Data-driven prediction of structure of metal-organic frameworks

TL;DR

This paper introduces a data-driven neural network approach for predicting the structure of metal-organic frameworks, enabling high-throughput exploration of their vast chemical space for applications like gas separation.

Contribution

It presents a novel coarse-grained neural network method for predicting MOF structures based on reticular chemistry principles, addressing scalability issues of ab initio techniques.

Findings

Models showed satisfactory performance in topology prediction

Enhanced accuracy by limiting applicability domain

Identified discrepancies in adsorption capacity among polymorphs

Abstract

Crystal structure prediction (CSP) has proven to be a highly effective route for discovering new materials. Substantial advancements have been made in CSP of inorganic and molecular crystals, while hybrid materials, including metal-organic frameworks (MOFs), have been unfairly overlooked. The ab initio techniques adopted for the CSP of MOFs cannot be scaled to a high-throughput regime, which is required for efficient exploration of the immense chemical space. Here, we propose a data-driven method to tackle current needs of computational MOF discovery. By examining CSP through the lens of reticular chemistry, coarse-grained neural networks were implemented to predict underlying net topology of crystal graphs. The models showed satisfactory performance, which was next enhanced by limiting the applicability domain. Flue gas separation was used as an illustrative example to validate the proposed CSP approach. Several hundred in silico-generated systems revealed a notable discrepancy in adsorption capacity among competing polymorphs.