Torsional Diffusion for Molecular Conformer Generation

Molecular conformer generation is a fundamental task in computational chemistry. Several machine learning approaches have been developed, but none have outperformed state-of-the-art cheminformatics methods. We propose torsional diffusion, a novel diffusion framework that operates on the space of torsion angles via a diffusion process on the hypertorus and an extrinsic-to-intrinsic score model. On a standard benchmark of drug-like molecules, torsional diffusion generates superior conformer ensembles compared to machine learning and cheminformatics methods in terms of both RMSD and chemical properties, and is orders of magnitude faster than previous diffusion-based models. Moreover, our model provides exact likelihoods, which we employ to build the first generalizable Boltzmann generator. Code is available at https://github.com/gcorso/torsional-diffusion.

[1]  Bowen Jing,et al.  Subspace Diffusion Generative Models , 2022, ArXiv.

[2]  S. Ermon,et al.  GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation , 2022, ICLR.

[3]  T. Jaakkola,et al.  EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction , 2022, ICML.

[4]  Valentin De Bortoli,et al.  Riemannian Score-Based Generative Modeling , 2022, ArXiv.

[5]  R. B. Angel.  Spacetime and Geometry , 2022, A Student's Guide to Special Relativity.

[6]  Tim Salimans,et al.  Progressive Distillation for Fast Sampling of Diffusion Models , 2022, ICLR.

[7]  Jonathan P. Mailoa,et al.  E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials , 2021, Nature Communications.

[8]  Simon Axelrod,et al.  GEOM: Energy-annotated molecular conformations for property prediction and molecular generation , 2020, ArXiv.

[9]  Jos'e Miguel Hern'andez-Lobato,et al.  Bootstrap Your Flow , 2021, ArXiv.

[10]  Jonas Köhler,et al.  Smooth Normalizing Flows , 2021, NeurIPS.

[11]  Jan Kautz,et al.  Score-based Generative Modeling in Latent Space , 2021, NeurIPS.

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

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

[14]  Jian Tang,et al.  Learning Gradient Fields for Molecular Conformation Generation , 2021, ICML.

[15]  E. A. del Rio-Chanona,et al.  A geometric deep learning approach to predict binding conformations of bioactive molecules , 2021, Nature Machine Intelligence.

[16]  Max Welling,et al.  E(n) Equivariant Graph Neural Networks , 2021, ICML.

[17]  Prafulla Dhariwal,et al.  Improved Denoising Diffusion Probabilistic Models , 2021, ICML.

[18]  Abhishek Kumar,et al.  Score-Based Generative Modeling through Stochastic Differential Equations , 2020, ICLR.

[19]  Raphael J. L. Townshend,et al.  Learning from Protein Structure with Geometric Vector Perceptrons , 2020, ICLR.

[20]  Shitong Luo,et al.  Predicting Molecular Conformation via Dynamic Graph Score Matching , 2021, NeurIPS.

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

[22]  Pieter Abbeel,et al.  Denoising Diffusion Probabilistic Models , 2020, NeurIPS.

[23]  Stefan Grimme,et al.  Automated exploration of the low-energy chemical space with fast quantum chemical methods. , 2020, Physical chemistry chemical physics : PCCP.

[24]  Yang Song,et al.  Generative Modeling by Estimating Gradients of the Data Distribution , 2019, NeurIPS.

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

[26]  C. Bannwarth,et al.  GFN2-xTB-An Accurate and Broadly Parametrized Self-Consistent Tight-Binding Quantum Chemical Method with Multipole Electrostatics and Density-Dependent Dispersion Contributions. , 2018, Journal of chemical theory and computation.

[27]  Li Li,et al.  Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds , 2018, ArXiv.

[28]  Patrick McCabe,et al.  Knowledge-Based Conformer Generation Using the Cambridge Structural Database , 2018, J. Chem. Inf. Model..

[29]  P. Hawkins.  Conformation Generation: The State of the Art , 2017, J. Chem. Inf. Model..

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

[31]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[32]  David Frederic Crouse,et al.  On implementing 2D rectangular assignment algorithms , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[33]  Sereina Riniker,et al.  Better Informed Distance Geometry: Using What We Know To Improve Conformation Generation , 2015, J. Chem. Inf. Model..

[34]  Anthony Nicholls,et al.  Conformer Generation with OMEGA: Learning from the Data Set and the Analysis of Failures , 2012, J. Chem. Inf. Model..

[35]  G. Chirikjian.  Stochastic Models, Information Theory, and Lie Groups, Volume 2 , 2012 .

[36]  Evan Bolton,et al.  PubChem3D: Conformer generation , 2011, J. Cheminformatics.

[37]  Pierre Tufféry,et al.  Frog2: Efficient 3D conformation ensemble generator for small compounds , 2010, Nucleic Acids Res..

[38]  Benjamin A. Ellingson,et al.  Conformer Generation with OMEGA: Algorithm and Validation Using High Quality Structures from the Protein Databank and Cambridge Structural Database , 2010, J. Chem. Inf. Model..

[39]  Maria A Miteva,et al.  DG-AMMOS: A New tool to generate 3D conformation of small molecules using Distance Geometry and Automated Molecular Mechanics Optimization for in silico Screening , 2009, BMC chemical biology.

[40]  Stephen P. Hale,et al.  The exploration of macrocycles for drug discovery — an underexploited structural class , 2008, Nature Reviews Drug Discovery.

[41]  Jiabo Li,et al.  CAESAR: A New Conformer Generation Algorithm Based on Recursive Buildup and Local Rotational Symmetry Consideration , 2007, J. Chem. Inf. Model..

[42]  Martin Quack,et al.  How important is parity violation for molecular and biomolecular chirality? , 2002, Angewandte Chemie.

[43]  Radford M. Neal.  Annealed importance sampling , 1998, Stat. Comput..

[44]  T. Halgren.  Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94 , 1996, J. Comput. Chem..

[45]  M. Hutchinson.  A stochastic estimator of the trace of the influence matrix for laplacian smoothing splines , 1989 .

[46]  B. Anderson.  Reverse-time diffusion equation models , 1982 .