Inverse design of porous materials using artificial neural networks

We have developed a user-desired generative adversarial network and used them to generate 121 zeolite materials. Generating optimal nanomaterials using artificial neural networks can potentially lead to a notable revolution in future materials design. Although progress has been made in creating small and simple molecules, complex materials such as crystalline porous materials have yet to be generated using any of the neural networks. Here, we have implemented a generative adversarial network that uses a training set of 31,713 known zeolites to produce 121 crystalline porous materials. Our neural network takes in inputs in the form of energy and material dimensions, and we show that zeolites with a user-desired range of 4 kJ/mol methane heat of adsorption can be reliably produced using our neural network. The fine-tuning of user-desired capability can potentially accelerate materials development as it demonstrates a successful case of inverse design of porous materials.

[1]  Jihan Kim,et al.  Predicting performance limits of methane gas storage in zeolites with an artificial neural network , 2019, Journal of Materials Chemistry A.

[2]  B. Sumpter,et al.  Prediction of Carbon Dioxide Adsorption via Deep Learning. , 2018, Angewandte Chemie.

[3]  Michael Gastegger,et al.  Generating equilibrium molecules with deep neural networks , 2018, ArXiv.

[4]  Rochus Schmid,et al.  TopoFF: MOF structure prediction using specifically optimized blueprints. , 2018, Faraday discussions.

[5]  Qi Liu,et al.  Advances and challenges in deep generative models for de novo molecule generation , 2018, WIREs Computational Molecular Science.

[6]  Alán Aspuru-Guzik,et al.  Inverse molecular design using machine learning: Generative models for matter engineering , 2018, Science.

[7]  Nicola De Cao,et al.  MolGAN: An implicit generative model for small molecular graphs , 2018, ArXiv.

[8]  Alán Aspuru-Guzik,et al.  Reinforced Adversarial Neural Computer for de Novo Molecular Design , 2018, J. Chem. Inf. Model..

[9]  Jakoah Brgoch,et al.  Predicting the Band Gaps of Inorganic Solids by Machine Learning. , 2018, The journal of physical chemistry letters.

[10]  Thierry Kogej,et al.  Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks , 2017, ACS central science.

[11]  Jeffrey C Grossman,et al.  Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. , 2017, Physical review letters.

[12]  Alán Aspuru-Guzik,et al.  Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules , 2016, ACS central science.

[13]  Siqi Shi,et al.  The onset temperature (Tg) of AsxSe1−x glasses transition prediction: A comparison of topological and regression analysis methods , 2017 .

[14]  Jihan Kim,et al.  Excavating hidden adsorption sites in metal-organic frameworks using rational defect engineering , 2017, Nature Communications.

[15]  Yue Liu,et al.  Materials discovery and design using machine learning , 2017 .

[16]  Sergey Nikolenko,et al.  druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico. , 2017, Molecular pharmaceutics.

[17]  Jihan Kim,et al.  Modeling adsorption properties of structurally deformed metal–organic frameworks using structure–property map , 2017, Proceedings of the National Academy of Sciences.

[18]  Alán Aspuru-Guzik,et al.  Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models , 2017, ArXiv.

[19]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[20]  Matt J. Kusner,et al.  Grammar Variational Autoencoder , 2017, ICML.

[21]  Fengqi You,et al.  In silico discovery of metal-organic frameworks for precombustion CO2 capture using a genetic algorithm , 2016, Science Advances.

[22]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[23]  Saratchandra Babu Mukkamala,et al.  A review on contemporary Metal–Organic Framework materials , 2016 .

[24]  Siqi Shi,et al.  Multi-scale computation methods: Their applications in lithium-ion battery research and development , 2016 .

[25]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[26]  Richard L. Martin,et al.  In silico prediction of MOFs with high deliverable capacity or internal surface area. , 2015, Physical chemistry chemical physics : PCCP.

[27]  Maciej Haranczyk,et al.  In Silico Discovery of High Deliverable Capacity Metal–Organic Frameworks , 2015 .

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Maciej Haranczyk,et al.  In Silico Design of Three-Dimensional Porous Covalent Organic Frameworks via Known Synthesis Routes and Commercially Available Species , 2014 .

[30]  Tom K Woo,et al.  Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO2 Capture. , 2014, The journal of physical chemistry letters.

[31]  G. Qian,et al.  Methane storage in metal-organic frameworks. , 2014, Chemical Society Reviews.

[32]  Michael O’Keeffe,et al.  The Chemistry and Applications of Metal-Organic Frameworks , 2013, Science.

[33]  Hong-Cai Zhou,et al.  Methane storage in advanced porous materials. , 2012, Chemical Society reviews.

[34]  Abhoyjit S Bhown,et al.  In silico screening of carbon-capture materials. , 2012, Nature materials.

[35]  Oliver Rübel,et al.  High-Throughput Characterization of Porous Materials Using Graphics Processing Units. , 2012, Journal of chemical theory and computation.

[36]  C. Wilmer,et al.  Large-scale screening of hypothetical metal-organic frameworks. , 2012, Nature chemistry.

[37]  Michael W Deem,et al.  A database of new zeolite-like materials. , 2011, Physical chemistry chemical physics : PCCP.

[38]  R. Krishna,et al.  A computational study of CO2, N2, and CH4 adsorption in zeolites , 2007 .

[39]  C. Ania,et al.  A computational study of CO 2 , N 2 , and CH 4 adsorption in zeolites , 2007 .

[40]  Michael W. Deem,et al.  Toward a Database of Hypothetical Zeolite Structures , 2006 .

[41]  Julian D. Gale,et al.  The General Utility Lattice Program (GULP) , 2003 .

[42]  W. Goddard,et al.  UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations , 1992 .

[43]  Klaus-Peter Schröder,et al.  Bridging hydrodyl groups in zeolitic catalysts: a computer simulation of their structure, vibrational properties and acidity in protonated faujasites (HY zeolites) , 1992 .

[44]  W. M. Meier,et al.  The topology of three-dimensional 4-connected nets: Classification of zeolite framework types using coordination sequences , 1979 .