Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules

Deep learning has proven to yield fast and accurate predictions of quantum-chemical properties to accelerate the discovery of novel molecules and materials. As an exhaustive exploration of the vast chemical space is still infeasible, we require generative models that guide our search towards systems with desired properties. While graph-based models have previously been proposed, they are restricted by a lack of spatial information such that they are unable to recognize spatial isomerism and non-bonded interactions. Here, we introduce a generative neural network for 3d point sets that respects the rotational invariance of the targeted structures. We apply it to the generation of molecules and demonstrate its ability to approximate the distribution of equilibrium structures using spatial metrics as well as established measures from chemoinformatics. As our model is able to capture the complex relationship between 3d geometry and electronic properties, we bias the distribution of the generator towards molecules with a small HOMO-LUMO gap - an important property for the design of organic solar cells.

[1]  Alexandre Tkatchenko,et al.  Quantum-chemical insights from deep tensor neural networks , 2016, Nature Communications.

[2]  Regina Barzilay,et al.  Learning Multimodal Graph-to-Graph Translation for Molecular Optimization , 2018, ICLR.

[3]  K-R Müller,et al.  SchNetPack: A Deep Learning Toolbox For Atomistic Systems. , 2018, Journal of chemical theory and computation.

[4]  Nikos Komodakis,et al.  GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders , 2018, ICANN.

[5]  Michael Gastegger,et al.  Machine learning molecular dynamics for the simulation of infrared spectra† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02267k , 2017, Chemical science.

[6]  Marco Häser,et al.  Auxiliary basis sets to approximate Coulomb potentials , 1995 .

[7]  Frank Neese,et al.  The ORCA program system , 2012 .

[8]  Vijay S. Pande,et al.  Massively Multitask Networks for Drug Discovery , 2015, ArXiv.

[9]  Yibo Li,et al.  Multi-objective de novo drug design with conditional graph generative model , 2018, Journal of Cheminformatics.

[10]  Jure Leskovec,et al.  Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation , 2018, NeurIPS.

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

[12]  S. Grimme,et al.  A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu. , 2010, The Journal of chemical physics.

[13]  Klaus-Robert Müller,et al.  SchNet: A continuous-filter convolutional neural network for modeling quantum interactions , 2017, NIPS.

[14]  Parr,et al.  Development of the Colle-Salvetti correlation-energy formula into a functional of the electron density. , 1988, Physical review. B, Condensed matter.

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

[16]  Mikkel N. Schmidt,et al.  Machine learning-based screening of complex molecules for polymer solar cells. , 2018, The Journal of chemical physics.

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

[18]  J. Almlöf,et al.  Integral approximations for LCAO-SCF calculations , 1993 .

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

[20]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[21]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

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

[23]  Kristof T. Schütt,et al.  Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions , 2019, Nature Communications.

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

[25]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[26]  Niloy Ganguly,et al.  NeVAE: A Deep Generative Model for Molecular Graphs , 2018, AAAI.

[27]  A. Becke.  Density-functional thermochemistry. , 1996 .

[28]  Steven Skiena,et al.  Syntax-Directed Variational Autoencoder for Structured Data , 2018, ICLR.

[29]  Jean-Louis Reymond,et al.  Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17 , 2012, J. Chem. Inf. Model..

[30]  Qi Liu,et al.  Constrained Graph Variational Autoencoders for Molecule Design , 2018, NeurIPS.

[31]  Stéphane Mallat,et al.  Solid Harmonic Wavelet Scattering: Predicting Quantum Molecular Energy from Invariant Descriptors of 3D Electronic Densities , 2017, NIPS.

[32]  Jiajun Wu,et al.  Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling , 2016, NIPS.

[33]  Regina Barzilay,et al.  Junction Tree Variational Autoencoder for Molecular Graph Generation , 2018, ICML.

[34]  J. Reymond.  The chemical space project. , 2015, Accounts of chemical research.

[35]  A. Becke.  Density-functional thermochemistry. III. The role of exact exchange , 1993 .

[36]  M. Frisch,et al.  Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields , 1994 .

[37]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.

[38]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[39]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[40]  Leonidas J. Guibas,et al.  Learning Representations and Generative Models for 3D Point Clouds , 2017, ICML.

[41]  Matt J. Kusner,et al.  Learning a Generative Model for Validity in Complex Discrete Structures , 2017, ICLR.

[42]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[43]  F. Weigend,et al.  Balanced basis sets of split valence, triple zeta valence and quadruple zeta valence quality for H to Rn: Design and assessment of accuracy. , 2005, Physical chemistry chemical physics : PCCP.

[44]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[45]  Joseph Gomes,et al.  MoleculeNet: a benchmark for molecular machine learning† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02664a , 2017, Chemical science.

[46]  Pavlo O. Dral,et al.  Quantum chemistry structures and properties of 134 kilo molecules , 2014, Scientific Data.

[47]  S. H. Vosko,et al.  Accurate spin-dependent electron liquid correlation energies for local spin density calculations: a critical analysis , 1980 .

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

[49]  Klaus-Robert Müller,et al.  Machine learning of accurate energy-conserving molecular force fields , 2016, Science Advances.

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

[51]  David Weininger,et al.  SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules , 1988, J. Chem. Inf. Comput. Sci..

[52]  Razvan Pascanu,et al.  Learning Deep Generative Models of Graphs , 2018, ICLR 2018.

[53]  Michael Walter,et al.  The atomic simulation environment-a Python library for working with atoms. , 2017, Journal of physics. Condensed matter : an Institute of Physics journal.

[54]  Olexandr Isayev,et al.  Deep reinforcement learning for de novo drug design , 2017, Science Advances.

[55]  Gaël Varoquaux,et al.  Mayavi: 3D Visualization of Scientific Data , 2010, Computing in Science & Engineering.

[56]  K. Müller,et al.  Towards exact molecular dynamics simulations with machine-learned force fields , 2018, Nature Communications.

[57]  Burke,et al.  Generalized Gradient Approximation Made Simple. , 1996, Physical review letters.

[58]  Chris Morley,et al.  Open Babel: An open chemical toolbox , 2011, J. Cheminformatics.

[59]  Wei-keng Liao,et al.  ElemNet: Deep Learning the Chemistry of Materials From Only Elemental Composition , 2018, Scientific Reports.

[60]  Thomas Blaschke,et al.  Application of Generative Autoencoder in De Novo Molecular Design , 2017, Molecular informatics.

[61]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[62]  Olexandr Isayev,et al.  ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules , 2017, Scientific Data.

[63]  Elman Mansimov,et al.  Molecular Geometry Prediction using a Deep Generative Graph Neural Network , 2019, Scientific Reports.

[64]  Petra Schneider,et al.  Generative Recurrent Networks for De Novo Drug Design , 2017, Molecular informatics.

[65]  Alexander V. Shapeev,et al.  Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning , 2018, Physical Review B.