Comment on page

# Differential Selection

Univariate feature selection (categorical variables)

Performs differential analysis of OTU data based on pairwise categorical metadata.

Taxonomic groups/OTUs that are statistically different between the two sample groupings will be displayed.

- Selecting OTUs or taxonomic groups ("OTU signature") that have a significant difference between two or more sample groups according to a differential analysis

The taxonomic level to aggregate the OTUs at. The OTUs will be grouped together (by summing the OTU values) at the selected taxonomic level before the analysis is applied.

Create comparative sample groups based on categorical variables uploaded in the metadata file.

Optionally create a categorical variable from a quantitative variable by using the Quantile Range feature on the Projects home page.

The two unique values for the selected Categorical Variable field that will be used to build a contingency table.

**ANCOM**Differential abundance testing using pairwise log ratios and applying a parametric one-way ANOVA statistical test. Recommended if using unsampled data sets**Wilcoxon Rank-Sum**A non-parametric test to test whether a randomly selected sample from one group will be different from a randomly selected sample from another group**Welch's T-Test**A parametric test to test whether two populations have equal means

Only OTUs or taxonomic groups whose resultant p-value was less than this threshold will be displayed

Indicate whether the training set should remain the same every time a parameter is changed and the model is retrained.

Define the proportion of the data that should be randomly picked to form a training dataset.

You can set this value to be 1.0 if you don't plan on evaluating with a test dataset.

- Link back to boxplots

**Save Snapshot**: Save the results to the experiment notebook**Download**: Downloads the results as a CSV file**Share**: Creates a shareable link that allows you to share the results with others

Last modified 3yr ago