Biological interpretation of deep neural network for phenotype prediction based on gene expression
Abstract Background The use of predictive gene signatures to assist clinical decision is becoming more and more important. Deep learning has a huge potential in the prediction of phenotype from gene expression profiles. However, neural networks are viewed as black boxes, where accurate predictions a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-11-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-020-03836-4 |
| _version_ | 1818217186832941056 |
|---|---|
| author | Blaise Hanczar Farida Zehraoui Tina Issa Mathieu Arles |
| author_facet | Blaise Hanczar Farida Zehraoui Tina Issa Mathieu Arles |
| author_sort | Blaise Hanczar |
| collection | DOAJ |
| description | Abstract Background The use of predictive gene signatures to assist clinical decision is becoming more and more important. Deep learning has a huge potential in the prediction of phenotype from gene expression profiles. However, neural networks are viewed as black boxes, where accurate predictions are provided without any explanation. The requirements for these models to become interpretable are increasing, especially in the medical field. Results We focus on explaining the predictions of a deep neural network model built from gene expression data. The most important neurons and genes influencing the predictions are identified and linked to biological knowledge. Our experiments on cancer prediction show that: (1) deep learning approach outperforms classical machine learning methods on large training sets; (2) our approach produces interpretations more coherent with biology than the state-of-the-art based approaches; (3) we can provide a comprehensive explanation of the predictions for biologists and physicians. Conclusion We propose an original approach for biological interpretation of deep learning models for phenotype prediction from gene expression data. Since the model can find relationships between the phenotype and gene expression, we may assume that there is a link between the identified genes and the phenotype. The interpretation can, therefore, lead to new biological hypotheses to be investigated by biologists. |
| first_indexed | 2024-12-12T07:03:52Z |
| format | Article |
| id | doaj.art-ec4f16e81c0747e2b686def3e4bc6503 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-12T07:03:52Z |
| publishDate | 2020-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-ec4f16e81c0747e2b686def3e4bc65032022-12-22T00:33:47ZengBMCBMC Bioinformatics1471-21052020-11-0121111810.1186/s12859-020-03836-4Biological interpretation of deep neural network for phenotype prediction based on gene expressionBlaise Hanczar0Farida Zehraoui1Tina Issa2Mathieu Arles3IBISC, Univ Evry, Université Paris-SaclayIBISC, Univ Evry, Université Paris-SaclayIBISC, Univ Evry, Université Paris-SaclayIBISC, Univ Evry, Université Paris-SaclayAbstract Background The use of predictive gene signatures to assist clinical decision is becoming more and more important. Deep learning has a huge potential in the prediction of phenotype from gene expression profiles. However, neural networks are viewed as black boxes, where accurate predictions are provided without any explanation. The requirements for these models to become interpretable are increasing, especially in the medical field. Results We focus on explaining the predictions of a deep neural network model built from gene expression data. The most important neurons and genes influencing the predictions are identified and linked to biological knowledge. Our experiments on cancer prediction show that: (1) deep learning approach outperforms classical machine learning methods on large training sets; (2) our approach produces interpretations more coherent with biology than the state-of-the-art based approaches; (3) we can provide a comprehensive explanation of the predictions for biologists and physicians. Conclusion We propose an original approach for biological interpretation of deep learning models for phenotype prediction from gene expression data. Since the model can find relationships between the phenotype and gene expression, we may assume that there is a link between the identified genes and the phenotype. The interpretation can, therefore, lead to new biological hypotheses to be investigated by biologists.http://link.springer.com/article/10.1186/s12859-020-03836-4Deep neural networkBiological interpretationPhenotype prediction |
| spellingShingle | Blaise Hanczar Farida Zehraoui Tina Issa Mathieu Arles Biological interpretation of deep neural network for phenotype prediction based on gene expression BMC Bioinformatics Deep neural network Biological interpretation Phenotype prediction |
| title | Biological interpretation of deep neural network for phenotype prediction based on gene expression |
| title_full | Biological interpretation of deep neural network for phenotype prediction based on gene expression |
| title_fullStr | Biological interpretation of deep neural network for phenotype prediction based on gene expression |
| title_full_unstemmed | Biological interpretation of deep neural network for phenotype prediction based on gene expression |
| title_short | Biological interpretation of deep neural network for phenotype prediction based on gene expression |
| title_sort | biological interpretation of deep neural network for phenotype prediction based on gene expression |
| topic | Deep neural network Biological interpretation Phenotype prediction |
| url | http://link.springer.com/article/10.1186/s12859-020-03836-4 |
| work_keys_str_mv | AT blaisehanczar biologicalinterpretationofdeepneuralnetworkforphenotypepredictionbasedongeneexpression AT faridazehraoui biologicalinterpretationofdeepneuralnetworkforphenotypepredictionbasedongeneexpression AT tinaissa biologicalinterpretationofdeepneuralnetworkforphenotypepredictionbasedongeneexpression AT mathieuarles biologicalinterpretationofdeepneuralnetworkforphenotypepredictionbasedongeneexpression |