Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models
For researchers and industry practitioners working on MOF discovery, this provides a data-driven tool to triage scalable syntheses, addressing a key bottleneck between lab discovery and industrial deployment.
The authors tackled the problem of predicting scalability of metal-organic framework (MOF) syntheses from literature data. Their model, ESU-MOF, achieves 91.4% accuracy in predicting scalability potential.
Scalable synthesis remains the gate between MOF discovery and industrial deployment, as scale-up know-how is fragmented across disparate reports. We introduce ESU-MOF, a literature-mined dataset and a positive-unlabeled learning strategy that fine-tunes large language models to predict scalability potential with 91.4% accuracy, enabling rapid data-driven triage for industrial MOF discovery.