search

ifyoungnet / ADMETlab

A platform for systematic ADME evaluation of drug molecules, thereby accelerating the drug discovery process.
GNU Affero General Public License v3.0
60 stars 27 forks source link

Reproducibility Issues, documentation issues #8

Open misterbrandonwalker opened 3 years ago

misterbrandonwalker commented 3 years ago

Hello,

I am going through and attempting to reproduce everything. Here are just some things I noticed.

1) caco2 model has length of input 27 not length 30 as descriptors docs say 2) What is Getov? Geometric topological index by Narumi is this the same as Geto? and if they are the same why is logD being trained on two desciptors that are the same? 3) for T1/2, the docs say there are 40 descriptors but their is actually 50. 4) LD50 has no descriptors labels on the docs website (but it is in the LABEL folder on github). 5) This one is just a slight annoyance, but some of the topological descriptors are not in PyBioMed but instead in chemopy (most of them are in PyBioMed however).

misterbrandonwalker commented 3 years ago

I stand corrected, 1 is not an issue (my mistake), I found 2 in chemo py. 3 and 4 are still issues and also PPB labels are not in docs website. I also for some reason cannot open PPB labels on github but can open the others.

misterbrandonwalker commented 3 years ago 
Just some more comments I made as going through this content.
# HHT labels not in docs
# PPB Labels will not load
# labels for LD50 not in docs
# druglikeness not in documentation
# what are the models in old folders?
#HIA and SkinSen have 9 models which correspond to the documentation?
#HHT rdkit has issues computing entropy for BertzCT (at least in my example)
Larraitz5 commented 3 months ago

Hello,

I am trying to reproduce the tool but I am facing issues with dependencies. Could someone provide a requirements file and specify the Python version needed to run the tool?

Thank you