Home Software Services About Contact     
Follow on twitter

Robert C. Edgar on twitter

11-Aug-2018 New paper describes octave plots for visualizing alpha diversity.

12-Jun-2018 New paper shows that one in five taxonomy annotations in SILVA and Greengenes are wrong.

18-Apr-2018 New paper shows that taxonomy prediction accuracy is <50% for V4 sequences.

05-Oct-2017 PeerJ paper shows low accuracy of closed- and open-ref. QIIME OTUs.

22-Sep-2017 New paper shows 97% threshold is wrong, OTUs should be 99% full-length 16S, 100% for V4.

UPARSE tutorial video posted on YouTube. Make OTUs from MiSeq reads.


 New in v11 

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).


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