Cluster Analysis by descriptors

Bit of modification to previous post to k-means cluster the chemicals.

So these nodes are from previous workflow...

File Reader: Read csv file

Column Filter: Filter out non-SMILES paramters

RDKit Descriptor Calculation: Used All Descriptors!!!!

Normalizer: Gaussian (but 0 to 1 could be good too)

PCA: Into 3D

And two addtions

k-Means: Into 10 clusters for a trial

Joiner: Join by row ID so that I can add colour to 3D plot

Then set the 3D plot to colour by the Cluster column

Hmm... seems to clustering at near places. Not bad again.

I though PCA may cause some werid things but looks like it didn't. Nice simple clustering workflow I guess... KNIME is so cool.