• Corpus ID: 225076249

Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models

@article{Masuda2020Generating3M,
  title={Generating 3D Molecular Structures Conditional on a Receptor Binding Site with Deep Generative Models},
  author={Tomohide Masuda and Matthew Ragoza and David Ryan Koes},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.14442}
}
Deep generative models have been applied with increasing success to the generation of two dimensional molecules as SMILES strings and molecular graphs. In this work we describe for the first time a deep generative model that can generate 3D molecular structures conditioned on a three-dimensional (3D) binding pocket. Using convolutional neural networks, we encode atomic density grids into separate receptor and ligand latent spaces. The ligand latent space is variational to support sampling of… 

Figures from this paper

Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets
Deep generative models have achieved tremen-dous success in designing novel drug molecules in recent years. A new thread of works have shown the great potential in advancing the specificity and
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.
Fragment-Based Ligand Generation Guided By Geometric Deep Learning On Protein-Ligand Structure
TLDR
Overall, this work demonstrates the feasibility of 3D molecular structure expansion conditioned on protein pockets while maintaining desirable drug-like physiochemical properties and developed a tool that could accelerate the work of medicinal chemists.
A 3D Generative Model for Structure-Based Drug Design Step 1: 3D Generative Model Design 2: Sampling Step 3: Training Molecule Design Data: at 30% sequence identity,
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.
De Novo Molecular Generation with Stacked Adversarial Model
TLDR
A new generative model is proposed which extends an existing adversarial autoencoder (AAE) based model by stacking two models together by generating more valid molecules, as well as molecules that are more similar to known drugs.
Decoding Surface Fingerprints for Protein-Ligand Interactions
TLDR
A new computational workflow for high-throughput fragment-based screening and binding affinity prediction where the available protein-ligand complex structures are leveraged using a state-of-the-art protein surface embedding framework (dMaSIF).
EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction
TLDR
A novel and fast fine-tuning model that adjusts torsion angles of a ligand’s rotatable bonds based on closed-form global minima of the von Mises angular distance to a given input atomic point cloud, avoiding previous expensive differential evolution strategies for energy minimization.
In-Pocket 3D Graphs Enhance Ligand-Target Compatibility in Generative Small-Molecule Creation
TLDR
This work shows how the structural context of a protein target can be used to enhance molecule generation by combining a conditional variational autoencoder that allows for activity-specific molecule generation with putative contact generation that provides predictions of molecular interactions within the target binding pocket.
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.
Molecule Generation for Drug Design: a Graph Learning Perspective
TLDR
This survey provides an overview of the state-of-the-art molecule design and discovery aiding methods whose methodology involves (deep) graph learning, and proposes to categorize these methods into three groups: all at once, fragment-based and node-by-node.
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration
AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
TLDR
AtomNet is introduced, the first structure-based, deep convolutional neural network designed to predict the bioactivity of small molecules for drug discovery applications and it is shown that AtomNet outperforms previous docking approaches on a diverse set of benchmarks by a large margin.
RosENet: Improving Binding Affinity Prediction by Leveraging Molecular Mechanics Energies with an Ensemble of 3D Convolutional Neural Networks
TLDR
RosENet (Rosetta Energy Neural Network), an ensemble of three-dimensional (3D) Convolutional Neural Networks (CNN), which combines voxelized molecular mechanics energies and molecular descriptors for predicting the absolute binding affinity of protein - ligand complexes is presented.
Junction Tree Variational Autoencoder for Molecular Graph Generation
TLDR
The junction tree variational autoencoder generates molecular graphs in two phases, by first generating a tree-structured scaffold over chemical substructures, and then combining them into a molecule with a graph message passing network, which allows for incrementally expand molecules while maintaining chemical validity at every step.
Optimol : Optimization of Binding Affinities in Chemical Space for Drug Discovery
TLDR
A new graph to selfies VAE is introduced which is competitive with the state of the art and benefits from faster decoding than graph to graph methods and allows to iteratively generate leads that better fit the target structure in a closed optimization loop, without prior knowledge about bio-actives.
Development and evaluation of a deep learning model for protein-ligand binding affinity prediction
TLDR
A novel deep neural network estimating the binding affinity of ligand-receptor complexes is developed, using a 3D convolution to produce a feature map of this representation, treating the atoms of both proteins and ligands in the same manner.
Randomized SMILES strings improve the quality of molecular generative models
TLDR
An extensive benchmark on models trained with subsets of GDB-13 of different sizes, with different SMILES variants (canonical, randomized and DeepSMILES), with two different recurrent cell types (LSTM and GRU) and with different hyperparameter combinations shows that models that use LSTM cells trained with 1 million randomized SMilES are able to generalize to larger chemical spaces than the other approaches and they represent more accurately the target chemical space.
Molecular Generation with Recurrent Neural Networks (RNNs)
TLDR
It is explored to what extent a recurrent neural network with long short term memory cells can figure out sensible chemical rules and generate synthesizable molecules by being trained on existing compounds encoded as SMILES.
Shape-Based Generative Modeling for de Novo Drug Design
TLDR
This work proposes a machine learning approach to generate novel molecules starting from a seed compound, its three-dimensional shape, and its pharmacophoric features, and represents a first example of the de novo design of lead-like molecules guided by shape-based features.
Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
TLDR
This work shows that recurrent neural networks can be trained as generative models for molecular structures, similar to statistical language models in natural language processing, and demonstrates that the properties of the generated molecules correlate very well with those of the molecules used to train the model.
...
1
2
3
4
5
...