MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation

Xingang Peng, Jiaqi Guan, Qiang Liu, Jianzhu Ma
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:27611-27629, 2023.

Abstract

Deep generative models have recently achieved superior performance in 3D molecule generation. Most of them first generate atoms and then add chemical bonds based on the generated atoms in a post-processing manner. However, there might be no corresponding bond solution for the temporally generated atoms as their locations are generated without considering potential bonds. We define this problem as the atom-bond inconsistency problem and claim it is the main reason for current approaches to generating unrealistic 3D molecules. To overcome this problem, we propose a new diffusion model called MolDiff which can generate atoms and bonds simultaneously while still maintaining their consistency by explicitly modeling the dependence between their relationships. We evaluated the generation ability of our proposed model and the quality of the generated molecules using criteria related to both geometry and chemical properties. The empirical studies showed that our model outperforms previous approaches, achieving a three-fold improvement in success rate and generating molecules with significantly better quality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-peng23b, title = {{M}ol{D}iff: Addressing the Atom-Bond Inconsistency Problem in 3{D} Molecule Diffusion Generation}, author = {Peng, Xingang and Guan, Jiaqi and Liu, Qiang and Ma, Jianzhu}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {27611--27629}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/peng23b/peng23b.pdf}, url = {https://proceedings.mlr.press/v202/peng23b.html}, abstract = {Deep generative models have recently achieved superior performance in 3D molecule generation. Most of them first generate atoms and then add chemical bonds based on the generated atoms in a post-processing manner. However, there might be no corresponding bond solution for the temporally generated atoms as their locations are generated without considering potential bonds. We define this problem as the atom-bond inconsistency problem and claim it is the main reason for current approaches to generating unrealistic 3D molecules. To overcome this problem, we propose a new diffusion model called MolDiff which can generate atoms and bonds simultaneously while still maintaining their consistency by explicitly modeling the dependence between their relationships. We evaluated the generation ability of our proposed model and the quality of the generated molecules using criteria related to both geometry and chemical properties. The empirical studies showed that our model outperforms previous approaches, achieving a three-fold improvement in success rate and generating molecules with significantly better quality.} }
Endnote
%0 Conference Paper %T MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation %A Xingang Peng %A Jiaqi Guan %A Qiang Liu %A Jianzhu Ma %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-peng23b %I PMLR %P 27611--27629 %U https://proceedings.mlr.press/v202/peng23b.html %V 202 %X Deep generative models have recently achieved superior performance in 3D molecule generation. Most of them first generate atoms and then add chemical bonds based on the generated atoms in a post-processing manner. However, there might be no corresponding bond solution for the temporally generated atoms as their locations are generated without considering potential bonds. We define this problem as the atom-bond inconsistency problem and claim it is the main reason for current approaches to generating unrealistic 3D molecules. To overcome this problem, we propose a new diffusion model called MolDiff which can generate atoms and bonds simultaneously while still maintaining their consistency by explicitly modeling the dependence between their relationships. We evaluated the generation ability of our proposed model and the quality of the generated molecules using criteria related to both geometry and chemical properties. The empirical studies showed that our model outperforms previous approaches, achieving a three-fold improvement in success rate and generating molecules with significantly better quality.
APA
Peng, X., Guan, J., Liu, Q. & Ma, J.. (2023). MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:27611-27629 Available from https://proceedings.mlr.press/v202/peng23b.html.

Related Material