Message Passing Neural Networks for Partial Charge Assignment to Metal–Organic Frameworks

2020 ◽  
Vol 124 (35) ◽  
pp. 19070-19082
Author(s):  
Ali Raza ◽  
Arni Sturluson ◽  
Cory M. Simon ◽  
Xiaoli Fern
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
Metal Organic Frameworks ◽  
Partial Charge ◽  
Charge Assignment ◽  
Metal Organic

scholarly journals Role of partial charge assignment methods in high-throughput screening of MOF adsorbents and membranes for CO2/CH4 separation

2020 ◽  
Vol 5 (2) ◽  
pp. 532-543 ◽  
Author(s):  
Cigdem Altintas ◽  
Seda Keskin
Keyword(s):  
High Throughput ◽  
High Throughput Screening ◽  
Metal Organic Frameworks ◽  
Partial Charge ◽  
Computational Screening ◽  
Charge Assignment ◽  
Metal Organic

The role of partial charge assignment methods used in high-throughput computational screening of metal organic frameworks (MOFs) for CO2/CH4 separation is examined.

Message Passing Neural Networks for Partial Charge Assignment to Metal-Organic Frameworks

2020 ◽  
Author(s):  
Ali Raza ◽  
Arni Sturluson ◽  
Cory Simon ◽  
Xiaoli Fern
Keyword(s):  
Electronic Structure ◽  
Message Passing ◽  
Gas Adsorption ◽  
Metal Organic Frameworks ◽  
Computational Cost ◽  
Electronic Structure Calculations ◽  
High Fidelity ◽  
Partial Charges ◽  
Metal Organic ◽  
Structure Calculations

Virtual screenings can accelerate and reduce the cost of discovering metal-organic frameworks (MOFs) for their applications in gas storage, separation, and sensing. In molecular simulations of gas adsorption/diffusion in MOFs, the adsorbate-MOF electrostatic interaction is typically modeled by placing partial point charges on the atoms of the MOF. For the virtual screening of large libraries of MOFs, it is critical to develop computationally inexpensive methods to assign atomic partial charges to MOFs that accurately reproduce the electrostatic potential in their pores. Herein, we design and train a message passing neural network (MPNN) to predict the atomic partial charges on MOFs under a charge neutral constraint. A set of ca. 2,250 MOFs labeled with high-fidelity partial charges, derived from periodic electronic structure calculations, serves as training examples. In an end-to-end manner, from charge-labeled crystal graphs representing MOFs, our MPNN machine-learns features of the local bonding environments of the atoms and learns to predict partial atomic charges from these features. Our trained MPNN assigns high-fidelity partial point charges to MOFs with orders of magnitude lower computational cost than electronic structure calculations. To enhance the accuracy of virtual screenings of large libraries of MOFs for their adsorption-based applications, we make our trained MPNN model and MPNN-charge-assigned computation-ready, experimental MOF structures publicly available.<br>

Message Passing Neural Networks for Partial Charge Assignment to Metal-Organic Frameworks

2020 ◽  
Author(s):  
Ali Raza ◽  
Arni Sturluson ◽  
Cory Simon ◽  
Xiaoli Fern
Keyword(s):  
Electronic Structure ◽  
Message Passing ◽  
Gas Adsorption ◽  
Metal Organic Frameworks ◽  
Computational Cost ◽  
Electronic Structure Calculations ◽  
High Fidelity ◽  
Partial Charges ◽  
Metal Organic ◽  
Structure Calculations

Virtual screenings can accelerate and reduce the cost of discovering metal-organic frameworks (MOFs) for their applications in gas storage, separation, and sensing. In molecular simulations of gas adsorption/diffusion in MOFs, the adsorbate-MOF electrostatic interaction is typically modeled by placing partial point charges on the atoms of the MOF. For the virtual screening of large libraries of MOFs, it is critical to develop computationally inexpensive methods to assign atomic partial charges to MOFs that accurately reproduce the electrostatic potential in their pores. Herein, we design and train a message passing neural network (MPNN) to predict the atomic partial charges on MOFs under a charge neutral constraint. A set of ca. 2,250 MOFs labeled with high-fidelity partial charges, derived from periodic electronic structure calculations, serves as training examples. In an end-to-end manner, from charge-labeled crystal graphs representing MOFs, our MPNN machine-learns features of the local bonding environments of the atoms and learns to predict partial atomic charges from these features. Our trained MPNN assigns high-fidelity partial point charges to MOFs with orders of magnitude lower computational cost than electronic structure calculations. To enhance the accuracy of virtual screenings of large libraries of MOFs for their adsorption-based applications, we make our trained MPNN model and MPNN-charge-assigned computation-ready, experimental MOF structures publicly available.<br>

Metal-Organic Frameworks

2021 ◽  
Author(s):  
Lars Öhrström ◽  
Francoise M. Amombo Noa
Keyword(s):  
Metal Organic Frameworks ◽  
Metal Organic

Substrate templated synthesis of single-phase and uniform Zr-porphyrin-based metal–organic frameworks

2020 ◽  
Vol 7 (1) ◽  
pp. 221-231
Author(s):  
Seong Won Hong ◽  
Ju Won Paik ◽  
Dongju Seo ◽  
Jae-Min Oh ◽  
Young Kyu Jeong ◽  
...  
Keyword(s):  
Chemical Bath Deposition ◽  
Single Phase ◽  
Metal Organic Frameworks ◽  
Templated Synthesis ◽  
Pore Structures ◽  
Phase Pure ◽  
Metal Organic ◽  
Cbd Method

We successfully demonstrate that the chemical bath deposition (CBD) method is a versatile method for synthesizing phase-pure and uniform MOFs by controlling their nucleation stages and pore structures.

Sign in / Sign up

Export Citation Format

Share Document