Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Quantitative Structure–Mutation–Activity Relationship Tests (QSMART) model for protein kinase inhibitor response prediction

Fig. 2

Prediction performances of different datasets and different prediction models. Wilcoxon signed-rank test is performed, and the p value is shown in each box plot. a Comparison between actual \(\hbox {IC}_{50}\) (x-axis) and the \(\hbox {IC}_{50}\) predicted by using QSMART with neural networks across all cancer types (y-axis). A fitted regression line is shown. b Prediction performances of different statistical or machine learning methods. NN: neural networks; RF: random forests; MCA: multiscale convolutional attentive [36]. c ROC curves for 23 cancer-centric models as well as an overall ROC. d Impact of different data sets on prediction performance

Back to article page