The node finds the most diverse molecules either by (default) looking for the furthest apart molecules (1-Tanimotoscore), which is deterministic depending on the order of the input, or by first clustering and choosing the most diverse molecules of each cluster, which is non-deterministic(multiple runs different results). For this it uses the fingerprints.
- Type: Data Table containing the input molecules.
- Type: Data Table containing the most diverse molecules. Number for output molecules is set by the user.