Research Paper Advance Articles
SAMP-Score: a morphology-based machine learning classification method for screening pro-senescence compounds in p16 positive cancer cells
Figure 3. SAMP-Score model development and metric assessment. (A, B) Machine learning (ML) model assessment metrics and confusion matrix for all individual ML models and stacked meta-model (SAMP-Score). Abbreviations: NPV: Negative Prediction Value; AUC: Area under curve; PPV: Positive Prediction Value; TP: True Positive; TN: True Negative; FN: False Negative; FP: False Positive. (C) Effect of altering decision boundary position on model metrics and confusion matrix. (D) Neural network model. Features are input nodes and lead to a prediction of Senescence or Non-Senescence. (E) Receiver operating characteristic (ROC) curve for stacked meta model. (F, G) Model feature contributions to Lasso and Random Forest models.