A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer
Purpose: There is a lack of tools for identifying the site of origin in mucinous cancer. This study aimed to evaluate the performance of a transcriptome-based classifier for identifying the site of origin in mucinous cancer. Materials And Methods: Transcriptomic data of 1878 non-mucinous and 82 muci...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2022-11-01
|
| Series: | Cancer Informatics |
| Online Access: | https://doi.org/10.1177/11769351221135141 |
| _version_ | 1811313273977438208 |
|---|---|
| author | Taejin Ahn Kidong Kim Hyojin Kim Sarah Kim Sangick Park Kyoungbun Lee |
| author_facet | Taejin Ahn Kidong Kim Hyojin Kim Sarah Kim Sangick Park Kyoungbun Lee |
| author_sort | Taejin Ahn |
| collection | DOAJ |
| description | Purpose: There is a lack of tools for identifying the site of origin in mucinous cancer. This study aimed to evaluate the performance of a transcriptome-based classifier for identifying the site of origin in mucinous cancer. Materials And Methods: Transcriptomic data of 1878 non-mucinous and 82 mucinous cancer specimens, with 7 sites of origin, namely, the uterine cervix (CESC), colon (COAD), pancreas (PAAD), stomach (STAD), uterine endometrium (UCEC), uterine carcinosarcoma (UCS), and ovary (OV), obtained from The Cancer Genome Atlas, were used as the training and validation sets, respectively. Transcriptomic data of 14 mucinous cancer specimens from a tissue archive were used as the test set. For identifying the site of origin, a set of 100 differentially expressed genes for each site of origin was selected. After removing multiple iterations of the same gene, 427 genes were chosen, and their RNA expression profiles, at each site of origin, were used to train the deep neural network classifier. The performance of the classifier was estimated using the training, validation, and test sets. Results: The accuracy of the model in the training set was 0.998, while that in the validation set was 0.939 (77/82). In the test set which is newly sequenced from a tissue archive, the model showed an accuracy of 0.857 (12/14). t-SNE analysis revealed that samples in the test set were part of the clusters obtained for the training set. Conclusion: Although limited by small sample size, we showed that a transcriptome-based classifier could correctly identify the site of origin of mucinous cancer. |
| first_indexed | 2024-04-13T10:51:57Z |
| format | Article |
| id | doaj.art-12687f2cd1fd4788913db132956d84c0 |
| institution | Directory Open Access Journal |
| issn | 1176-9351 |
| language | English |
| last_indexed | 2024-04-13T10:51:57Z |
| publishDate | 2022-11-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Cancer Informatics |
| spelling | doaj.art-12687f2cd1fd4788913db132956d84c02022-12-22T02:49:38ZengSAGE PublishingCancer Informatics1176-93512022-11-012110.1177/11769351221135141A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous CancerTaejin Ahn0Kidong Kim1Hyojin Kim2Sarah Kim3Sangick Park4Kyoungbun Lee5Department of Life Science, Handong Global University, Pohang, Republic of KoreaDepartment of Obstetrics and Gynecology, Seoul National University Bundang Hospital, Seongnam, Republic of KoreaDepartment of Pathology, Seoul National University Bundang Hospital, Seongnam, Republic of KoreaDepartment of Life Science, Handong Global University, Pohang, Republic of KoreaDepartment of Life Science, Handong Global University, Pohang, Republic of KoreaDepartment of Pathology, Seoul National University Hospital, Seoul, Republic of KoreaPurpose: There is a lack of tools for identifying the site of origin in mucinous cancer. This study aimed to evaluate the performance of a transcriptome-based classifier for identifying the site of origin in mucinous cancer. Materials And Methods: Transcriptomic data of 1878 non-mucinous and 82 mucinous cancer specimens, with 7 sites of origin, namely, the uterine cervix (CESC), colon (COAD), pancreas (PAAD), stomach (STAD), uterine endometrium (UCEC), uterine carcinosarcoma (UCS), and ovary (OV), obtained from The Cancer Genome Atlas, were used as the training and validation sets, respectively. Transcriptomic data of 14 mucinous cancer specimens from a tissue archive were used as the test set. For identifying the site of origin, a set of 100 differentially expressed genes for each site of origin was selected. After removing multiple iterations of the same gene, 427 genes were chosen, and their RNA expression profiles, at each site of origin, were used to train the deep neural network classifier. The performance of the classifier was estimated using the training, validation, and test sets. Results: The accuracy of the model in the training set was 0.998, while that in the validation set was 0.939 (77/82). In the test set which is newly sequenced from a tissue archive, the model showed an accuracy of 0.857 (12/14). t-SNE analysis revealed that samples in the test set were part of the clusters obtained for the training set. Conclusion: Although limited by small sample size, we showed that a transcriptome-based classifier could correctly identify the site of origin of mucinous cancer.https://doi.org/10.1177/11769351221135141 |
| spellingShingle | Taejin Ahn Kidong Kim Hyojin Kim Sarah Kim Sangick Park Kyoungbun Lee A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer Cancer Informatics |
| title | A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer |
| title_full | A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer |
| title_fullStr | A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer |
| title_full_unstemmed | A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer |
| title_short | A transcriptome-Based Deep Neural Network Classifier for Identifying the Site of Origin in Mucinous Cancer |
| title_sort | transcriptome based deep neural network classifier for identifying the site of origin in mucinous cancer |
| url | https://doi.org/10.1177/11769351221135141 |
| work_keys_str_mv | AT taejinahn atranscriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT kidongkim atranscriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT hyojinkim atranscriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT sarahkim atranscriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT sangickpark atranscriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT kyoungbunlee atranscriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT taejinahn transcriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT kidongkim transcriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT hyojinkim transcriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT sarahkim transcriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT sangickpark transcriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer AT kyoungbunlee transcriptomebaseddeepneuralnetworkclassifierforidentifyingthesiteoforigininmucinouscancer |