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

Abstract Due to the potencies in the treatments of neurodegenerative diseases, caspase-6 inhibitors have attracted widespread attentions. However, the existing caspase-6 inhibitors showed more or less inevitable deficiencies that restrict their clinical development and applications. Therefore, there is an urgent need to develop novel caspase-6 candidate inhibitors. 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. Based on the novel molecules derived from the molecular generative model, an optimal machine learning model and Surflex-dock were further employed for predicting and ranking the inhibitory activities. Three potential caspase-6 inhibitors with different scaffolds were selected as the most promising candidates for further researches. In general, this paper provides an efficient combinational strategy for de novo molecular design of caspase-6 inhibitors.

Download Full-text

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

10.21203/rs.3.rs-22726/v1 ◽

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.

Download Full-text

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

10.26434/chemrxiv.8299544.v3 ◽

2019 ◽

Cited By ~ 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

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.

Download Full-text

Molecular generative model based on conditional variational autoencoder for de novo molecular design

Journal of Cheminformatics ◽

10.1186/s13321-018-0286-7 ◽

2018 ◽

Vol 10 (1) ◽

Cited By ~ 43

Author(s):

Jaechang Lim ◽

Seongok Ryu ◽

Jin Woo Kim ◽

Woo Youn Kim

Keyword(s):

De Novo ◽

Molecular Design ◽

Generative Model ◽

Model Based ◽

Variational Autoencoder ◽

De Novo Molecular Design

Download Full-text

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

Journal of Cheminformatics ◽

10.1186/s13321-019-0397-9 ◽

2019 ◽

Vol 11 (1) ◽

Cited By ~ 24

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.

Download Full-text

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

10.26434/chemrxiv.8299544.v4 ◽

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

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.

Download Full-text

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

10.26434/chemrxiv.8299544 ◽

2019 ◽

Cited By ~ 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

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.

Download Full-text

Molecular Generation Targeting Desired Electronic Properties via Deep Generative Models

10.26434/chemrxiv.9913865.v2 ◽

2019 ◽

Author(s):

Qi Yuan ◽

Alejandro Santana-Bonilla ◽

Martijn Zwijnenburg ◽

Kim Jelfs

Keyword(s):

Neural Network ◽

Electronic Properties ◽

Transfer Learning ◽

Recurrent Neural Network ◽

Chemical Space ◽

Generative Models ◽

Molecular Features ◽

Donor Acceptor ◽

Homo Lumo ◽

Training Sets

The chemical space for novel electronic donor-acceptor oligomers with targeted properties was explored using deep generative models and transfer learning. A General Recurrent Neural Network model was trained from the ChEMBL database to generate chemically valid SMILES strings. The parameters of the General Recurrent Neural Network were fine-tuned via transfer learning using the electronic donor-acceptor database from the Computational Material Repository to generate novel donor-acceptor oligomers. Six different transfer learning models were developed with different subsets of the donor-acceptor database as training sets. We concluded that electronic properties such as HOMO-LUMO gaps and dipole moments of the training sets can be learned using the SMILES representation with deep generative models, and that the chemical space of the training sets can be efficiently explored. This approach identified approximately 1700 new molecules that have promising electronic properties (HOMO-LUMO gap <2 eV and dipole moment <2 Debye), 6-times more than in the original database. Amongst the molecular transformations, the deep generative model has learned how to produce novel molecules by trading off between selected atomic substitutions (such as halogenation or methylation) and molecular features such as the spatial extension of the oligomer. The method can be extended as a plausible source of new chemical combinations to effectively explore the chemical space for targeted properties.

Download Full-text