Fig. 6

(A) Two-dimensional scatter plot of saliva sample based on t-Distributed Stochastic Neighbor Embedding (t-SNE) technique. (B) Bar plot of species importance at the genus level performed by random forest algorithm. Each bar represents a genus, and the height of the bar indicates the importance or contribution of that genus to the overall predictive power of the random forest model. Genera with higher importance values have a stronger influence on the classification outcome. (C) Trend graph of area under the curve (AUC) increasing with the number of top important features. (D) Receiver operating characteristic (ROC) curve of saliva sample for predicting pulmonary nodules at the genus level. The x-axis of the curve represents the false positive rate (1-specificity), and the y-axis represents the true positive rate (sensitivity)