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

Yinan Huang, Xingang Peng, Jianzhu Ma, Muhan Zhang
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:9280-9294, 2022.

Abstract

Deep learning has achieved tremendous success in designing novel chemical compounds with desirable pharmaceutical properties. In this work, we focus on a new type of drug design problem — generating a small “linker” to physically attach two independent molecules with their distinct functions. The main computational challenges include: 1) the generation of linkers is conditional on the two given molecules, in contrast to generating complete molecules from scratch in previous works; 2) linkers heavily depend on the anchor atoms of the two molecules to be connected, which are not known beforehand; 3) 3D structures and orientations of the molecules need to be considered to avoid atom clashes, for which equivariance to E(3) group are necessary. To address these problems, 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 E(3) equivariant graph variational autoencoder. So far as we know, no previous models could achieve this task. 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 3D coordinates of all the atoms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-huang22g, title = {3{DL}inker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design}, author = {Huang, Yinan and Peng, Xingang and Ma, Jianzhu and Zhang, Muhan}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {9280--9294}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/huang22g/huang22g.pdf}, url = {https://proceedings.mlr.press/v162/huang22g.html}, abstract = {Deep learning has achieved tremendous success in designing novel chemical compounds with desirable pharmaceutical properties. In this work, we focus on a new type of drug design problem — generating a small “linker” to physically attach two independent molecules with their distinct functions. The main computational challenges include: 1) the generation of linkers is conditional on the two given molecules, in contrast to generating complete molecules from scratch in previous works; 2) linkers heavily depend on the anchor atoms of the two molecules to be connected, which are not known beforehand; 3) 3D structures and orientations of the molecules need to be considered to avoid atom clashes, for which equivariance to E(3) group are necessary. To address these problems, 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 E(3) equivariant graph variational autoencoder. So far as we know, no previous models could achieve this task. 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 3D coordinates of all the atoms.} }
Endnote
%0 Conference Paper %T 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design %A Yinan Huang %A Xingang Peng %A Jianzhu Ma %A Muhan Zhang %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-huang22g %I PMLR %P 9280--9294 %U https://proceedings.mlr.press/v162/huang22g.html %V 162 %X Deep learning has achieved tremendous success in designing novel chemical compounds with desirable pharmaceutical properties. In this work, we focus on a new type of drug design problem — generating a small “linker” to physically attach two independent molecules with their distinct functions. The main computational challenges include: 1) the generation of linkers is conditional on the two given molecules, in contrast to generating complete molecules from scratch in previous works; 2) linkers heavily depend on the anchor atoms of the two molecules to be connected, which are not known beforehand; 3) 3D structures and orientations of the molecules need to be considered to avoid atom clashes, for which equivariance to E(3) group are necessary. To address these problems, 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 E(3) equivariant graph variational autoencoder. So far as we know, no previous models could achieve this task. 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 3D coordinates of all the atoms.
APA
Huang, Y., Peng, X., Ma, J. & Zhang, M.. (2022). 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:9280-9294 Available from https://proceedings.mlr.press/v162/huang22g.html.

Related Material