Atom-Level Optical Chemical Structure Recognition with Limited Supervision
This addresses a challenge in drug development by improving generalization and data efficiency for chemical structure recognition, though it is incremental as it builds on existing methods with a novel localization feature.
The paper tackles the problem of chemical structure recognition from images, particularly in data-scarce domains like hand-drawn molecules, by proposing a tool that achieves state-of-the-art performance with limited supervision and provides atom-level localization.
Identifying the chemical structure from a graphical representation, or image, of a molecule is a challenging pattern recognition task that would greatly benefit drug development. Yet, existing methods for chemical structure recognition do not typically generalize well, and show diminished effectiveness when confronted with domains where data is sparse, or costly to generate, such as hand-drawn molecule images. To address this limitation, we propose a new chemical structure recognition tool that delivers state-of-the-art performance and can adapt to new domains with a limited number of data samples and supervision. Unlike previous approaches, our method provides atom-level localization, and can therefore segment the image into the different atoms and bonds. Our model is the first model to perform OCSR with atom-level entity detection with only SMILES supervision. Through rigorous and extensive benchmarking, we demonstrate the preeminence of our chemical structure recognition approach in terms of data efficiency, accuracy, and atom-level entity prediction.