• Corpus ID: 237592805

Differentiable Scaffolding Tree for Molecular Optimization

@article{Fu2022DifferentiableST,
  title={Differentiable Scaffolding Tree for Molecular Optimization},
  author={Tianfan Fu and Wenhao Gao and Cao Xiao and Jacob Yasonik and Connor W. Coley and Jimeng Sun},
  journal={ArXiv},
  year={2022},
  volume={abs/2109.10469}
}
The structural design of functional molecules, also called molecular optimization, is an essential chemical science and engineering task with important applications, such as drug discovery. Deep generative models and combinatorial optimization methods achieve initial success but still struggle with directly modeling discrete chemical structures and often heavily rely on brute-force enumeration. The challenge comes from the discrete and non-differentiable nature of molecule structures. To… 

Reinforced Genetic Algorithm for Structure-based Drug Design

  • Biology, Computer Science
TLDR
Empirical studies on optimizing binding affinity to various disease targets are conducted and it is shown that RGA outperforms the baselines in terms of docking scores and is more robust to random initializations.

MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization

TLDR
MIMOSA enables flexible encoding of multiple property- and similarity-constraints and can efficiently generate new molecules that satisfy various property constraints and achieved up to 49.1% relative improvement over the best baseline in terms of success rate.

Interpretable Molecular Graph Generation via Monotonic Constraints

TLDR
New methodologies for molecule generation with interpretable and controllable deep generative models, by proposing new monotonically-regularized graph variational autoencoders that learn to represent the molecules with latent variables and then learn the correspondence between them and molecule properties parameterized by polynomial functions.

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.

Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization

TLDR
The results show that most “state-of-the-art” methods fail to outperform their predecessors under a limited oracle budget allowing 10K queries and that no existing algorithm can efficiently solve certain molecular optimization problems in this setting.

LIMO: Latent Inceptionism for Targeted Molecule Generation

TLDR
Multi-objective optimization is successful in generating more molecules with potentially high binding affinity within the defined cutoff ranges, so is advantageous over single-objectives optimization.

Helix-MO: Sample-Efficient Molecular Optimization on Scene-Sensitive Latent Space

TLDR
A sample-efficient molecular generative method, namely Helix-MO, which can fast adapt to particular optimization scenes with only a small number of assessed samples, and is deployed on the website PaddleHelix to provide drug design service and applied to produce inhibitors of a kinase to demonstrate its practicability.

Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design

TLDR
An amortized approach to generate synthetic pathways as a Markov decision process conditioned on a target molecular embedding is reported, allowing for synthesis planning in a bottom-up manner and design synthesizable molecules by decoding from optimized conditional codes, demonstrating the potential to solve both problems of design and synthesis simultaneously.

How Much of the Chemical Space Has Been Explored? Selecting the Right Exploration Measure for Drug Discovery

TLDR
A novel framework to systematically evaluate exploration measures for drug candidate generation is proposed and recommendations on existing and novel exploration measures that are suitable for the task of drug discovery are made.

Antibody Complementarity Determining Regions (CDRs) design using Constrained Energy Model

TLDR
A Constrained Energy Model (CEM) is proposed to address the challenges of maintaining the specific geometry shape of the CDR loops of therapeutic antibodies, and theoretical analysis shows that learning on the constrained manifold requires less sample complexity than the unconstrained method.

References

SHOWING 1-10 OF 54 REFERENCES

The Synthesizability of Molecules Proposed by Generative Models

TLDR
This analysis suggests that to improve the utility of state-of-the-art generative models in real discovery workflows, new algorithm development is warranted.

ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations

TLDR
ChemBO, a Bayesian optimization framework for generating and optimizing organic molecules for desired molecular properties, is described and a novel optimal-transport based distance and kernel that accounts for graphical information explicitly is proposed.

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.

MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

TLDR
Experiments show that MARS achieves state-of-the-art performance in various multi-objective settings where molecular bio-activity, drug-likeness, and synthesizability are considered.

Multi-Objective Molecule Generation using Interpretable Substructures

TLDR
This work proposes to offset the complexity of the generative modeling of molecules by composing molecules from a vocabulary of substructures that are likely responsible for each property of interest, called molecular rationales.

MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization

TLDR
MIMOSA enables flexible encoding of multiple property- and similarity-constraints and can efficiently generate new molecules that satisfy various property constraints and achieved up to 49.1% relative improvement over the best baseline in terms of success rate.

Generating Focused 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.

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.

MoFlow: An Invertible Flow Model for Generating Molecular Graphs

TLDR
The proposed MoFlow is a flow-based graph generative model to learn invertible mappings between molecular graphs and their latent representations and achieves state-of-the-art performance, which implies its potential efficiency and effectiveness to explore large chemical space for drug discovery.

MolGAN: An implicit generative model for small molecular graphs

TLDR
MolGAN is introduced, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuris-tics of previous likelihood-based methods.
...