UnixJunkie / molenc

MolEnc: a molecular encoder using rdkit and OCaml.

improve standardize.py

UnixJunkie opened this issue 4 years ago · comments

François Bérenger commented 4 years ago

use a salts dictionary like
https://github.com/chembl/ChEMBL_Structure_Pipeline/tree/master/chembl_structure_pipeline/data
as used in
https://github.com/chembl/ChEMBL_Structure_Pipeline/blob/9d6e20c290cfe5c801b603ff6616b31badb744eb/chembl_structure_pipeline/standardizer.py

François Bérenger commented 4 years ago

They remove solvent and salt in the previous example.
This would become slower probably.

François Bérenger commented 3 years ago

or directly use the ChEMBL standardization pipeline, if they have a CLI program with -i and -o

François Bérenger commented 2 years ago

we now use rdkit's standardization pipeline in molenc_std.py