LitMOF:用于文献验证的金属有机框架数据库校正与扩展的LLM多智能体系统
LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion
AI总结:
提出LitMOF框架,利用大语言模型多智能体从原始文献验证并修复MOF数据库中的结构错误,成功修复9227个无效条目并发现8771个新MOF,通过直接空气捕获案例证明结构错误严重影响材料筛选可靠性。
摘要:
金属有机框架(MOF)数据库通过实验沉积和大规模文献提取快速增长,但最近的分析表明,近一半的条目包含严重的结构错误。这些不准确性通过高通量筛选和机器学习工作流程传播,限制了数据驱动的MOF发现的可靠性。纠正此类错误异常困难,因为真正的修复需要整合晶体学文件、合成描述以及散布在文献中的上下文证据。在此,我们介绍LitMOF,一个由大语言模型驱动的多智能体框架,它直接从原始文献验证晶体学信息,并与数据库条目交叉验证以修复结构错误。将LitMOF应用于实验MOF数据库(CSD MOF子集),我们构建了LitMOF-DB,一个包含189,567个计算就绪结构的精选集合,包括成功修复的9,227个无效条目,占最新CoRE MOF DB中源自CSD的非计算就绪MOF的69.1%。此外,该系统发现了现有资源中缺失的8,771个实验报道的MOF,显著扩展了已知的实验设计空间。以直接空气捕获筛选为案例,我们证明结构错误严重扭曲了预测的吸附能和CO2/H2O选择性,导致材料的系统性误排序、假阳性以及高性能候选者的遗漏。这项工作为自纠正科学数据库建立了一条可扩展的路径,并为材料科学中大语言模型驱动的策展提供了一种通用方法。
英文摘要:
Metal-organic framework (MOF) databases have grown rapidly through experimental deposition and large-scale literature extraction, but recent analyses show that nearly half of their entries contain substantial structural errors. These inaccuracies propagate through high-throughput screening and machine-learning workflows, limiting the reliability of data-driven MOF discovery. Correcting such errors is exceptionally difficult because true repairs require integrating crystallographic files, synthesis descriptions, and contextual evidence scattered across the literature. Here we introduce LitMOF, a large language model-driven multi-agent framework that validates crystallographic information directly from the original literature and cross-validates it with database entries to repair structural errors. Applying LitMOF to the experimental MOF database (the CSD MOF Subset), we constructed LitMOF-DB, a curated set of 189,567 computation-ready structures, including the successful repair of 9,227 invalid entries, which accounts for 69.1% of the CSD-derived not-computation-ready MOFs in the latest CoRE MOF DB. Additionally, the system uncovered 8,771 experimentally reported MOFs absent from existing resources, substantially expanding the known experimental design space. Using direct air capture screening as a case study, we demonstrate that structural errors severely distort predicted adsorption energies and CO2/H2O selectivity, leading to systematic misranking of materials, false positives, and the omission of high-performance candidates. This work establishes a scalable pathway toward self-correcting scientific databases and a generalizable approach for LLM-driven curation in materials science.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。