Hi Wesley. Wanted to let you know that the latest version is posted here: https://git.durrantlab.pitt.edu/jdurrant/wisp All the best.
Hi Douglas. Wanted to let you know that the latest version is posted here: https://git.durrantlab.pitt.edu/jdurrant/wisp All the best.
Hi Patrick. Much thanks for your interest in AutoGrow, and please forgive my delay in getting back to you. We're currently putting together a new version of AutoGrow with some major improvements. My student Jake Spiegel has rewritten and modernized almost the entire codebase. We hope to submit the work for publication in a few months. I'm not sure why exactly the old version isn't processing your input molecules properly, but I'm confident the new version will be able to handle them if they are amenable...
Hi Douglas. Sorry for the delay. You're right that NNScore could use an update. It's remarkable how quickly the PDBbind database expands! :) I do think it would take a bit more to create a new version of NNScore than applying my existing scripts, though. Here are just a few things that come to mind: 1) It would need to be Python3 compatible, since Python2 will soon reach end of life. All my scripts are written in Python2. 2) It would probably be best if it used a more modern neural-network library...
Hi Dr. Houston. Much thanks for your interest in nnscore. I believe that error occurs when nnscore encounters two adjacent atoms with types that were not commonly found to be adjacent in the training data. Rather than trying to make a guess based on insufficient data, nnscore simply throws the error. In practice, though, the fact that these atoms are adjacent is probably a good indication that the pose is not correct. Hope this answer helps. All the best.
Hi Wesley. Just wanted to let you know that I got your code. Much thanks for this contribution! I've gotten this version running on Python 3 as well. We're going to test it intnerally for a bit and then publish it for others to use. Can I include you in the CONTRIBUTORS.md file? All the best.
Wesley, please forgive me for my delay in getting back to you! My sourceforge emails were going to my old UCSD email address, but I'm now at the University of Pittsburgh. Wonderful that you were able to patch the code to work with the latest version of networkx. Would you mind emailing your updated code to me at durrantj at pitt dot edu? All the best.
Hi Andrew. Please forgive my ridiculous delay in getting back to you. I wanted to let you know that we have begun to work on Autogrow 4. We intend to make it more modular so that custom filters can be easily added. I expect we won't be ready to publish for some months, but I wanted to let you know we're working on it! All the best.