Tumor cell sensitivity to vemurafenib can be predicted from protein expression in a BRAF-V600E basket trial setting

BMC Cancer. 2019 Oct 31;19(1):1025. doi: 10.1186/s12885-019-6175-2.


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.

Keywords: BRAF inhibitor; Orthogonal partials least squares; Protein activity; Reverse phase protein array; Targeted therapies.

MeSH terms

  • Cell Line, Tumor
  • Cell Proliferation / drug effects
  • Drug Resistance, Neoplasm / drug effects*
  • Drug Therapy, Combination
  • ErbB Receptors / antagonists & inhibitors
  • ErbB Receptors / metabolism
  • Humans
  • Inhibitory Concentration 50
  • Machine Learning
  • Melanoma / drug therapy
  • Melanoma / metabolism*
  • Models, Biological
  • Mutation
  • Protein Kinase Inhibitors / pharmacology*
  • Proteomics / methods
  • Proto-Oncogene Proteins B-raf / antagonists & inhibitors*
  • Proto-Oncogene Proteins B-raf / genetics*
  • Quinazolinones / pharmacology
  • Skin Neoplasms / drug therapy
  • Skin Neoplasms / metabolism*
  • Vemurafenib / pharmacology*


  • Protein Kinase Inhibitors
  • Quinazolinones
  • Vemurafenib
  • dacomitinib
  • ErbB Receptors
  • BRAF protein, human
  • Proto-Oncogene Proteins B-raf