As shown in the source code for MoleculeSet, name and descriptor columns are expected to be prefixed in a very particular way, but this is not stated in the documentation.
I suggest that we either add these requirements to the documentation, or devise a more general way to ingest data.
As shown in the source code for
MoleculeSet, name and descriptor columns are expected to be prefixed in a very particular way, but this is not stated in the documentation.I suggest that we either add these requirements to the documentation, or devise a more general way to ingest data.