Fig. 7From: Afann: bias adjustment for alignment-free sequence comparison based on sequencing data using neural network regressionDiagram of hyperparameter tuning and evaluation. (1) Trainig set is augmented. (2) Training set after data augmentation is used to fit the model. (3) The trained model is used to predict d(AG,BG) for the validation set. For each combination of hyperparameters, we repeated steps 1–3 ten times to calculate the average R2, and the combination of hyperparameters with the highest average R2 was chosen. (4) After hyperparameter tuning, the final model is tested on the test setBack to article page