直接从化学结构图提取指纹，提升专利文献中的分子检索效率
SubGrapher: Visual Fingerprinting of Chemical Structures
- 用实例分割识别官能团和碳骨架，构建子结构指纹
- 在多种分子图像上实现更优的检索准确率与鲁棒性
- 适合需要从专利图中挖掘分子信息的研究者
从科学文献中自动提取化学结构对药物发现与材料科学等领域的研究具有重要意义。专利文档中的分子信息多以图像形式存在，传统文本搜索难以触及。本文提出SubGrapher，一种针对化学结构图像的视觉指纹提取方法。不同于以往尝试重建完整分子图的光学化学结构识别（OCSR）模型，SubGrapher直接从图像中提取分子指纹。通过基于学习的实例分割技术，识别出官能团与碳骨架，构建基于子结构的指纹以支持化学结构检索。该方法在主流OCSR与指纹提取模型上进行评估，展现出更优的检索性能与跨多样分子图像的鲁棒性。相关数据集、模型与代码均已公开。
原文摘要 · Abstract (English)
Automatic extraction of chemical structures from scientific literature plays a crucial role in accelerating research across fields ranging from drug discovery to materials science. Patent documents, in particular, contain molecular information in visual form, which is often inaccessible through traditional text-based searches. In this work, we introduce SubGrapher, a method for the visual fingerprinting of chemical structure images. Unlike conventional Optical Chemical Structure Recognition (OCSR) models that attempt to reconstruct full molecular graphs, SubGrapher focuses on extracting molecular fingerprints directly from chemical structure images. Using learning-based instance segmentation, SubGrapher identifies functional groups and carbon backbones, constructing a substructure-based fingerprint that enables chemical structure retrieval. Our approach is evaluated against state-of-the-art OCSR and fingerprinting methods, demonstrating superior retrieval performance and robustness across diverse molecular depictions. The dataset, models, and code are publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。