You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,
I have read this paper (https://doi.org/10.1021/acs.jpcb.3c06662) and would like to try ML/MM calculations.
However, I am struggling to understand what kind of Python script is needed for this purpose.
Would it be possible to provide a working Python script example, such as for alanine dipeptide?
Additionally, is it possible to perform MD simulations using only the machine learning potential?
Thank you for your help!
The text was updated successfully, but these errors were encountered:
You can find some usage instructions for openmm-ml here. These instructions can be combined with the standard approach for running simulations in OpenMM. The documentation includes several examples. See here.
Technically speaking, yes, it is possible to perform MD simulations using only the MLP. However, these simulations may be very expensive, and the ML potential might not have been trained to reproduce condesed-phase behaviour. For the MLPs provided with this package (ANI and MACE), you should be cautious regarding the results when using them in this way. These MLPs are near-sighted, meaning they only consider chemical environments within 3–4 A.
Hello,
I have read this paper (https://doi.org/10.1021/acs.jpcb.3c06662) and would like to try ML/MM calculations.
However, I am struggling to understand what kind of Python script is needed for this purpose.
Would it be possible to provide a working Python script example, such as for alanine dipeptide?
Additionally, is it possible to perform MD simulations using only the machine learning potential?
Thank you for your help!
The text was updated successfully, but these errors were encountered: