Alby M.
What version are you using? This looks correct in the versions I'm looking at.
Maybe try the `develop` branch of `nequip`.
Hi @asedova , Thanks very much for your interest in our methods and working on this integration! We previously had some discussion about this (https://github.com/mir-group/nequip/issues/76) and the great news is...
OK @asedova I've edited the above to reflect more recent versions of OpenMM-Torch 🙂
Great! Let me know if you have any questions. It looks like a lot but I think it should hopefully be straightforward, mostly "copy-paste" style coding.
> It treats atom types as a property of a particular force field. That sounds quite compatible. In `nequip`, atom types are just 0-based integer indexes of which there can...
> receives a [Topology](http://docs.openmm.org/latest/api-python/generated/openmm.app.topology.Topology.html) object which contains chemical information: elements, bonds, residue names, etc. I think as a first solution, you can just ignore all of that, take the elements,...
👍 I vote then to start with just taking OpenMM element -> chemical symbol as NequIP type name, possibly with an option of letting the user provide their own function...
Hi @asedova , Just curious if you'd had any luck with this. Thanks!
@sef43 hi, thank you for reaching out! :wave: We'd love to see this happen, so your help and hopefully leadership on it as an RSE who knows OpenMM well would...