Re: [Rdkit-discuss] Removing solvent and ions from dataset

[Francois B. <ml...@li...>]

On 06/06/2020 17:33, Max Pinheiro Jr wrote:
> Hi RDkit team,
> 
> I am working on a chemically diverse dataset of smiles strings and I
> need to do some preprocessing to clean a bit the data before starting
> the modeling part. So I was looking for some tools or built-in
> functions in RDkit to make such preprocessing by removing, for
> instance, solvent (water) molecules and ions. I found the
> "SaltRemover" module that may solve my problem with removing ions from
> the database, but I could not find an equivalent module for the case
> of solvent molecules. Does anyone know a specific tool in RDkit (or
> any other python program) to make such preprocessing in the smile
> strings? If so, could you please provide just a simple example of how
> to do it? I will be really thankful for any help you may provide.

I have used this program several times:

https://github.com/flatkinson/standardiser

You can try this:
```
pip3 install chemo-standardizer
standardiser -i input.smi -o output_std.smi
```

I believe it uses rdkit under the hood.

Regards,
F.

> Max Pinheiro Jr
> ---------------------------------------------
> Université Aix-Marseille, France
> Institut de Chimie Radicalaire
> _______________________________________________
> Rdkit-discuss mailing list
> Rdk...@li...
> https://lists.sourceforge.net/lists/listinfo/rdkit-discuss