In Translational cancer research
BACKGROUND : BRAF inhibitors have been approved for the treatment of melanoma, non-small cell lung cancer, and colon cancer. Real-time polymerase chain reaction or next-generation sequencing were clinically used for BRAF variant detection to select who responds to BRAF inhibitors. The prediction of BRAF variants using gene expression data might be an alternative test when the direct variant sequencing test is not feasible. In this study, we built a prediction model to detect BRAF V600 variants with mRNA gene expression data in various cancer types.
METHODS : We adopted a penalized logistic regression for the BRAF V600E variants prediction model. Ten times bootstrap resampling was done with a combined target variable and cancer type stratification. Data preprocessing included knnimputation for missing value imputation, YeoJohnson transformation for skewness correction, center, and scale for standardization, synthetic minority over-sampling technique for class imbalance. Hyperparameter optimization with a grid search was undertaken for model selection in terms of area under the precision-recall.
RESULTS : The area under the curve of the receiver operating characteristic curve on the test set was 0.98 in thyroid carcinoma, 0.90 in colon adenocarcinoma, and 0.85 in cutaneous melanoma. The area under the precision-recall of the test set was 0.98 in thyroid carcinoma, 0.71 in colon adenocarcinoma, and 0.65 in cutaneous melanoma.
CONCLUSIONS : Our penalized logistic regression model can predict BRAF V600E variants with good performance in thyroid carcinoma, cutaneous melanoma, and colon adenocarcinoma.
Kang Jun, Lee Jieun, Lee Ahwon, Lee Youn Soo
2022-Nov
BRAF, BRAF kinase inhibitor, The Cancer Genome Atlas (TCGA), machine learning
