Skip to main content
Fig. 1 | Microbiome

Fig. 1

From: Fecal source identification using random forest

Fig. 1

Design of the classifiers. (a) Determination of the bacterial group profiles for each of the source samples. (b) Analysis of the bacterial profile discrepancies between the samples that belong to the targeted source and all other samples using random forest (one classifier per source). (c) Selection of the relevant representative sequences based on mean decrease Gini values to form the classifier. Classifiers are then trained using the selected representative sequences. Abbreviations: MDG mean decrease Gini

Back to article page