Kerro

Oh! If the `vina` and other `CNN scoring function model` are all use `1A `as unit of `box_size`, there must be some unreasonable data in their paper using 20*20*20 to...

the ligands are prepared with the adfr scripts, so I do not think it is a typo error. Here is another example: autogrid4: ERROR: unknown ligand atom type AN add...

I tired the 1a30_ligand.sdf in CASF2016 coreset, it couldn't be transferred into pdbqt: ``` mk_prepare_ligand.py -i 1a30_ligand.sdf -o 1a30_ligand.pdbqt [10:19:21] Explicit valence for atom # 6 C, 6, is greater...

There is nothing special about the usage of prepare_gpf.py to generate multiple gpf files: _(the following script is compatible and run with python2.5)_

We have prepared all the glg, fld and maps files that needed. But our script encounters the following error: ``` Reading AD4.2 maps ... done. ERROR: Cannot compute Vina affinity...

Thanks for your advise, but I wonder why ADFR -A "hydrogens" is not good to use? I encountered error like the following information when processing the `*_protein.pdb without any waters...

Though the default scoring function can deal with metals, the `protein.pdb` cannot be converted into `pdbqt file` if they have Zn,Mg... for example, _1ew9_pocket.pdb_ consists of Zn and Mg, and...

Hi, I have questions about your article: ``` the binding affinity (pKa) of the native pose is 2.29, whereas with OnionNet, the predicted binding affinity based on the crystal structure...

your google driver link works, thank you, But I want to give you a tip that `git lfs` is not working now

> If that's the case, I think training with default2018.model also should fail, but it works well, so I guess there can be other reasson Hi, i want to ask...