Giters

MarcusOlivecrona / REINVENT

Molecular De Novo design using Recurrent Neural Networks and Reinforcement Learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

query regarding the target

meghanakaranam1 opened this issue · comments

commented

Hello,
As mentioned in issue #11, I've trained the model on 1.5M smiles. But as specified in the paper, "The dopamine type 2 receptor DRD2 was chosen as the target, and corresponding bioactivity data was extracted from ExCAPE-DB [33]. In this dataset there are 7218 actives (pIC50 > 5) and 343204 inactives (pIC50 < 5)." I have a few questions to ask on this. @MarcusOlivecrona

  1. is that 1.5M dataset related to DRD2 only?
  2. if yes then how do I filter 1.5M down to ( 343204+7218)
    please help me understand this.
    looking forward to hearing from you.