Generating 3D Molecules for Target Protein Binding

Meng Liu, Youzhi Luo, Kanji Uchino, Koji Maruhashi, Shuiwang Ji
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:13912-13924, 2022.

Abstract

A fundamental problem in drug discovery is to design molecules that bind to specific proteins. To tackle this problem using machine learning methods, here we propose a novel and effective framework, known as GraphBP, to generate 3D molecules that bind to given proteins by placing atoms of specific types and locations to the given binding site one by one. In particular, at each step, we first employ a 3D graph neural network to obtain geometry-aware and chemically informative representations from the intermediate contextual information. Such context includes the given binding site and atoms placed in the previous steps. Second, to preserve the desirable equivariance property, we select a local reference atom according to the designed auxiliary classifiers and then construct a local spherical coordinate system. Finally, to place a new atom, we generate its atom type and relative location w.r.t. the constructed local coordinate system via a flow model. We also consider generating the variables of interest sequentially to capture the underlying dependencies among them. Experiments demonstrate that our GraphBP is effective to generate 3D molecules with binding ability to target protein binding sites. Our implementation is available at https://github.com/divelab/GraphBP.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-liu22m, title = {Generating 3{D} Molecules for Target Protein Binding}, author = {Liu, Meng and Luo, Youzhi and Uchino, Kanji and Maruhashi, Koji and Ji, Shuiwang}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {13912--13924}, 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/liu22m/liu22m.pdf}, url = {https://proceedings.mlr.press/v162/liu22m.html}, abstract = {A fundamental problem in drug discovery is to design molecules that bind to specific proteins. To tackle this problem using machine learning methods, here we propose a novel and effective framework, known as GraphBP, to generate 3D molecules that bind to given proteins by placing atoms of specific types and locations to the given binding site one by one. In particular, at each step, we first employ a 3D graph neural network to obtain geometry-aware and chemically informative representations from the intermediate contextual information. Such context includes the given binding site and atoms placed in the previous steps. Second, to preserve the desirable equivariance property, we select a local reference atom according to the designed auxiliary classifiers and then construct a local spherical coordinate system. Finally, to place a new atom, we generate its atom type and relative location w.r.t. the constructed local coordinate system via a flow model. We also consider generating the variables of interest sequentially to capture the underlying dependencies among them. Experiments demonstrate that our GraphBP is effective to generate 3D molecules with binding ability to target protein binding sites. Our implementation is available at https://github.com/divelab/GraphBP.} }
Endnote
%0 Conference Paper %T Generating 3D Molecules for Target Protein Binding %A Meng Liu %A Youzhi Luo %A Kanji Uchino %A Koji Maruhashi %A Shuiwang Ji %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-liu22m %I PMLR %P 13912--13924 %U https://proceedings.mlr.press/v162/liu22m.html %V 162 %X A fundamental problem in drug discovery is to design molecules that bind to specific proteins. To tackle this problem using machine learning methods, here we propose a novel and effective framework, known as GraphBP, to generate 3D molecules that bind to given proteins by placing atoms of specific types and locations to the given binding site one by one. In particular, at each step, we first employ a 3D graph neural network to obtain geometry-aware and chemically informative representations from the intermediate contextual information. Such context includes the given binding site and atoms placed in the previous steps. Second, to preserve the desirable equivariance property, we select a local reference atom according to the designed auxiliary classifiers and then construct a local spherical coordinate system. Finally, to place a new atom, we generate its atom type and relative location w.r.t. the constructed local coordinate system via a flow model. We also consider generating the variables of interest sequentially to capture the underlying dependencies among them. Experiments demonstrate that our GraphBP is effective to generate 3D molecules with binding ability to target protein binding sites. Our implementation is available at https://github.com/divelab/GraphBP.
APA
Liu, M., Luo, Y., Uchino, K., Maruhashi, K. & Ji, S.. (2022). Generating 3D Molecules for Target Protein Binding. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:13912-13924 Available from https://proceedings.mlr.press/v162/liu22m.html.

Related Material