ARC–MOF: A Diverse Database of Metal-Organic Frameworks with DFT-Derived Partial Atomic Charges and Descriptors for Machine Learning

Abstract

Metal–organic frameworks (MOFs) are a class of crystalline materials composed of metal nodes or clusters connected via semi-rigid organic linkers. Owing to their high-surface area, porosity, and tunability, MOFs have received significant attention for numerous applications such as gas separation and storage. Atomistic simulations and data-driven methods [e.g., machine learning (ML)] have been successfully employed to screen large databases and successfully develop new experimentally synthesized and validated MOFs for CO2 capture. To enable data-driven materials discovery for any application, the first (and arguably most crucial) step is database curation. This work introduces the ab initio REPEAT charge MOF (ARC–MOF) database. This is a database of ∼280,000 MOFs which have been either experimentally characterized or computationally generated, spanning all publicly available MOF databases. A key feature of ARC–MOF is that it contains density functional theory-derived electrostatic potential fitted partial atomic charges for each MOF. Additionally, ARC–MOF contains pre-computed descriptors for out-of-the-box ML applications. An in-depth analysis of the diversity of ARC–MOF with respect to the currently mapped design space of MOFs was performeda critical, yet commonly overlooked aspect of previously reported MOF databases. Using this analysis, balanced subsets from ARC–MOF for various ML purposes have been identified, with a case study of the effect of training set on the ML performance. Other chemical and geometric diversity analyses are presented, with an analysis on the effect of the charge-assignment method on atomistic simulation of the gas uptake in MOFs.

An Ecosystem for Digital Reticular Chemistry

“…Machine learning studies typically need to go through multiple, often iterative stages, all supported by our software library. Collecting a data set. For machine learning efforts to be comparable, consistent data sets, along with measures that mitigate data leakage, are needed. In , we provide a consistent interface to multiple commonly used data sets ,− as well as a completely new data set of adsorption properties, complementing the QMOF database. , Additionally, we implement measures to mitigate the effects of data leakage. Featurizing a material. Most machine learning models only accept inputs of fixed shape.…”

“…In , we provide a consistent interface to multiple commonly used data sets ,− as well as a completely new data set of adsorption properties, complementing the QMOF database. , Additionally, we implement measures to mitigate the effects of data leakage.…”

“…As a first step toward more comparable machine learning for MOFs, our package implements a consistent interface for collections of structures, along with some corresponding properties (e.g., gas adsorption or electronic properties) with which all data sets can be used via the same interface. Our package implements reference data sets based on the QMOF database, , the ARC database, the BW database, ,, the ARABG database, as well as on a subset of the CoRE-MOF database. , …”

Inverse design of metal-organic frameworks for direct air capture of CO2 via deep reinforcement learning

“…drug delivery [6], conductivity [7], and so on. To date, there are more than 100,000 experimentally reported MOF structures [8][9][10] and millions of MOF structures that have been predicted in silico [2,[11][12][13][14][15][16][17][18].…”

“…However, as we are interested in a small subset of top-performing materials, most of the effort in these brute-force methods is spent on computing properties of those materials that are not interesting. As the number of structures in these databases has grown significantly, several groups have started taking a different approach in searching more efficiently within this infinite chemical space of MOFs, using methods such as diversity-driven searches [16,17,20], and active learning based searches [19,21].…”