Iván Pulido
Iván Pulido
From https://github.com/choderalab/espaloma/issues/213 We could probably benefit from using newer/up-to-date versions of DGL. We would need to check if this requires a significant refactor or not, I haven't checked in detail...
We have noticed that some important parts of the code are not covered by tests. We should aim to improve the testing coverage as we progress towards a more stable...
When dealing with the `insane.py` script I noticed that when solvating a CG protein with ```bash insane -o system_solvated.gro -p system.top -f system.gro -sol W -salt 0.15 -center ``` The...
We have scripts/notebooks that can be used to take the information in the protein-ligand benchmark dataset to be run with alchemiscale. I think it would be good if we add...
We currently have a basic pipeline that uses Schrodinger tools for the generation of poses (docking). As discussed in #101 and #104 , we probably want to consider using OpenEye...
We should probably consider including the data in https://github.com/schrodinger/public_binding_free_energy_benchmark in this dataset
Some users have manually curated transformation networks that give very good results, we probably want to add these to the edges for the systems that they were created for, such...
We currently have a [`targets.yaml` file in the data base directory](https://github.com/openforcefield/protein-ligand-benchmark/blob/main/data/targets.yml). Do we still want to have this file? My guess is that this was useful for the previous versions...
It would be very useful if we can install and use the `plbenchmarks` package without having to download the complete data set. Having points in the API that download the...
Are there any plans on making a conda-installable package at conda-forge for this project? I think other projects using it will benefit from a conda-forge package.