Amino Acid k-mer Feature Extraction for Quantitative Antimicrobial Resistance (AMR) Prediction by Machine Learning and Model Interpretation for Biological Insights

. 2020 Oct 28;9(11):365. doi: 10.3390/biology9110365

Algorithm 1 Feature selection.

1:
for $i = 1, 2, \dots, 10$ do
2:
Rank the features in fold i based on their SHAP values;
3:
Selected features i = Top $N_{t o p}$ features in fold i;
4:
end for
5:
Find union of selected features in all folds;
6:
for feature in union set do
7:
Find in how many folds this features makes it to top $N_{t o p}$ ;
8:
end for
9:
Rank features in the union based on the number of times each feature appears in the top $N_{t o p}$ ;
10:
Output the ranked list of features;