Douglas Houston

Hi Jacob, I thought you might be interested in where this discussion went: https://pubmed.ncbi.nlm.nih.gov/35901959/ Best regards, Doug

Hi Jacob, I was wondering if you had managed to dig up your old Python scripts for this? The call has gone out to advertise MSc projects and I'd like to offer one based on this, but I don't want to promise students anything until I have a starting point ... Best regards, Doug

Hi Jacob, Many thanks for the very helpful reply! and 3. look straightforward, so I think the challenging bit will be 2. I don't have any experience with pyTorch or Tensorflow, but I was planning to learn one of them at some point anyway! If that proves too challenging I note that FFNET is still going, and has been updated to Python3 ... https://pypi.org/project/ffnet/ If you could provide your scripts and anything else that you think might be useful to get us started that would be really great....

One thing that's occurred to me since re-reading the paper and watching your excellent talk on Youtube; NNScore was trained with PDBbind and MOAB, but it was a good few years ago and these databases have since grown greatly (DUD-E too). My guess is that NNscore's performance would get even better if it was re-trained, and that (definitely guessing this time!) it ought to be relatively straightforward since presumably all your tools and the data preparation and training pipeline shouldn't need changing...

Ah yes, very helpful, thank you!

That's great! I'd be very interested in trying out this new version ...

Hi, OK I figured out how to create a new thread! I am running NNscore1 on my docking results, but I am seeing many pose evaluations fail with the following type of messages: The program can't deal with the PROXIMITY_4 calculation between ligand,receptor atom types: NA NA, ligand = t op1k932_largestC.pdbqt LIGAND: ATOM 21 N UNL d 1 13.118 -43.051 -2.497 -0.42 +0.02 -0.066 NA RECEPTOR: ATOM 463 ND1 HIS 145 16.675 -44.777 -2.032 0.00 0.00 -0.247 NA Average score: -999999.9 (bad binder) You can download...

Hi jdurrant, I tried to make a new thread (you have to send an email??) but nothing appeared, so I'm posting here. I am running NNscore1 on my docking results, but I am seeing many pose evaluations fail with the following type of messages: The program can't deal with the PROXIMITY_4 calculation between ligand,receptor atom types: NA NA, ligand = t op1k932_largestC.pdbqt LIGAND: ATOM 21 N UNL d 1 13.118 -43.051 -2.497 -0.42 +0.02 -0.066 NA RECEPTOR: ATOM 463 ND1 HIS 145 16.675 -44.777 -2.032 0.00...