Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders
Genomics data provide great opportunities for translational research and the clinical practice, for example, for predicting disease stages. However, the classification of such data is a challenging task due to their high dimensionality, noise, and heterogeneity. In recent years, deep learning classi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-07-01
|
| Series: | FEBS Open Bio |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/2211-5463.12652 |
| _version_ | 1797681630703255552 |
|---|---|
| author | Johannes Smolander Matthias Dehmer Frank Emmert‐Streib |
| author_facet | Johannes Smolander Matthias Dehmer Frank Emmert‐Streib |
| author_sort | Johannes Smolander |
| collection | DOAJ |
| description | Genomics data provide great opportunities for translational research and the clinical practice, for example, for predicting disease stages. However, the classification of such data is a challenging task due to their high dimensionality, noise, and heterogeneity. In recent years, deep learning classifiers generated much interest, but due to their complexity, so far, little is known about the utility of this method for genomics. In this paper, we address this problem by studying a computational diagnostics task by classification of breast cancer and inflammatory bowel disease patients based on high‐dimensional gene expression data. We provide a comprehensive analysis of the classification performance of deep belief networks (DBNs) in dependence on its multiple model parameters and in comparison with support vector machines (SVMs). Furthermore, we investigate combined classifiers that integrate DBNs with SVMs. Such a classifier utilizes a DBN as representation learner forming the input for a SVM. Overall, our results provide guidelines for the complex usage of DBN for classifying gene expression data from complex diseases. |
| first_indexed | 2024-03-11T23:47:39Z |
| format | Article |
| id | doaj.art-109a41c78f67404eb85d12e8f50db7a2 |
| institution | Directory Open Access Journal |
| issn | 2211-5463 |
| language | English |
| last_indexed | 2024-03-11T23:47:39Z |
| publishDate | 2019-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | FEBS Open Bio |
| spelling | doaj.art-109a41c78f67404eb85d12e8f50db7a22023-09-19T08:50:32ZengWileyFEBS Open Bio2211-54632019-07-01971232124810.1002/2211-5463.12652Comparing deep belief networks with support vector machines for classifying gene expression data from complex disordersJohannes Smolander0Matthias Dehmer1Frank Emmert‐Streib2Predictive Society and Data Analytics Lab Faculty of Information Technology and Communication Sciences Tampere University FinlandInstitute for Intelligent Production Faculty for Management University of Applied Sciences Upper Austria Steyr AustriaPredictive Society and Data Analytics Lab Faculty of Information Technology and Communication Sciences Tampere University FinlandGenomics data provide great opportunities for translational research and the clinical practice, for example, for predicting disease stages. However, the classification of such data is a challenging task due to their high dimensionality, noise, and heterogeneity. In recent years, deep learning classifiers generated much interest, but due to their complexity, so far, little is known about the utility of this method for genomics. In this paper, we address this problem by studying a computational diagnostics task by classification of breast cancer and inflammatory bowel disease patients based on high‐dimensional gene expression data. We provide a comprehensive analysis of the classification performance of deep belief networks (DBNs) in dependence on its multiple model parameters and in comparison with support vector machines (SVMs). Furthermore, we investigate combined classifiers that integrate DBNs with SVMs. Such a classifier utilizes a DBN as representation learner forming the input for a SVM. Overall, our results provide guidelines for the complex usage of DBN for classifying gene expression data from complex diseases.https://doi.org/10.1002/2211-5463.12652artificial intelligencedeep belief networkdeep learninggenomicsneural networkssupport vector machine |
| spellingShingle | Johannes Smolander Matthias Dehmer Frank Emmert‐Streib Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders FEBS Open Bio artificial intelligence deep belief network deep learning genomics neural networks support vector machine |
| title | Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders |
| title_full | Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders |
| title_fullStr | Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders |
| title_full_unstemmed | Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders |
| title_short | Comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders |
| title_sort | comparing deep belief networks with support vector machines for classifying gene expression data from complex disorders |
| topic | artificial intelligence deep belief network deep learning genomics neural networks support vector machine |
| url | https://doi.org/10.1002/2211-5463.12652 |
| work_keys_str_mv | AT johannessmolander comparingdeepbeliefnetworkswithsupportvectormachinesforclassifyinggeneexpressiondatafromcomplexdisorders AT matthiasdehmer comparingdeepbeliefnetworkswithsupportvectormachinesforclassifyinggeneexpressiondatafromcomplexdisorders AT frankemmertstreib comparingdeepbeliefnetworkswithsupportvectormachinesforclassifyinggeneexpressiondatafromcomplexdisorders |