Conditional generative model for linker generation

Home

Discover

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

Source arXiv

Machine Learning

Artificial Intelligence

Biomolecules

Conditional generative model for linker generation

3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design

We propose a conditional generative model, named 3dlinker, which is able to predict anchor atoms and jointly generate linker graphs and their 3d structures based on an equivariant graph variational autoencoder.

We compare our model with multiple conditional generative models modified from other molecular design tasks and find that our model has a significantly higher rate in recovering molecular graphs, and more importantly, accurately predicting the 3dcoordinates of all the atoms.

Authors

Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang

◐ Recommended Members

◐ Latest Activity