I'm not qualified to discuss drug discovery, but my eye was caught by the authors statement that char-RNN on SMILES strings might outperform the use of a coulomb matrix. IMO this is really misguided as a SMILES string does not contain specific geometrical data (bond angles, dihedrals etc) of a compound...
Learning the grammar of smiles-representation is not the same as learning to use inter atomic distances.
SMILES implicitly stores the geometry data. It's technically true it doesn't encode a unique 3D structure (for a rigid molecule), but you could convert the implict bonds to standard-length ones, embed the molecule in 3D space, and minimize it (that's precisely what SMILES to 3D structure systems do).
Learning the grammar of smiles-representation is not the same as learning to use inter atomic distances.