Converting pandas columns of chemical formulas to SMILES

Question

I’m wondering if there’s a way to get SMILES strings starting from a pandas data frame that looks like this:

Formula.   Band_Gap(eV)
He         3.1
NaCl       1.2
NO2        3.5
...        ...

Basically, I want to perform a regression task (predicting band gap values for a ton of compounds) using some graph neural network architecture (GraphConv) but I don’t have access to SMILES information. Any suggestion on this? Thanks a lot!

Answer 1

There is a package to perform such kind of task, "pysmiles". I dunno much abt it. I hope it might help you.

Pysmiles