6
$\begingroup$

Is there any Pythonic way (a.k.a: a module, an rdkit package, etc) or an API I can use for ADME predictions? I need to prioritize some compounds for purchase/synthesis and some sort of ADME scoring might help me rule out most of them.

I am aware of tools like SwissADME but given the amount of compounds I want to test, it isn't a viable option. Should I train my own model?

$\endgroup$
5
  • 1
    $\begingroup$ You mean, KNIME would be just fine, too? As this 2020JChemInfModel2660, for example? $\endgroup$
    – Buttonwood
    Commented Feb 26, 2021 at 7:29
  • 1
    $\begingroup$ This might be better suited for matter modeling $\endgroup$
    – Cody Aldaz
    Commented Feb 26, 2021 at 8:13
  • $\begingroup$ @Buttonwood yeah, found that right after posting the question. It is my understanding that KNIME requires a license for batch jobs such as this one, though. Do yuo have any experience with it? Care to share? :) $\endgroup$
    – Leitouran
    Commented Feb 26, 2021 at 14:31
  • $\begingroup$ @Leitouran The topic is too broad for ChemSE and really better suited for the sibling site (MatterModelling). Literature search (e.g. this), the RDKit UserGroupMeetings (you equally find recordings on youtube) empirical application of rules (e.g., Lilly rules, or DataWarrior to crunch many relevant data at once) may be examples of tools and resources useful for you, so ChemSE can't give a hand-on tutorial. $\endgroup$
    – Buttonwood
    Commented Feb 26, 2021 at 21:34
  • $\begingroup$ I don't think is necessarily better suited for a modelling SE, since I'm not asking "how to make my own model". I'm not asking for a tutorial on how to do ADME modeling. I know there's enough literature on how to do it... I'd just rather not to, and I was asking if there was any tool readily available to so. $\endgroup$
    – Leitouran
    Commented Feb 27, 2021 at 0:51

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.