Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting
Abstract Background Genetics-based basket trials have emerged to test targeted therapeutics across multiple cancer types. However, while vemurafenib is FDA-approved for BRAF-V600E melanomas, the non-melanoma basket trial was unsuccessful, suggesting mutation status is insufficient to predict respons...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-10-01
|
| Series: | BMC Cancer |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12885-019-6175-2 |
| _version_ | 1828813363957727232 |
|---|---|
| author | Molly J. Carroll Carl R. Parent David Page Pamela K. Kreeger |
| author_facet | Molly J. Carroll Carl R. Parent David Page Pamela K. Kreeger |
| author_sort | Molly J. Carroll |
| collection | DOAJ |
| description | Abstract Background Genetics-based basket trials have emerged to test targeted therapeutics across multiple cancer types. However, while vemurafenib is FDA-approved for BRAF-V600E melanomas, the non-melanoma basket trial was unsuccessful, suggesting mutation status is insufficient to predict response. We hypothesized that proteomic data would complement mutation status to identify vemurafenib-sensitive tumors and effective co-treatments for BRAF-V600E tumors with inherent resistance. Methods Reverse Phase Proteomic Array (RPPA, MD Anderson Cell Lines Project), RNAseq (Cancer Cell Line Encyclopedia) and vemurafenib sensitivity (Cancer Therapeutic Response Portal) data for BRAF-V600E cancer cell lines were curated. Linear and nonlinear regression models using RPPA protein or RNAseq were evaluated and compared based on their ability to predict BRAF-V600E cell line sensitivity (area under the dose response curve). Accuracies of all models were evaluated using hold-out testing. CausalPath software was used to identify protein-protein interaction networks that could explain differential protein expression in resistant cells. Human examination of features employed by the model, the identified protein interaction networks, and model simulation suggested anti-ErbB co-therapy would counter intrinsic resistance to vemurafenib. To validate this potential co-therapy, cell lines were treated with vemurafenib and dacomitinib (a pan-ErbB inhibitor) and the number of viable cells was measured. Results Orthogonal partial least squares (O-PLS) predicted vemurafenib sensitivity with greater accuracy in both melanoma and non-melanoma BRAF-V600E cell lines than other leading machine learning methods, specifically Random Forests, Support Vector Regression (linear and quadratic kernels) and LASSO-penalized regression. Additionally, use of transcriptomic in place of proteomic data weakened model performance. Model analysis revealed that resistant lines had elevated expression and activation of ErbB receptors, suggesting ErbB inhibition could improve vemurafenib response. As predicted, experimental evaluation of vemurafenib plus dacomitinb demonstrated improved efficacy relative to monotherapies. Conclusions: Combined, our results support that inclusion of proteomics can predict drug response and identify co-therapies in a basket setting. |
| first_indexed | 2024-12-12T09:59:22Z |
| format | Article |
| id | doaj.art-a9fd937ff1a74cbaa05f6586c5d7dfb3 |
| institution | Directory Open Access Journal |
| issn | 1471-2407 |
| language | English |
| last_indexed | 2024-12-12T09:59:22Z |
| publishDate | 2019-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Cancer |
| spelling | doaj.art-a9fd937ff1a74cbaa05f6586c5d7dfb32022-12-22T00:28:02ZengBMCBMC Cancer1471-24072019-10-0119111310.1186/s12885-019-6175-2Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial settingMolly J. Carroll0Carl R. Parent1David Page2Pamela K. Kreeger3Department of Biomedical Engineering, University of Wisconsin-Madison 1111 Highland AveDepartment of Biomedical Engineering, University of Wisconsin-Madison 1111 Highland AveDepartment of Biostatistics and Bioinformatics, Duke UniversityDepartment of Biomedical Engineering, University of Wisconsin-Madison 1111 Highland AveAbstract Background Genetics-based basket trials have emerged to test targeted therapeutics across multiple cancer types. However, while vemurafenib is FDA-approved for BRAF-V600E melanomas, the non-melanoma basket trial was unsuccessful, suggesting mutation status is insufficient to predict response. We hypothesized that proteomic data would complement mutation status to identify vemurafenib-sensitive tumors and effective co-treatments for BRAF-V600E tumors with inherent resistance. Methods Reverse Phase Proteomic Array (RPPA, MD Anderson Cell Lines Project), RNAseq (Cancer Cell Line Encyclopedia) and vemurafenib sensitivity (Cancer Therapeutic Response Portal) data for BRAF-V600E cancer cell lines were curated. Linear and nonlinear regression models using RPPA protein or RNAseq were evaluated and compared based on their ability to predict BRAF-V600E cell line sensitivity (area under the dose response curve). Accuracies of all models were evaluated using hold-out testing. CausalPath software was used to identify protein-protein interaction networks that could explain differential protein expression in resistant cells. Human examination of features employed by the model, the identified protein interaction networks, and model simulation suggested anti-ErbB co-therapy would counter intrinsic resistance to vemurafenib. To validate this potential co-therapy, cell lines were treated with vemurafenib and dacomitinib (a pan-ErbB inhibitor) and the number of viable cells was measured. Results Orthogonal partial least squares (O-PLS) predicted vemurafenib sensitivity with greater accuracy in both melanoma and non-melanoma BRAF-V600E cell lines than other leading machine learning methods, specifically Random Forests, Support Vector Regression (linear and quadratic kernels) and LASSO-penalized regression. Additionally, use of transcriptomic in place of proteomic data weakened model performance. Model analysis revealed that resistant lines had elevated expression and activation of ErbB receptors, suggesting ErbB inhibition could improve vemurafenib response. As predicted, experimental evaluation of vemurafenib plus dacomitinb demonstrated improved efficacy relative to monotherapies. Conclusions: Combined, our results support that inclusion of proteomics can predict drug response and identify co-therapies in a basket setting.http://link.springer.com/article/10.1186/s12885-019-6175-2Reverse phase protein arrayOrthogonal partials least squaresProtein activityTargeted therapiesBRAF inhibitor |
| spellingShingle | Molly J. Carroll Carl R. Parent David Page Pamela K. Kreeger Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting BMC Cancer Reverse phase protein array Orthogonal partials least squares Protein activity Targeted therapies BRAF inhibitor |
| title | Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting |
| title_full | Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting |
| title_fullStr | Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting |
| title_full_unstemmed | Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting |
| title_short | Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting |
| title_sort | tumor cell sensitivity to vemurafenib can be predicted from protein expression in a braf v600e basket trial setting |
| topic | Reverse phase protein array Orthogonal partials least squares Protein activity Targeted therapies BRAF inhibitor |
| url | http://link.springer.com/article/10.1186/s12885-019-6175-2 |
| work_keys_str_mv | AT mollyjcarroll tumorcellsensitivitytovemurafenibcanbepredictedfromproteinexpressioninabrafv600ebaskettrialsetting AT carlrparent tumorcellsensitivitytovemurafenibcanbepredictedfromproteinexpressioninabrafv600ebaskettrialsetting AT davidpage tumorcellsensitivitytovemurafenibcanbepredictedfromproteinexpressioninabrafv600ebaskettrialsetting AT pamelakkreeger tumorcellsensitivitytovemurafenibcanbepredictedfromproteinexpressioninabrafv600ebaskettrialsetting |