TalkRL: The Reinforcement Learning Podcast cover image

Sai Krishna Gottipati

TalkRL: The Reinforcement Learning Podcast

00:00

Are You Using Graphic Representation in Drug Discovery?

Having the ability to a predicter the proteins tucus has lot of use cases in drug discovery, but not, i don't think it's related to this work. The alpa fol is mostly supervisedo leni olritm. So these are established standard representations. And then people were er trying out different representations. I think graphical representation is a very attractive one. People can also try and learn the inversegrap so we're just doing forward synthesis. It could probably have been the reward a function design that we were talking about at lear instead of just a learning from the existing data.

Play episode from 51:40
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app