Fig. 6: Normalized viability versus the important features for each random forest model reveals cell composition dynamics in drug response prediction. | npj Biomedical Innovations

Fig. 6: Normalized viability versus the important features for each random forest model reveals cell composition dynamics in drug response prediction.

From: Cracking the code: predicting tumor microenvironment enabled chemoresistance with machine learning in the human tumoroid models

Fig. 6

The most important features in predicting response to A carboplatin, (B) paclitaxel, (C) PACMA31, (D) N773, and E SC144 versus normalized viability. F Plotting the second most important feature in predicting carboplatin response versus normalized viability reveals the expected relationship between the presence of mesenchymal cells and resistance to carboplatin (higher ratios of MSCs to OVCAR3 are associated with greater resistance to carboplatin).

Back to article page