These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
MGM_v2.pdf (1.57 MB)

Masked Graph Modeling for Molecule Generation

revised on 19.01.2021, 23:05 and posted on 21.01.2021, 04:58 by Omar Mahmood, Elman Mansimov, Richard Bonneau, Kyunghyun Cho
De novo, in-silico design of molecules is a challenging problem with applications in drug discovery and material design.
Here, we introduce a masked graph model which learns a distribution over graphs by capturing all possible conditional distributions over unobserved nodes and edges given observed ones.
We train our masked graph model on existing molecular graphs and then sample novel molecular graphs from it by iteratively masking and replacing different parts of initialized graphs.
We evaluate our approach on the QM9 and ChEMBL datasets using the distribution-learning benchmark from the GuacaMol framework.
The benchmark contains five metrics: the validity, uniqueness, novelty, KL-divergence and Fréchet ChemNet Distance scores, the last two of which are measures of the similarity of the generated samples to the training, validation and test distributions.
We find that KL-divergence and Fréchet ChemNet Distance scores are anti-correlated with novelty scores. By varying generation initialization and the fraction of the graph masked and replaced at each generation step, we can increase the Fréchet score at the cost of novelty.
In this way, we show that our model offers transparent and tunable control of the trade-off between these metrics, a point of control currently lacking in other approaches to molecular graph generation.
We observe that our model outperforms previously proposed graph-based approaches and is competitive with SMILES-based approaches.
Finally, we show that our model can generate molecules with desired values of specified properties while maintaining physiochemical similarity to molecules from the training distribution.


Email Address of Submitting Author


New York University



ORCID For Submitting Author


Declaration of Conflict of Interest

No conflict of interest