New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Why not directly use a simple RNN to generate molecules (like REINVENT) ? #2

Open

jkwang93 opened this issue Apr 12, 2021 · 3 comments

jkwang93 commented Apr 12, 2021

Hello~ I have a new question to ask you😂. Why not directly use an RNN to generate molecules (just like REINVENT), but use a seq2seq model?

Owner

marcopodda commented Apr 12, 2021

Not sure what you mean, this is simply a different approach to the learning task.

Author

jkwang93 commented Apr 12, 2021

These two generation methods should be applicable in this article of yours?
However, there are hundreds of thousands of Vocabulary on the model that does not use LFM. Will the generated model be problematic?

Author

jkwang93 commented Apr 13, 2021

More over, why choose BRICS instead of RECAP to break down molecules?Is it because RECAP cannot assemble fragments?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment