Fecal source identification using random forest

Script_RF_V6.R: Code to perform the source identification using random forest classification (creation/training of the classifiers + prediction of new samples).RF_SourceIdentification_v6.RData: R-objects that contains the training/testing V6-databases used in the publication. ClostridialesBacteroiales_v6.fa: File containing the sequences of the V6- Clostridiales/Bacteroidales amplicon sequence variants.RF_training_outputs.zip: Folder containing the outputs of the random forest classifications performed to train the V6-classifiers.Confusion_Matrix_V6.xlsx: Excel spreadsheet containing the confusion matrix for each V6-classifiers.Comparison_V4V5_V6.zip (not peer-reviewed): Folder containing the files used to train/test/compare the classifiers.