Skip to main content
. 2019 Jun 13;44:607–617. doi: 10.1016/j.ebiom.2019.05.054

Fig. 7.

Fig. 7

a. Predicted vs. actual TIL using ketometabolic pathway molecules as input data for PLS regression with leave-one-out validation (Study 1). b. Predicted vs. actual GOS (6 m) using ketometabolic pathway molecules as input data for neural net with leave-one-out validation. c. Predicted vs. actual TIL using ketometabolic pathway molecules as input data for hybrid PLS regression with leave-one-out validation for Study 1 (blue) and Study 2 (red).