Study of Deep Generative Models for Inorganic Chemical Compositions

Generative models based on generative adversarial networks (GANs) and variational autoencoders (VAEs) have been widely studied in the fields of image generation, speech generation, and drug discovery, but, only a few studies have focused on the generation of inorganic materials. Such studies use the crystal structures of materials, but material researchers rarely store this information. Thus, we generate chemical compositions without using crystal information. We use a conditional VAE (CondVAE) and a conditional GAN (CondGAN) and show that CondGAN using the bag-of-atom representation with physical descriptors generates better compositions than other generative models. Also, we evaluate the effectiveness of the Metropolis-Hastings-based atomic valency modification and the extrapolation performance, which is important to material discovery.

[1]  K-R Müller,et al.  SchNet - A deep learning architecture for molecules and materials. , 2017, The Journal of chemical physics.

[2]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[3]  Chi Chen,et al.  Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals , 2018, Chemistry of Materials.

[4]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[5]  Atsuto Seko,et al.  Representation of compounds for machine-learning prediction of physical properties , 2016, 1611.08645.

[6]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[7]  Nataliya Sokolovska,et al.  CrystalGAN: Learning to Discover Crystallographic Structures with Generative Adversarial Networks , 2018, AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering.

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

[9]  Richard S. Zemel,et al.  Learning Latent Subspaces in Variational Autoencoders , 2018, NeurIPS.

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

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

[12]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[13]  Ian Foster,et al.  Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery , 2018 .

[14]  Motoki Abe,et al.  GraphNVP: An Invertible Flow Model for Generating Molecular Graphs , 2019, ArXiv.

[15]  Ali Razavi,et al.  Preventing Posterior Collapse with delta-VAEs , 2019, ICLR.

[16]  Jin Woo Kim,et al.  Molecular generative model based on conditional variational autoencoder for de novo molecular design , 2018, Journal of Cheminformatics.

[17]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[18]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[19]  Kristin A. Persson,et al.  Commentary: The Materials Project: A materials genome approach to accelerating materials innovation , 2013 .

[20]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[21]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[22]  Yoshua Bengio,et al.  DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation , 2018, ArXiv.

[23]  Yoshua Bengio,et al.  Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures , 2019, ArXiv.

[24]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[25]  Xavier Bresson,et al.  A Two-Step Graph Convolutional Decoder for Molecule Generation , 2019, ArXiv.

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

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

[28]  Anubhav Jain,et al.  Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis , 2012 .

[29]  Rafael Gómez-Bombarelli,et al.  Generative Models for Automatic Chemical Design , 2019, Machine Learning Meets Quantum Physics.

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

[31]  Alán Aspuru-Guzik,et al.  Inverse Design of Solid-State Materials via a Continuous Representation , 2019, Matter.

[32]  Kaushalya Madhawa,et al.  GraphNVP: an Invertible Flow-based Model for Generating Molecular Graphs , 2019 .

[33]  Alán Aspuru-Guzik,et al.  Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC) , 2017 .