MOFSimplify: Machine Learning Models with Extracted Stability Data of Three Thousand Metal-Organic Frameworks

TL;DR

This paper introduces MOFSimplify, a workflow that uses NLP to extract stability data from MOF literature, creating a dataset for training ML models to predict MOF stability with a web interface for community engagement.

Contribution

It presents a novel NLP-based data extraction pipeline and ML models for MOF stability prediction, along with an accessible web platform for community use and feedback.

Findings

Extracted over 2,000 solvent removal stability measures.

Collected 3,000 thermal decomposition temperatures.

ML models accurately predict MOF stability with quantified uncertainty.

Abstract

We report a workflow and the output of a natural language processing (NLP)-based procedure to mine the extant metal-organic framework (MOF) literature describing structurally characterized MOFs and their solvent removal and thermal stabilities. We obtain over 2,000 solvent removal stability measures from text mining and 3,000 thermal decomposition temperatures from thermogravimetric analysis data. We assess the validity of our NLP methods and the accuracy of our extracted data by comparing to a hand-labeled subset. Machine learning (ML, i.e. artificial neural network) models trained on this data using graph- and pore-geometry-based representations enable prediction of stability on new MOFs with quantified uncertainty. Our web interface, MOFSimplify, provides users access to our curated data and enables them to harness that data for predictions on new MOFs. MOFSimplify also encourages community feedback on existing data and on ML model predictions for community-based active learning for improved MOF stability models.