forest_classify command

See also
Random forest classifier
Feature table file
forest_train command

The forest_classify command is used to predict metadata categories for observations in a feature table using a random forest which was previously trained on an feature table (or OTU table) with known categories.

The feature table filename is specified following forest_classify.

The random forest parameter file is specified by the -forestin option. The parameter file is generated by running forest_train or otutab_forest_train .

Predictions are written to a tabbed text file specified by the -tabbedout option. There are three fields:

#1. Observation label (typically, sample name).
#2. Predicted category.
#3. Confidence (P).

Confidence values are in the range 0 (lowest confidence) to 1 (highest confidence).

Example

usearch -forest_classify feature_table.txt -forestin forest.txt \
-tabbedout predictions.txt