Machine Learning the Quantum-Chemical Properties of Metal–Organic Frameworks for Accelerated Materials Discovery with a New Electronic Structure Database

Abstract

<p>Metal–organic frameworks (MOFs) are a widely investigated class of crystalline solids with tunable structures that make it possible to impart specific chemical functionality tailored for a given application. However, the enormous number of possible MOFs that can be synthesized makes it difficult to determine which materials would be the most promising candidates, especially for applications governed by electronic structure properties that are often computationally demanding to simulate and time-consuming to probe experimentally. Here, we have developed the first publicly available quantum-chemical database for MOFs (the “QMOF database”), which consists of properties derived from density functional theory (DFT) for over 14,000 experimentally synthesized MOFs. Throughout this study, we demonstrate how this new database can be used to identify MOFs with targeted electronic structure properties. As a proof-of-concept, we use the QMOF database to evaluate the performance of several machine learning models for the prediction of DFT-computed band gaps and find that crystal graph convolutional neural networks are capable of achieving superior predictive performance, making it possible to circumvent computationally expensive quantum-chemical calculations. We also show how unsupervised learning methods can aid the discovery of otherwise subtle structure–property relationships using the computational findings in this work. We conclude by highlighting several MOFs with low band gaps, a challenging task given the electronically insulating nature of most MOF structures. The data and predictive models generated in this work, as well as the database of MOF structures, should be highly useful to other researchers interested in the predictive design and discovery of MOFs for the many applications dictated by quantum-chemical phenomena.<br></p>

What has scripting ever done for us? The CSD Python application programming interface (API)

“…High numbers of MOF structures from the CSD have been characterized using quantum mechanical methods for training faster machine learning models. These models can, in turn, be used for virtual screening of potential new MOFs (Rosen et al, 2020). Similarly, MOF structures have been annotated with property predictions for understanding the influence of topology type on absorption properties (Moghadam et al, 2020).…”

Molecular excited states through a machine learning lens

“…85,95,98,[102][103][104][105][106][107][108][109][110][111][112][113][114][115] Such studies are also facilitated by the availability of many big databases with these properties. 100,[116][117][118][119][120] One should be aware that orbital energy gaps are a poor approximation for excitation energies. Kohn-Sham energy gaps, for instance, correspond to a zero-order expansion of TD-DFT results.…”

Recommendation System to Predict Missing Adsorption Properties of Nanoporous Materials

“…Finally, recently [53] an autoencoder enabled inverse design [54,55] of NPMs, where one specifies a desired adsorption property, and the machine learning model generates a NPM structure with that property. To enable machine learning approaches to NPM discovery, several open, structured databases [56][57][58] of (i) crystal structure models of NPMs [25,[59][60][61][62][63], (ii) simulated [17,62,64,65] and experimentally measured [19] adsorption properties of NPMs, and (iii) electronic properties of NPMs [66,67], have been curated. Text mining and natural language processing could be used to extract data and knowledge from the literature for machine learning studies as well [68][69][70].…”