Skip to content
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.

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

Dragonns for drug discovery? #4

Open
rbharath opened this issue Jul 15, 2017 · 2 comments
Open

Dragonns for drug discovery? #4

rbharath opened this issue Jul 15, 2017 · 2 comments

Comments

@rbharath
Copy link
Member

Dragonn (http://kundajelab.github.io/dragonn/) is the most mature deep learning library for genomic data. Would it be possible to adapt dragonn models for drug discovery?

@vsomnath
Copy link

vsomnath commented Mar 7, 2019

As far as as I recall, DeepChem still doesn't have full functionality of dragonn ported in right?

There are also some custom layers, a few of which I found in Avanti's paper and few from the Janggu library, which could be ported into DeepGene pr dc.genomics.

With TF 2.0 based on tf.keras and tf.contrib going away, it might be easier to integrate DragoNN now.
Relevant discussion #1461.

What do you think?

@rbharath
Copy link
Member Author

rbharath commented Mar 7, 2019

Yes, agreed. We're going to start pushing to integrate DeepChem layers with tf.keras layers so we get full TF 2.0 inter-op. This will be the next big push after DeepChem 2.2 is cut.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants