Journal
CHEMICAL SCIENCE
Volume 12, Issue 42, Pages 14174-14181Publisher
ROYAL SOC CHEMISTRY
DOI: 10.1039/d1sc01839f
Keywords
-
Categories
Funding
- Bayer AG Life Science Collaboration (DeepMinds)
- Bayer AG Life Science Collaboration (Explainable AI)
- Bayer AG's PhD scholarships
- European Commission under the Horizon2020 Framework Program for Research and Innovation [963845, 956832]
- Marie Curie Actions (MSCA) [956832] Funding Source: Marie Curie Actions (MSCA)
Ask authors/readers for more resources
The paper introduces a model that combines deep convolutional neural network learning and a pre-trained decoder to accurately translate molecular images into SMILES representation. Evaluation shows that the model can correctly translate up to 88% of molecular images.
The automatic recognition of the molecular content of a molecule's graphical depiction is an extremely challenging problem that remains largely unsolved despite decades of research. Recent advances in neural machine translation enable the auto-encoding of molecular structures in a continuous vector space of fixed size (latent representation) with low reconstruction errors. In this paper, we present a fast and accurate model combining deep convolutional neural network learning from molecule depictions and a pre-trained decoder that translates the latent representation into the SMILES representation of the molecules. This combination allows us to precisely infer a molecular structure from an image. Our rigorous evaluation shows that Img2Mol is able to correctly translate up to 88% of the molecular depictions into their SMILES representation. A pretrained version of Img2Mol is made publicly available on GitHub for non-commercial users.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available