scholarly journals Multi-objective de novo molecular design of organic structure-directing agents for zeolites using nature-inspired ant colony optimization

2020 ◽  
Vol 11 (31) ◽  
pp. 8214-8223 ◽  
Author(s):  
Koki Muraoka ◽  
Watcharop Chaikittisilp ◽  
Tatsuya Okubo
Keyword(s):  
Ant Colony Optimization ◽  
Organic Molecules ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Adaptive Optimization ◽  
Ant Colonies ◽  
Organic Structure ◽  
Multi Objective ◽  
De Novo Molecular Design

Inspired by the exploratory methods of ant colonies, adaptive optimization was employed to explore the chemical space for organic molecules that guide zeolite crystallization, giving both physicochemically and economically promising molecules.

scholarly journals Multi-Objective De Novo Molecular Design of Organic Structure-Directing Agents for Zeolites Using Nature-Inspired Ant Colony Optimization

2020 ◽  
Author(s):  
Koki Muraoka ◽  
Watcharop Chaikittisilp ◽  
Tatsuya Okubo
Keyword(s):  
Ant Colony Optimization ◽  
De Novo ◽  
Molecular Design ◽  
A Priori ◽  
Optimization Method ◽  
Critical Issue ◽  
Ant Colony ◽  
Organic Structure ◽  
De Novo Molecular Design ◽  
Structure Directing Agents

<div><p><a>Organic structure-directing agents (OSDAs) are often employed for synthesis of zeolites with desired frameworks. <i>A priori</i> prediction of such</a> OSDAs has mainly relied on the interaction energies between OSDAs and zeolite frameworks, without cost considerations. For practical purposes, the cost of OSDAs becomes a critical issue. Therefore, the development of a computational <i>de novo</i> prediction methodology that can speed up the trial-and-error cycle in search for less expensive OSDAs is desired. This study utilized a nature-inspired ant colony optimization method to predict physicochemically and/or economically preferable OSDAs, while also taking molecular similarity and heuristics of zeolite synthesis into consideration. The prediction results included experimentally known OSDAs, candidates having structures closely related to known OSDAs, and novel ones, suggesting the applicability of this approach.</p></div>

scholarly journals Multi-Objective De Novo Molecular Design of Organic Structure-Directing Agents for Zeolites Using Nature-Inspired Ant Colony Optimization

2020 ◽  
Author(s):  
Koki Muraoka ◽  
Watcharop Chaikittisilp ◽  
Tatsuya Okubo
Keyword(s):  
Ant Colony Optimization ◽  
De Novo ◽  
Molecular Design ◽  
A Priori ◽  
Optimization Method ◽  
Critical Issue ◽  
Ant Colony ◽  
Organic Structure ◽  
De Novo Molecular Design ◽  
Structure Directing Agents

<div><p><a>Organic structure-directing agents (OSDAs) are often employed for synthesis of zeolites with desired frameworks. <i>A priori</i> prediction of such</a> OSDAs has mainly relied on the interaction energies between OSDAs and zeolite frameworks, without cost considerations. For practical purposes, the cost of OSDAs becomes a critical issue. Therefore, the development of a computational <i>de novo</i> prediction methodology that can speed up the trial-and-error cycle in search for less expensive OSDAs is desired. This study utilized a nature-inspired ant colony optimization method to predict physicochemically and/or economically preferable OSDAs, while also taking molecular similarity and heuristics of zeolite synthesis into consideration. The prediction results included experimentally known OSDAs, candidates having structures closely related to known OSDAs, and novel ones, suggesting the applicability of this approach.</p></div>

PRO_LIGAND: An approach to de novo molecular design. 1. Application to the design of organic molecules

1995 ◽  
Vol 9 (1) ◽  
pp. 13-32 ◽  
Author(s):  
David E. Clark ◽  
David Frenkel ◽  
Stephen A. Levy ◽  
Jin Li ◽  
Christopher W. Murray ◽  
...  
Keyword(s):  
Organic Molecules ◽  
De Novo ◽  
Molecular Design ◽  
De Novo Molecular Design

scholarly journals Memory-assisted reinforcement learning for diverse molecular de novo design

2020 ◽  
Author(s):  
Thomas Blaschke ◽  
Ola Engkvist ◽  
Jürgen Bajorath ◽  
Hongming Chen
Keyword(s):  
Reinforcement Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Scoring Function ◽  
Chemical Diversity ◽  
Chemical Structures ◽  
Machine Learning Model ◽  
Low Diversity ◽  
De Novo Molecular Design

Abstract In de novo molecular design, recurrent neural networks (RNN) have been shown to be effective methods for sampling and generating novel chemical structures. Using a technique called reinforcement learning (RL), an RNN can be tuned to target a particular section of chemical space with optimized desirable properties using a scoring function. However, ligands generated by current RL methods so far tend to have relatively low diversity, and sometimes even result in duplicate structures when optimizing towards desired properties. Here, we propose a new method to address the low diversity issue in RL for molecular design. Memory-assisted RL is an extension of the known RL, with the introduction of a so-called memory unit. As proof of concept, we applied our method to generate structures with a desired AlogP value. In a second case study, we applied our method to design ligands for the dopamine type 2 receptor and the 5-hydroxytryptamine type 1A receptor. For both receptors, a machine learning model was developed to predict whether generated molecules were active or not for the receptor. In both case studies, it was found that memory-assisted RL led to the generation of more compounds predicted to be active having higher chemical diversity, thus achieving better coverage of chemical space of known ligands compared to established RL methods.

scholarly journals A De Novo Molecular Generation Method Using Latent Vector Based Generative Adversarial Network

