific predictions. METHODS: Layer-wise Relevance Propagation (LRP) is a technique to explain decisions of deep learning methods. It is widely used to interpret Convolutional Neural Networks (CNNs) applied on image data. Recently, CNNs started to extend towards non-Euclidean domains like graphs. Molecular networks are commonly represented as graphs detailing interactions between molecules. Gene expression data can be assigned to the vertices of these graphs. In other words, gene expression data can be structured by utilizing molecular network information as prior knowledge. Graph-CNNs can be applied to structured gene expression data, for example, to predict metastatic events in breast cancer. Therefore, there is a need for explanations showing which part of a molecular network is relevant for predicting an event, e.g., distant metastasis in cancer, for each individual patient. RESULTS: We extended the procedure of LRP to make it available for Graph-CNN and tested its applicability on a large breast cancer dataset. We present Graph Layer-wise Relevance Propagation (GLRP) as a new method to explain the decisions made by Graph-CNNs. We demonstrate a sanity check of the developed GLRP on a hand-written digits dataset and then apply the method on gene expression data. We show that GLRP provides patient-specific molecular subnetworks that largely agree with clinical knowledge and identify common as well as novel, and potentially druggable, drivers of tumor progression. CONCLUSIONS: The developed method could be potentially highly useful on interpreting classification results in the context of different omics data and prior knowledge molecular networks on the individual patient level, as for example in precision medicine approaches or a molecular tumor board. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at (10.1186/s13073-021-00845-7). BioMed Central 2021-03-11 /pmc/articles/PMC7953710/ /pubmed/33706810 http://dx.doi.org/10.1186/s13073-021-00845-7 Text en © The Author(s) 2021 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data. |
spellingShingle | Research Chereda, Hryhorii Bleckmann, Annalen Menck, Kerstin Perera-Bel, Júlia Stegmaier, Philip Auer, Florian Kramer, Frank Leha, Andreas Beißbarth, Tim Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
title | Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
title_full | Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
title_fullStr | Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
title_full_unstemmed | Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
title_short | Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
title_sort | explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7953710/ https://www.ncbi.nlm.nih.gov/pubmed/33706810 http://dx.doi.org/10.1186/s13073-021-00845-7 |
work_keys_str_mv | AT cheredahryhorii explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT bleckmannannalen explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT menckkerstin explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT pererabeljulia explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT stegmaierphilip explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT auerflorian explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT kramerfrank explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT lehaandreas explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer AT beißbarthtim explainingdecisionsofgraphconvolutionalneuralnetworkspatientspecificmolecularsubnetworksresponsibleformetastasispredictioninbreastcancer |