Inverse design of 3d molecular structures with conditional generative neural networks

Niklas W. A. Gebauer, 2, 3, ∗ Michael Gastegger, 3 Stefaan S. P. Hessmann, 2 Klaus-Robert Müller, 2, 4, 5 and Kristof T. Schütt 2, † Machine Learning Group, Technische Universität Berlin, 10587 Berlin, Germany Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany BASLEARN – TU Berlin/BASF Joint Lab for Machine Learning, Technische Universität Berlin, 10587 Berlin, Germany Department of Artificial Intelligence, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, Korea Max-Planck-Institut für Informatik, 66123 Saarbrücken, Germany.

[1]  Jos'e Miguel Hern'andez-Lobato,et al.  Reinforcement Learning for Molecular Design Guided by Quantum Mechanics , 2020, ICML.

[2]  Klaus-Robert Müller,et al.  Exploring chemical compound space with quantum-based machine learning , 2020, Nature Reviews Chemistry.

[3]  Christoph J. Brabec,et al.  Design Rules for Donors in Bulk‐Heterojunction Solar Cells—Towards 10 % Energy‐Conversion Efficiency , 2006 .

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

[5]  A. Tkatchenko,et al.  Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems , 2021, Chemical reviews.

[6]  Kristof T. Schütt,et al.  Perspective on integrating machine learning into computational chemistry and materials science. , 2021, The Journal of chemical physics.

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

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

[9]  Jos'e Miguel Hern'andez-Lobato,et al.  Symmetry-Aware Actor-Critic for 3D Molecular Design , 2021, ICLR.

[10]  Daniel C. Elton,et al.  Deep learning for molecular generation and optimization - a review of the state of the art , 2019, Molecular Systems Design & Engineering.

[11]  A. Zunger.  Inverse design in search of materials with target functionalities , 2018 .

[12]  O. A. von Lilienfeld,et al.  Machine learning based energy-free structure predictions of molecules, transition states, and solids , 2021, Nature Communications.

[13]  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.

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

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

[16]  Anubhav Jain,et al.  Novel mixed polyanions lithium-ion battery cathode materials predicted by high-throughput ab initio computations , 2011 .

[17]  P. Hajduk,et al.  A decade of fragment-based drug design: strategic advances and lessons learned , 2007, Nature Reviews Drug Discovery.

[18]  Michael Wand,et al.  Adversarial reverse mapping of condensed-phase molecular structures: Chemical transferability , 2021, APL Materials.

[19]  Yi Zheng,et al.  Rational Drug Design , 2012, Methods in Molecular Biology.

[20]  G. Hunault,et al.  Dataset’s chemical diversity limits the generalizability of machine learning predictions , 2019, Journal of Cheminformatics.

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

[22]  Anders S Christensen,et al.  FCHL revisited: Faster and more accurate quantum machine learning. , 2020, The Journal of chemical physics.

[23]  N. Gebauer,et al.  3D-Scaffold: Deep Learning Framework to Generate 3D Coordinates of Drug-like Molecules with Desired Scaffolds , 2021, bioRxiv.

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

[25]  Regina Barzilay,et al.  GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles , 2021, NeurIPS.

[26]  Mordechai Kornbluth,et al.  SE(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials , 2021, ArXiv.

[27]  Christine Peter,et al.  EncoderMap: Dimensionality Reduction and Generation of Molecule Conformations. , 2019, Journal of chemical theory and computation.

[28]  Frank Noé,et al.  Generating valid Euclidean distance matrices , 2019, ArXiv.

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

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

[31]  Klaus-Robert Müller,et al.  Machine Learning Force Fields , 2020, Chemical reviews.

[32]  Bing Huang,et al.  Quantum machine learning using atom-in-molecule-based fragments selected on the fly , 2017, Nature Chemistry.

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

[34]  José Miguel Hernández-Lobato,et al.  A Generative Model for Molecular Distance Geometry , 2020, ICML.

[35]  Debora S. Marks,et al.  Learning Protein Structure with a Differentiable Simulator , 2018, ICLR.

[36]  V. Batista,et al.  Search for Catalysts by Inverse Design: Artificial Intelligence, Mountain Climbers, and Alchemists. , 2019, Chemical reviews.

[37]  Stephan Günnemann,et al.  Directional Message Passing for Molecular Graphs , 2020, ICLR.

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

[39]  Michael Gastegger,et al.  Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules , 2019, NeurIPS.

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

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

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

[43]  Lu-Ming Duan,et al.  Machine learning meets quantum physics , 2019, Physics Today.

[44]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[45]  Luhua Lai,et al.  Structure-based de novo drug design using 3D deep generative models , 2021, Chemical science.

[46]  F. Neese,et al.  Efficient, approximate and parallel Hartree–Fock and hybrid DFT calculations. A ‘chain-of-spheres’ algorithm for the Hartree–Fock exchange , 2009 .

[47]  Volker Roth,et al.  3DMolNet: A Generative Network for Molecular Structures , 2020, ArXiv.

[48]  Jerzy Leszczynski,et al.  Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network , 2018, Science Advances.

[49]  J. Behler,et al.  Comparing the accuracy of high-dimensional neural network potentials and the systematic molecular fragmentation method: A benchmark study for all-trans alkanes. , 2016, The Journal of chemical physics.

[50]  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.

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

[52]  Demis Hassabis,et al.  Improved protein structure prediction using potentials from deep learning , 2020, Nature.

[53]  Ambuj Tewari,et al.  TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search , 2020, NeurIPS.

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

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

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

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

[58]  Carlos Nieto-Draghi,et al.  Inverse‐QSPR for de novo Design: A Review , 2020, Molecular informatics.

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

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

[61]  Max Welling,et al.  E(n) Equivariant Normalizing Flows for Molecule Generation in 3D , 2021, ArXiv.

[62]  Markus Meuwly,et al.  PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges. , 2019, Journal of chemical theory and computation.

[63]  Jonas Köhler,et al.  Generating stable molecules using imitation and reinforcement learning , 2021, Mach. Learn. Sci. Technol..

[64]  Y. Bengio,et al.  Learning Neural Generative Dynamics for Molecular Conformation Generation , 2021, ICLR.

[65]  Hao Wu,et al.  Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning , 2018, Science.

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

[67]  Oriol Vinyals,et al.  Highly accurate protein structure prediction with AlphaFold , 2021, Nature.

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

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

[70]  Ying Shirley Meng,et al.  Electrodes with High Power and High Capacity for Rechargeable Lithium Batteries , 2006, Science.

[71]  Jian Tang,et al.  An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming , 2021, ICML.

[72]  Mohammed AlQuraishi,et al.  End-to-end differentiable learning of protein structure , 2018, bioRxiv.

[73]  M. Ceriotti,et al.  Machine learning meets chemical physics. , 2021, The Journal of chemical physics.

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

[75]  Frank Noé,et al.  Equivariant Flows: exact likelihood generative learning for symmetric densities , 2020, ICML.

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

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

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

[79]  Douglas A. Keszler,et al.  Inverse Design of High Absorption Thin‐Film Photovoltaic Materials , 2013 .

[80]  Michael Gastegger,et al.  Equivariant message passing for the prediction of tensorial properties and molecular spectra , 2021, ICML.