2019 ◽  
Author(s):  
Oleksii Prykhodko ◽  
Simon Viet Johansson ◽  
Panagiotis-Christos Kotsias ◽  
Josep Arús-Pous ◽  
Esben Jannik Bjerrum ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
De Novo Molecular Design ◽  
Novel Structures

<p> </p><p>Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases: sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.</p><p> </p>

scholarly journals A de novo molecular generation method using latent vector based generative adversarial network

2019 ◽  
Vol 11 (1) ◽  
Author(s):  
Oleksii Prykhodko ◽  
Simon Viet Johansson ◽  
Panagiotis-Christos Kotsias ◽  
Josep Arús-Pous ◽  
Esben Jannik Bjerrum ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
De Novo Molecular Design ◽  
Novel Structures

AbstractDeep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases. Sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.

scholarly journals De Novo Molecular Design of Caspase-6 Inhibitors by GRU-Based Recurrent Neural Network Combined with Transfer Learning Approach

2020 ◽  
Author(s):  
Shuheng Huang ◽  
Hu Mei ◽  
Laichun Lu ◽  
Tingting Shi ◽  
Linxin Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Recurrent Neural Network ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Similar Chemical ◽  
De Novo Molecular Design ◽  
Caspase 6 ◽  
Potential Inhibitors

Abstract Due to the potencies in the treatments of neurodegenerative diseases, caspase-6 inhibitors have attracted widespread attentions. Herein, gated recurrent unit (GRU)-based recurrent neural network (RNN) combined with transfer learning was used to build the molecular generative model of caspase-6 inhibitors. The results showed that the GRU-based RNN model can learn accurately the SMILES grammars of about 2.4 million chemical molecules including ionic and isomeric compounds, and can generate potential caspase-6 inhibitors after transfer learning of the known 433 caspase-6 inhibitors. Further exploration of the chemical space and molecular docking showed that the generated potential inhibitors have similar chemical space distributions and binding mechanisms with the known caspase-6 inhibitors. In addition, 3 potential caspase-6 inhibitors with nanomolar-level activities were obtained and proved to be the most promising candidates for the further researches. In general, this paper provides an efficient combinational strategy for de novo molecular design of caspase-6 inhibitors.

scholarly journals Memory-Assisted Reinforcement Learning for Diverse Molecular De Novo Design

2020 ◽  
Author(s):  
Thomas Blaschke ◽  
Ola Engkvist ◽  
Jürgen Bajorath ◽  
Hongming Chen
Keyword(s):  
Reinforcement Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Scoring Function ◽  
De Novo Design ◽  
Memory Unit ◽  
Chemical Structures ◽  
Low Diversity ◽  
De Novo Molecular Design

<div><div><div><p>In de novo molecular design, recurrent neural networks (RNN) have been shown to be effective methods for sampling and generating novel chemical structures. Using a technique called reinforcement learning (RL), an RNN can be tuned to target a particular section of chemical space with optimized desirable properties using a scoring function. However, ligands generated by current RL methods so far tend to have relatively low diversity, and sometimes even result in duplicate structures when optimizing towards particular properties. Here, we propose a new method to address the low diversity issue in RL. Memory-assisted RL is an extension of the known RL, with the introduction of a so-called memory unit.</p></div></div></div>

scholarly journals A De Novo Molecular Generation Method Using Latent Vector Based Generative Adversarial Network

2019 ◽  
Author(s):  
Oleksii Prykhodko ◽  
Simon Viet Johansson ◽  
Panagiotis-Christos Kotsias ◽  
Josep Arús-Pous ◽  
Esben Jannik Bjerrum ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
De Novo Molecular Design ◽  
Novel Structures

<p> </p><p>Deep learning methods applied to drug discovery have been used to generate novel structures. In this study, we propose a new deep learning architecture, LatentGAN, which combines an autoencoder and a generative adversarial neural network for de novo molecular design. We applied the method in two scenarios: one to generate random drug-like compounds and another to generate target-biased compounds. Our results show that the method works well in both cases: sampled compounds from the trained model can largely occupy the same chemical space as the training set and also generate a substantial fraction of novel compounds. Moreover, the drug-likeness score of compounds sampled from LatentGAN is also similar to that of the training set. Lastly, generated compounds differ from those obtained with a Recurrent Neural Network-based generative model approach, indicating that both methods can be used complementarily.</p><p> </p>

scholarly journals MoleGear: A Java-Based Platform for Evolutionary De Novo Molecular Design

Molecules ◽  
2019 ◽  
Vol 24 (7) ◽  
pp. 1444 ◽  
Author(s):  
Chu ◽  
He
Keyword(s):  
Large Scale ◽  
De Novo ◽  
Molecular Design ◽  
Chemical Space ◽  
Binding Free Energy ◽  
Fitness Function ◽  
Chemistry Development ◽  
Fragment Library ◽  
Immunodeficiency Virus ◽  
De Novo Molecular Design

A Java-based platform, MoleGear, is developed for de novo molecular design based on the chemistry development kit (CDK) and other Java packages. MoleGear uses evolutionary algorithm (EA) to explore chemical space, and a suite of fragment-based operators of growing, crossover, and mutation for assembling novel molecules that can be scored by prediction of binding free energy or a weighted-sum multi-objective fitness function. The EA can be conducted in parallel over multiple nodes to support large-scale molecular optimizations. Some complementary utilities such as fragment library design, chemical space analysis, and graphical user interface are also integrated into MoleGear. The candidate molecules as inhibitors for the human immunodeficiency virus 1 (HIV-1) protease were designed by MoleGear, which validates the potential capability for de novo molecular design.

Sign in / Sign up

Export Citation Format

Share Document