MinerU.Chem：用于光学化学结构与反应识别的高精度系统
MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition
浏览论文内容
中文总结 AI 辅助
本研究提出MinerU.Chem系统，新增五个化学专用模块，以CARBON为核心实现有机化学结构与反应识别，在MolRecBench-Wild子集上SMILES精确匹配准确率达93.02%，优于对比系统，已集成至MinerU平台。
中文摘要 AI 辅助
在有机化学论文和专利中，分子结构、反应方案及实验条件常以分子结构示意图、反应图和复杂表格或图表形式呈现。这类信息难以被通用文档解析系统直接转换为机器可读数据，这限制了有机化学知识库构建的数据生产，以及化学领域人工智能任务（如反应预测、逆合成、条件推荐、分子性质预测和药物分子设计）的开展。本报告介绍MinerU.Chem，即集成于MinerU在线平台的有机化学文献文档解析系统。该系统基于MinerU通用文档解析流水线构建，新增五个化学专用模块：化学相关性过滤、分子结构检测、分子标识符提取、分子结构识别和反应方案解析。这些模块协同将文档中与有机化学相关的图像区域转换为分子摘要列表和反应摘要列表。对于分子结构识别，MinerU.Chem以CARBON（Complex Atomic Representation and Bonding Object Notation，复杂原子表示与键合对象标记）为核心表示，该表示使识别结果既能保留原始图像的视觉布局和复杂化学语义，又支持MolFile、SMILES等标准下游格式的导出。在MolRecBench-Wild的可SMILES评估子集（N=2,392）上，MinerU.Chem的分子结构识别模块达到93.02%的SMILES精确匹配准确率，较经评估的最优对比系统GPT-5.6-Sol（74.87%）高出18.15个百分点。该系统已集成至MinerU在线平台，可通过指定链接访问。
英文摘要
In organic chemistry papers and patents, molecular structures, reaction schemes, and experimental conditions are often presented as molecular structure depictions, reaction diagrams, and complex tables or figures. Such information is difficult for general-purpose document parsing systems to directly convert into machine-readable data. This limits data production for organic chemistry knowledge base construction and for AI for Chemistry tasks such as reaction prediction, retrosynthesis, condition recommendation, molecular property prediction, and drug molecule design. This report introduces MinerU-Chem, a document parsing system for organic chemistry literature integrated into the MinerU online platform. Built on top of MinerU's general document parsing pipeline, MinerU-Chem adds five chemistry-specific modules: chemistry relevance filtering, molecular structure detection, molecule identifier extraction, molecular structure recognition, and reaction scheme parsing. Together, these modules convert organic-chemistry-related image regions in documents into a Molecule Summary List and a Reaction Summary List. For molecular structure recognition, MinerU-Chem uses CARBON (Complex Atomic Representation and Bonding Object Notation) as its core representation. CARBON enables recognition results to preserve both the visual layout of the original image and complex chemical semantics, while supporting the export of standard downstream formats such as MolFile and SMILES. On the SMILES-evaluable subset of MolRecBench-Wild (N=2,392), MinerU-Chem's molecular structure recognition module achieves a SMILES exact-match accuracy of 93.02%, outperforming the best evaluated comparison system, GPT-5.6-Sol (74.87%), by 18.15 percentage points. The system has been integrated into the MinerU online platform and is available at https://mineru.net/OpenSourceTools/Extractor .
发表机构
- Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
- East China Normal University（华东师范大学）
- Tongji University（同济大学）
- Fudan University（复旦大学）
- East China University of Science and Technology（华东理工大学）
- Beijing University of Posts and Telecommunications（北京邮电大学）
- Shanghai Jiao Tong University（上海交通大学）
- Jilin University（吉林大学）
- Beihang University（北京航空航天大学）
- South China Normal University（华南师范大学）
- Peking University（北京大学）
- Northwestern Polytechnical University（西北工业大学）
机构由 AI 辅助整理，请以论文原文为准。
