News for hackers. Stuff that matters.
Re:Keras-based molecular autoencoder by cing on Tuesday October 25, 2016 @02:03AM (#12785672)
I like the idea, but I wouldn't call it "relative ease". Are we talking about making better force fields, or training a recurrent neural network for generative dynamics that obeys the laws of physics (can be used to calculate ensemble averages) for arbitrary length proteins/folds? How do you construct a VAE for protein dynamics when you only have a single structure? There's a serious lack of data that prevents these things.

There are no comments on this comment yet.