Wei Lu （陆威）

same situation here. The incompatibility issue make it hard to integrate torchDrug into the workflow. Also, TorchDrug could influence other packages outside the typical scope of a package. For example,...

I realize it is not only the pause button not function. but also the "increase speed" and "decrease speed" button have no real effect on the replay.(except the game time...

My keyboard doesn't have PgUp/PgDn, and Puase button. I can use on screen keyboard for now. but I hope it can be easier.(like being able to control through UI. Thanks.

Thanks for your interest. we plan to release the training code in later August when the paper is accepted.

Yes. You can construct the "info" pandas DataFrame yourself. The "pocket center" column could be manually changed. Hope this help.

Thanks for your interest. In early commit (https://github.com/luwei0917/TankBind/commit/18314e9664621f44fd1f83a7c3660d547c74afad), you could find an exmaple "examples/prediction_example_using_PDB_6hd6.ipynb" to construct the dataset, and the main.py script to train. "python main.py -d 0 -m 0...

It has been uploaded.

the result from the GitHub model should be about the same as the one reported in preprint. we only slightly updated the coordinates generation part of the code. The v1.0.1...

Yes. In my opinion, that's the beauty of TankBind. You don't need prior knowledge of the complex structure to predict the affinity.

The coordinates of the ligand is determined based on its interaction with the protein and constraint imposed by chemical bonds and excluded volume effects.