MolGrapher: Graph-based Visual Recognition of Chemical Structures
This work addresses the problem of accelerating materials and drug discovery by enabling more accurate automated analysis of chemical literature, though it is incremental as it builds on existing graph-based and learning techniques.
The authors tackled the challenge of automatically parsing chemical structures from figures in scientific literature by introducing MolGrapher, a graph-based visual recognition system that uses a deep keypoint detector and Graph Neural Network, achieving significant performance improvements over existing methods on five datasets.
The automatic analysis of chemical literature has immense potential to accelerate the discovery of new materials and drugs. Much of the critical information in patent documents and scientific articles is contained in figures, depicting the molecule structures. However, automatically parsing the exact chemical structure is a formidable challenge, due to the amount of detailed information, the diversity of drawing styles, and the need for training data. In this work, we introduce MolGrapher to recognize chemical structures visually. First, a deep keypoint detector detects the atoms. Second, we treat all candidate atoms and bonds as nodes and put them in a graph. This construct allows a natural graph representation of the molecule. Last, we classify atom and bond nodes in the graph with a Graph Neural Network. To address the lack of real training data, we propose a synthetic data generation pipeline producing diverse and realistic results. In addition, we introduce a large-scale benchmark of annotated real molecule images, USPTO-30K, to spur research on this critical topic. Extensive experiments on five datasets show that our approach significantly outperforms classical and learning-based methods in most settings. Code, models, and datasets are available.