Fig. 6

Prediction analysis between two T2D datasets. Boxplots of random forest AUC scores obtained in the cross-study analysis are provided. “MicroPro known” refers to using only known microbial abundance profile extracted by MicroPro as the feature while “MicroPro combined” refers to using both known and unknown abundances. Each random forest classification model was repeatedly trained and tested 30 times. Student’s t test p values are given