Alternative to Conformer Matching

gcorso / torsional-diffusion

Implementation of Torsional Diffusion for Molecular Conformer Generation (NeurIPS 2022)

https://arxiv.org/abs/2206.01729

MIT License

251 stars 46 forks source link

Alternative to Conformer Matching #7

Closed KruskalLin closed 1 year ago

KruskalLin commented 1 year ago

Hi,

Thanks for your great work! I wonder why we should use the optimization to perform conformer matching. Could we just set the ground truth torsions to our RDKit-generated conformers as our targets? Am I missing something here?

Thank you in advance!

Best regards, Lin