Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models
The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for buildin...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Genes |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4425/11/9/1070 |
| _version_ | 1797553960187330560 |
|---|---|
| author | Yitan Zhu Thomas Brettin Yvonne A. Evrard Fangfang Xia Alexander Partin Maulik Shukla Hyunseung Yoo James H. Doroshow Rick L. Stevens |
| author_facet | Yitan Zhu Thomas Brettin Yvonne A. Evrard Fangfang Xia Alexander Partin Maulik Shukla Hyunseung Yoo James H. Doroshow Rick L. Stevens |
| author_sort | Yitan Zhu |
| collection | DOAJ |
| description | The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted <i>p</i>-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response. |
| first_indexed | 2024-03-10T16:24:03Z |
| format | Article |
| id | doaj.art-f570a1ee7ea043d590d13caa602f2955 |
| institution | Directory Open Access Journal |
| issn | 2073-4425 |
| language | English |
| last_indexed | 2024-03-10T16:24:03Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Genes |
| spelling | doaj.art-f570a1ee7ea043d590d13caa602f29552023-11-20T13:28:44ZengMDPI AGGenes2073-44252020-09-01119107010.3390/genes11091070Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction ModelsYitan Zhu0Thomas Brettin1Yvonne A. Evrard2Fangfang Xia3Alexander Partin4Maulik Shukla5Hyunseung Yoo6James H. Doroshow7Rick L. Stevens8Computing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USAComputing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USALeidos Biomedical Research, National Laboratory for Cancer Research, Inc. Frederick, Frederick, MD 21702, USAComputing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USAComputing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USAComputing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USAComputing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USADevelopmental Therapeutics Branch, National Cancer Institute, Bethesda, MD 20892, USAComputing, Environment and Life Sciences, Argonne National Laboratory, Lemont, IL 60439, USAThe co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted <i>p</i>-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response.https://www.mdpi.com/2073-4425/11/9/1070general drug response prediction modelgene selectionco-expression extrapolation (COXEN)precision oncology |
| spellingShingle | Yitan Zhu Thomas Brettin Yvonne A. Evrard Fangfang Xia Alexander Partin Maulik Shukla Hyunseung Yoo James H. Doroshow Rick L. Stevens Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models Genes general drug response prediction model gene selection co-expression extrapolation (COXEN) precision oncology |
| title | Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models |
| title_full | Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models |
| title_fullStr | Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models |
| title_full_unstemmed | Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models |
| title_short | Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models |
| title_sort | enhanced co expression extrapolation coxen gene selection method for building anti cancer drug response prediction models |
| topic | general drug response prediction model gene selection co-expression extrapolation (COXEN) precision oncology |
| url | https://www.mdpi.com/2073-4425/11/9/1070 |
| work_keys_str_mv | AT yitanzhu enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT thomasbrettin enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT yvonneaevrard enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT fangfangxia enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT alexanderpartin enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT maulikshukla enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT hyunseungyoo enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT jameshdoroshow enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels AT ricklstevens enhancedcoexpressionextrapolationcoxengeneselectionmethodforbuildinganticancerdrugresponsepredictionmodels |