search

simonfqy / PADME

This is the repository containing the source code for my Master's thesis research, about predicting drug-target interaction using deep learning.
MIT License
41 stars 16 forks source link

Data preprocessing #13

Open bbrighttaer opened 4 years ago

bbrighttaer commented 4 years ago

Hello @simonfqy. Please, I would like to find out whether the Kd, Ki, and KIBA values of the Davis, Metz, and KIBA datasets in this repo have been transformed following the pKd, pKi, and Kiba scaling described in SimBoost. I have checked the supplementary material, nothing of the sort is mentioned but a histogram plot of the Davis dataset values seems to follow the pKd of the SimBoost paper. Thank you.

simonfqy commented 4 years ago

@bbrighttaer You can find the code for transforming them in the respective preprocess.py scripts in the folder for each dataset. An example is here: https://github.com/simonfqy/PADME/blob/master/davis_data/preprocess.py#L30