MolFinder: An Evolutionary Algorithm for the Global Optimization of Molecular Properties and the Extensive Exploration of Chemical Space Using SMILES

Kwon, Yongbeom; Lee, Juyong

doi:10.21203/rs.3.rs-104706/v1

Cited by 6 publications

(6 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The transferability issue was also discovered by the DL docking methods such that active learning is found to be essential for them to work 27,29 . Another example is V-Dock 41 , which uses a surrogate docking model as part of the linear objective function for evaluating molecules generated and optimized by the conformational space annealing algorithm 42 . Significant decrease in the correlation between predicted and actual docking scores was observed between training set and generated molecules 41 .…”

Section: Conclusion and Discussionmentioning

confidence: 99%

A Simple Way to Incorporate Target Structural Information in Molecular Generative Models

Zhang

Huang

2023

Preprint

View full text Add to dashboard Cite

Deep learning generative models are now being applied in various fields including drug discovery. In this work, we propose a novel approach to include target 3D structural information in molecular generative models for structure-based drug design. The method combines a message-passing neural network model that predicts docking scores with a generative neural network model as its reward function to navigate the chemical space searching for molecules that bind favorably with a specific target. A key component of the method is to construct target-specific molecular sets for training to overcome potential transferability issues. Tests on eight target proteins showed a 100-fold increase in hit generation compared to conventional docking calculations, and the ability to generate molecules similar to approved drugs or known active ligands for specific targets without prior knowledge. This method provides a general and highly efficient solution for structure-based molecular generation.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

A Simple Way to Incorporate Target Structural Information in Molecular Generative Models

Zhang

Huang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Most prevalent is the use of expert rules to ensure the validity of the generated structures. Particular examples of GAs implementing expert molecular generation rules include the GB-GA [48] and Molfinder [49]. However, recently, the robustness of SELFIES has been exploited in the GA-D [7] model to be able to rely only on random string modifications for mutations obviating the definition of hand-crafted structure modification rules.…”

Section: Metaheuristic Optimization Algorithmsmentioning

confidence: 99%

JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design

Nigam,

Pollice,

Aspuru-Guzik

2021

Preprint

View full text Add to dashboard Cite

Inverse molecular design, i.e., designing molecules with specific target properties, can be posed as an optimization problem. High-dimensional optimization tasks in the natural sciences are commonly tackled via population-based metaheuristic optimization algorithms such as evolutionary algorithms. However, expensive property evaluation, which is often required, can limit the widespread use of such approaches as the associated cost can become prohibitive. Herein, we present JANUS, a genetic algorithm that is inspired by parallel tempering. It propagates two populations, one for exploration and another for exploitation, improving optimization by reducing expensive property evaluations. Additionally, JANUS is augmented by a deep neural network that approximates molecular properties via active learning for enhanced sampling of the chemical space. Our method uses the SELFIES molecular representation and the STONED algorithm for the efficient generation of structures, and outperforms other generative models in common inverse molecular design tasks achieving state-of-the-art performance.Preprint. Under review.

show abstract

“…Some approaches (Jensen 2019;Nigam et al 2019Nigam et al , 2021Kwon and Lee 2021) manually design molecular transformation rules according to expert experience and optimize the molecules based on these rules with evolutionary algorithms. However, exploration of the chemical space in this way is heavily dependent on manually designed rules.…”

Section: Goal-directed Molecular Generationmentioning

confidence: 99%

HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space

Chen¹,

Fang²,

Zixu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Efficiently discovering molecules that meet various property requirements can significantly benefit the drug discovery industry. Since it is infeasible to search over the entire chemical space, recent works adopt generative models for goal-directed molecular generation. They tend to utilize the iterative processes, optimizing the parameters of the molecular generative models at each iteration to produce promising molecules for further validation. Assessments are exploited to evaluate the generated molecules at each iteration, providing direction for model optimization. However, most previous works require a massive number of expensive and time-consuming assessments, e.g., wet experiments and molecular dynamic simulations, leading to the lack of practicability. To reduce the assessments in the iterative process, we propose a costeffective evolution strategy in latent space, which optimizes the molecular latent representation vectors instead. We adopt a pre-trained molecular generative model to map the latent and observation spaces, taking advantage of the large-scale unlabeled molecules to learn chemical knowledge. To further reduce the number of expensive assessments, we introduce a pre-screener as the proxy to the assessments. We conduct extensive experiments on multiple optimization tasks comparing the proposed framework to several advanced techniques, showing that the proposed framework achieves better performance with fewer assessments.

show abstract

MolFinder: An Evolutionary Algorithm for the Global Optimization of Molecular Properties and the Extensive Exploration of Chemical Space Using SMILES

Cited by 6 publications

References 39 publications

A Simple Way to Incorporate Target Structural Information in Molecular Generative Models

A Simple Way to Incorporate Target Structural Information in Molecular Generative Models

JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design

HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space

Contact Info

Product

Resources

About