scholarly journals Machine learning the quantum-chemical properties of metal–organic frameworks for accelerated materials discovery

Matter ◽  
2021 ◽  
Author(s):  
Andrew S. Rosen ◽  
Shaelyn M. Iyer ◽  
Debmalya Ray ◽  
Zhenpeng Yao ◽  
Alán Aspuru-Guzik ◽  
...  
Keyword(s):  
Machine Learning ◽  
Quantum Chemical ◽  
Metal Organic Frameworks ◽  
Chemical Properties ◽  
Metal Organic

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

2020 ◽  
Author(s):  
Andrew Rosen ◽  
Shaelyn Iyer ◽  
Debmalya Ray ◽  
Zhenpeng Yao ◽  
Alan Aspuru-Guzik ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electronic Structure ◽  
Quantum Chemical ◽  
Density Functional ◽  
Metal Organic Frameworks ◽  
Band Gaps ◽  
Structure Property ◽  
Specific Chemical ◽  
Metal Organic ◽  
Structure Properties

<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>

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

2020 ◽  
Author(s):  
Andrew Rosen ◽  
Shaelyn Iyer ◽  
Debmalya Ray ◽  
Zhenpeng Yao ◽  
Alan Aspuru-Guzik ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electronic Structure ◽  
Quantum Chemical ◽  
Density Functional ◽  
Metal Organic Frameworks ◽  
Band Gaps ◽  
Structure Property ◽  
Specific Chemical ◽  
Metal Organic ◽  
Structure Properties

<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>

scholarly journals Quantum Chemical Characterization of Structural Single Fe(II) Sites in MIL-Type Metal–Organic Frameworks for the Oxidation of Methane to Methanol and Ethane to Ethanol

ACS Catalysis ◽  
2019 ◽  
Vol 9 (4) ◽  
pp. 2870-2879 ◽  
Author(s):  
Jenny G. Vitillo ◽  
Aditya Bhan ◽  
Christopher J. Cramer ◽  
Connie C. Lu ◽  
Laura Gagliardi
Keyword(s):  
Quantum Chemical ◽  
Metal Organic Frameworks ◽  
Chemical Characterization ◽  
Oxidation Of Methane ◽  
Metal Organic

Tuning Packing, Structural Flexibility, and Porosity in 2D Metal–Organic Frameworks by Metal Node Choice

2019 ◽  
Vol 72 (10) ◽  
pp. 797 ◽  
Author(s):  
Witold M. Bloch ◽  
Christian J. Doonan ◽  
Christopher J. Sumby
Keyword(s):  
Structural Changes ◽  
Metal Organic Frameworks ◽  
Chemical Properties ◽  
Complete Removal ◽  
Structural Flexibility ◽  
X Ray Diffraction ◽  
Metal Centre ◽  
Metal Organic ◽  
Physical And Chemical ◽  
And Chemical Properties

Understanding the key features that determine structural flexibility in metal–organic frameworks (MOFs) is key to exploiting their dynamic physical and chemical properties. We have previously reported a 2D MOF material, CuL1, comprising five-coordinate metal nodes that displays exceptional CO2/N2 selectively (L1=bis(4-(4-carboxyphenyl)-1H-pyrazolyl)methane). Here we examine the effect of utilising six-coordinate metal centres (CoII and NiII) in the synthesis of isostructural MOFs from L1, namely CoL1 and NiL1. The octahedral geometry of the metal centre within the MOF analogues precludes an ideal eclipse of the 2D layers, resulting in an offset stacking, and in certain cases, the formation of 2-fold interpenetrated analogues β-CoL1 and β-NiL1. We used a combination of thermogravimetric analysis (TGA), and powder and single crystal X-ray diffraction (PXRD and SCXRD) to show that desolvation is accompanied by a structural change for NiL1, and complete removal of the coordinated H2O ligands results in a reduction in long-range order. The offset nature of the 2D layers in combination with the structural changes impedes the adsorption of meaningful quantities of gases (N2, CO2), highlighting the importance of a five-coordinate metal centre in achieving optimal pore accessibility for this family of flexible materials.

scholarly journals Quantum Chemistry Meets Machine Learning

2019 ◽  
Vol 73 (12) ◽  
pp. 983-989 ◽  
Author(s):  
Alberto Fabrizio ◽  
Benjamin Meyer ◽  
Raimon Fabregat ◽  
Clemence Corminboeuf
Keyword(s):  
Machine Learning ◽  
Statistical Learning ◽  
Quantum Chemical ◽  
Large Scale ◽  
Organic Molecules ◽  
Chemical Properties ◽  
Learning Approaches ◽  
Energy Landscapes ◽  
Free Energy Landscapes ◽  
Large Scale Screening

In this account, we demonstrate how statistical learning approaches can be leveraged across a range of different quantum chemical areas to transform the scaling, nature, and complexity of the problems that we are tackling. Selected examples illustrate the power brought by kernel-based approaches in the large-scale screening of homogeneous catalysis, the prediction of fundamental quantum chemical properties and the free-energy landscapes of flexible organic molecules. While certainly non-exhaustive, these examples provide an intriguing glimpse into our own research efforts.

Sign in / Sign up

Export Citation Format

Share Document