• Corpus ID: 227162254

Symmetry-Aware Actor-Critic for 3D Molecular Design

@article{Simm2021SymmetryAwareAF,
  title={Symmetry-Aware Actor-Critic for 3D Molecular Design},
  author={Gregor N. C. Simm and Robert Pinsler and G{\'a}bor Cs{\'a}nyi and Jos{\'e} Miguel Hern{\'a}ndez-Lobato},
  journal={ArXiv},
  year={2021},
  volume={abs/2011.12747}
}
Automating molecular design using deep reinforcement learning (RL) has the potential to greatly accelerate the search for novel materials. Despite recent progress on leveraging graph representations to design molecules, such methods are fundamentally limited by the lack of three-dimensional (3D) information. In light of this, we propose a novel actor-critic architecture for 3D molecular design that can generate molecular structures unattainable with previous approaches. This is achieved by… 
Learning to design drug-like molecules in three-dimensional space using deep generative models
TLDR
This work introduces Ligand Neural Network (L-Net), a novel graph generative model for designing drug-like molecules with high-quality 3D structures that directly outputs the topological and 3D structure of molecules (including hydrogen atoms), without the need for additional atom placement or bond order inference algorithm.
Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning
Daniel Flam-Shepherd, 2, ∗ Alexander Zhigalin, 4, ∗ and Alán Aspuru-Guzik 2, 5, 6 Department of Computer Science, University of Toronto, Toronto, Ontario M5S 2E4, Canada Vector Institute for
3D pride without 2D prejudice: Bias-controlled multi-level generative models for structure-based ligand design
TLDR
This work shows how, by deconvolving the generative posterior into chemical, topological and structural context factors, it not only avoid common pitfalls in the design and evaluation of generative models, but furthermore gain detailed insight into theGenerative process itself.
3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design
Deep learning has achieved tremendous success in designing novel chemical compounds with de-sirable pharmaceutical properties. In this work, we focus on a new type of drug design problem— generating
A 3D Molecule Generative Model for Structure-Based Drug Design
TLDR
A 3D generative model that generates molecules given a designated 3D protein binding site that exhibits high binding affinity to specific targets and good drug properties such as drug-likeness even if the model is not explicitly optimized for them is proposed.
Atomistic Global Optimization X: A Python package for optimization of atomistic structures
TLDR
This paper introduces the Atomistic Global Optimization X (AGOX) framework and code, as a customizable approach to building efirst principles global optimization algorithms, and a modular way of expressing global optimizationgorithms in the freely available AGOX python package.
Equivariant Diffusion for Molecule Generation in 3D
TLDR
The proposed E(3) Equivariant Diffusion Model (EDM) learns to denoise a diffusion process with an equivariant network that jointly operates on both continuous (atom coordinates) and categorical features (atom types).
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
TLDR
This paper proposes a novel generative model named GEODIFF for molecular conformation prediction that treats each atom as a particle and learns to directly reverse the diffusion process (i.e., transforming from a noise distribution to stable conformations) as a Markov chain.
Inverse design of 3d molecular structures with conditional generative neural networks
TLDR
This research presents a probabilistic architecture for machine learning that automates the very labor-intensive and therefore time-heavy and therefore expensive process of training neural networks.
MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design
TLDR
This paper systematically review the most relevant work in machine learning models for molecule design and summarizes all the existing molecule design problems into several venues according to the problem setup, including input, output types and goals.
...
1
2
3
...

References

SHOWING 1-10 OF 53 REFERENCES
Optimization of Molecules via Deep Reinforcement Learning
TLDR
Inspired by problems faced during medicinal chemistry lead optimization, the MolDQN model is extended with multi-objective reinforcement learning, which maximizes drug-likeness while maintaining similarity to the original molecule.
Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
TLDR
A generative neural network for 3d point sets that respects the rotational invariance of the targeted structures is introduced and demonstrated its ability to approximate the distribution of equilibrium structures using spatial metrics as well as established measures from chemoinformatics.
Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design
Molecular de-novo design through deep reinforcement learning
TLDR
A method to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can learn to generate structures with certain specified desirable properties is introduced.
Constrained Graph Variational Autoencoders for Molecule Design
TLDR
A variational autoencoder model in which both encoder and decoder are graph-structured is proposed and it is shown that by using appropriate shaping of the latent space, this model allows us to design molecules that are (locally) optimal in desired properties.
Atomistic structure learning
TLDR
This work introduces an atomistic structure learning algorithm (ASLA) that utilizes a convolutional neural network to build 2D compounds and layered structures atom by atom using first-principles quantum mechanical program for physical properties.
Structure prediction of surface reconstructions by deep reinforcement learning.
We demonstrate how image recognition and reinforcement learning combined may be used to determine the atomistic structure of reconstructed crystalline surfaces. A deep neural network represents a
Generating equilibrium molecules with deep neural networks
TLDR
A novel, autoregressive, convolutional deep neural network architecture that generates molecular equilibrium structures by sequentially placing atoms in three-dimensional space is introduced.
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
TLDR
Graph Convolutional Policy Network (GCPN) is proposed, a general graph convolutional network based model for goal-directed graph generation through reinforcement learning that can achieve 61% improvement on chemical property optimization over state-of-the-art baselines while resembling known molecules, and achieve 184% improved on the constrained property optimization task.
GuacaMol: Benchmarking Models for De Novo Molecular Design
TLDR
This work proposes an evaluation framework, GuacaMol, based on a suite of standardized benchmarks, to standardize the assessment of both classical and neural models for de novo molecular design, and describes a variety of single and multiobjective optimization tasks.
...
1
2
3
4
5
...