Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Models
arXiv:2010.08687
Abstract
Machine learning in drug discovery has been focused on virtual screening of molecular libraries using discriminative models. Generative models are an entirely different approach that learn to represent and optimize molecules in a continuous latent space. These methods have been increasingly successful at generating two dimensional molecules as SMILES strings and molecular graphs. In this work, we describe deep generative models of three dimensional molecular structures using atomic density grids and a novel fitting algorithm for converting continuous grids to discrete molecular structures. Our models jointly represent drug-like molecules and their conformations in a latent space that can be explored through interpolation. We are also able to sample diverse sets of molecules based on a given input compound and increase the probability of creating valid, drug-like molecules.
Camera-ready submission to NeurIPS 2020 MLSB workshop
References in corpus (12)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Molecular Graph Convolutions: Moving Beyond Fingerprints
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Autoencoding beyond pixels using a learned similarity metric
- AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
- MolGAN: An implicit generative model for small molecular graphs
- Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
- Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
- Generating valid Euclidean distance matrices
- Generating equilibrium molecules with deep neural networks