Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning
BackgroundThe presence of lymph node metastasis leads to a poor prognosis for prostate cancer (Pca). Recently, many studies have indicated that gene signatures may be able to predict the status of lymph nodes. The purpose of this study is to probe and validate a new tool to predict lymph node metast...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2022.1084403/full |
| _version_ | 1797953980629778432 |
|---|---|
| author | Ping Xie Ping Xie Jesur Batur Xin An Musha Yasen Xuefeng Fu Lin Jia Yun Luo |
| author_facet | Ping Xie Ping Xie Jesur Batur Xin An Musha Yasen Xuefeng Fu Lin Jia Yun Luo |
| author_sort | Ping Xie |
| collection | DOAJ |
| description | BackgroundThe presence of lymph node metastasis leads to a poor prognosis for prostate cancer (Pca). Recently, many studies have indicated that gene signatures may be able to predict the status of lymph nodes. The purpose of this study is to probe and validate a new tool to predict lymph node metastasis (LNM) based on alternative splicing (AS).MethodsGene expression profiles and clinical information of prostate adenocarcinoma cohort were retrieved from The Cancer Genome Atlas (TCGA) database, and the corresponding RNA-seq splicing events profiles were obtained from the TCGA SpliceSeq. Limma package was used to identify the differentially expressed alternative splicing (DEAS) events between LNM and non-LNM groups. Eight machine learning classifiers were built to train with stratified five-fold cross-validation. SHAP values was used to explain the model.Results333 differentially expressed alternative splicing (DEAS) events were identified. Using correlation filter and the least absolute shrinkage and selection operator (LASSO) method, a 96 AS signature was identified that had favorable discrimination in the training set and validated in the validation set. The linear discriminant analysis (LDA) was the best classifier after 100 iterations of training. The LDA classifier was able to distinguish between LNM and non-LNM with an area under the receiver operating curve of 0.962 ± 0.026 in the training set (D1 = 351) and 0.953 in the validation set (D2 = 62). The decision curve analysis plot proved the clinical application of the AS-based model.ConclusionMachine learning combined with AS data could robustly distinguish between LNM and non-LNM in Pca. |
| first_indexed | 2024-04-10T23:10:32Z |
| format | Article |
| id | doaj.art-dc5a7cc99b164b8093cd68f41868e190 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-10T23:10:32Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-dc5a7cc99b164b8093cd68f41868e1902023-01-13T06:14:18ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-01-011210.3389/fonc.2022.10844031084403Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learningPing Xie0Ping Xie1Jesur Batur2Xin An3Musha Yasen4Xuefeng Fu5Lin Jia6Yun Luo7Department of Urology, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, ChinaDepartment of Urology, The First People’s Hospital of Kashi Prefecture, Kashi, Xinjiang, ChinaDepartment of Urology, The First People’s Hospital of Kashi Prefecture, Kashi, Xinjiang, ChinaDepartment of Urology, The First People’s Hospital of Kashi Prefecture, Kashi, Xinjiang, ChinaDepartment of Urology, The First People’s Hospital of Kashi Prefecture, Kashi, Xinjiang, ChinaDepartment of Urology, The People's Hospital of Suining County, Xuzhou, Jiangsu, ChinaDepartment of Urology, The First People’s Hospital of Kashi Prefecture, Kashi, Xinjiang, ChinaDepartment of Urology, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, ChinaBackgroundThe presence of lymph node metastasis leads to a poor prognosis for prostate cancer (Pca). Recently, many studies have indicated that gene signatures may be able to predict the status of lymph nodes. The purpose of this study is to probe and validate a new tool to predict lymph node metastasis (LNM) based on alternative splicing (AS).MethodsGene expression profiles and clinical information of prostate adenocarcinoma cohort were retrieved from The Cancer Genome Atlas (TCGA) database, and the corresponding RNA-seq splicing events profiles were obtained from the TCGA SpliceSeq. Limma package was used to identify the differentially expressed alternative splicing (DEAS) events between LNM and non-LNM groups. Eight machine learning classifiers were built to train with stratified five-fold cross-validation. SHAP values was used to explain the model.Results333 differentially expressed alternative splicing (DEAS) events were identified. Using correlation filter and the least absolute shrinkage and selection operator (LASSO) method, a 96 AS signature was identified that had favorable discrimination in the training set and validated in the validation set. The linear discriminant analysis (LDA) was the best classifier after 100 iterations of training. The LDA classifier was able to distinguish between LNM and non-LNM with an area under the receiver operating curve of 0.962 ± 0.026 in the training set (D1 = 351) and 0.953 in the validation set (D2 = 62). The decision curve analysis plot proved the clinical application of the AS-based model.ConclusionMachine learning combined with AS data could robustly distinguish between LNM and non-LNM in Pca.https://www.frontiersin.org/articles/10.3389/fonc.2022.1084403/fullalternative splicing (AS)prostate cancerlymph node metastasisTCGAmachine learning |
| spellingShingle | Ping Xie Ping Xie Jesur Batur Xin An Musha Yasen Xuefeng Fu Lin Jia Yun Luo Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning Frontiers in Oncology alternative splicing (AS) prostate cancer lymph node metastasis TCGA machine learning |
| title | Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning |
| title_full | Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning |
| title_fullStr | Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning |
| title_full_unstemmed | Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning |
| title_short | Novel, alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning |
| title_sort | novel alternative splicing signature to detect lymph node metastasis in prostate adenocarcinoma with machine learning |
| topic | alternative splicing (AS) prostate cancer lymph node metastasis TCGA machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2022.1084403/full |
| work_keys_str_mv | AT pingxie novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT pingxie novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT jesurbatur novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT xinan novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT mushayasen novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT xuefengfu novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT linjia novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning AT yunluo novelalternativesplicingsignaturetodetectlymphnodemetastasisinprostateadenocarcinomawithmachinelearning |