MolScribe: Robust Molecular Structure Recognition with Image-to-Graph Generation
Name
2205.14311v2.pdf
Description
Accepted version
Size
1.02 MB
Format
Adobe PDF
Checksum (MD5)
3b296e11be2be3f1b59c637dac18b119
Author(s)
Qian, Yujie
Guo, Jiang
Tu, Zhengkai
Li, Zhening
Coley, Connor W
Barzilay, Regina
Date Issued
April 10, 2023
Journal
Journal of Chemical Information and Modeling
Publisher
American Chemical Society
Citation
Yujie Qian, Jiang Guo, Zhengkai Tu, Zhening Li, Connor W. Coley, and Regina Barzilay. Journal of Chemical Information and Modeling 2023 63 (7), 1925-1934.
Version
Author's final manuscript
Abstract
Molecular structure recognition is the task of translating a molecular image into its graph structure. Significant variation in drawing styles and conventions exhibited in chemical literature poses a significant challenge for automating this task. In this paper, we propose MolScribe, a novel image-to-graph generation model that explicitly predicts atoms and bonds, along with their geometric layouts, to construct the molecular structure. Our model flexibly incorporates symbolic chemistry constraints to recognize chirality and expand abbreviated structures. We further develop data augmentation strategies to enhance the model robustness against domain shifts. In experiments on both synthetic and realistic molecular images, MolScribe significantly outperforms previous models, achieving 76-93% accuracy on public benchmarks. Chemists can also easily verify MolScribe's prediction, informed by its confidence estimation and atom-level alignment with the input image. MolScribe is publicly available through Python and web interfaces: https://github.com/thomas0809/MolScribe.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Chemical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial-ShareAlike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1021/acs.jcim.2c01480
