[gmx-developers] Neural Network

Francesco Guidarelli Mattioli f.guidarellimattioli at gmail.com
Mon Mar 29 14:20:19 CEST 2021


Hi everyone,
I would like to use a force field in GROMACS coming from my Trained Neural
Network. My Neural Network function represents the local potential energy
of an atom i , E_{i}.

E_{i} depends on, say, n descriptors (D_{i1},...,D_{in}),
E_{i}(D_{i1},...,D_{in}) . These descriptors depend on coordinates of atom
i and coordinates of the first, say, 20 nearest neighbour  atoms.

I found the Tabulated interaction functions topics in the reference manual.
It seems possible to use a custom pairwise interaction E(r_{ij})  but not
more.

I'm looking for a routine where:

I can compute at each step the descriptors for each molecule then evaluate
all E_{i} and then derivate it to get forces.

or

I can tabulate all the descriptors and the corresponding energies and
forces.

Is there a way to do something like that in GROMACS? If I have to modify
some source codes, how it could be difficult?

FGM
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://maillist.sys.kth.se/pipermail/gromacs.org_gmx-developers/attachments/20210329/f3a50314/attachment.html>


More information about the gromacs.org_gmx-developers mailing list