I am a novice at this, and I am attempting to sort a group of 10,000 compounds into a set of 2500 clusters. I want to bin the compounds based on substructure similarity. I have been attempting to use libmcs to do this, but the output is a little confusing. When I output as a csv I get 3 columns, which I'm assuming correspond to the parent smile, the node level, and the cluster number. Is it possible to get an output listing all of the compounds in the corresponding node, similar to the output of jklustor? I have also attempted to do this using the GUI, but I have been unsuccessful at both. Any help would be very much appreciated.