scholarly journals Sanitize It Yourself: Web-based molecular sanitization for machine-generated chemical structures

2021 ◽  
Author(s):  
Naruki Yoshikawa ◽  
Kentaro Rikimaru ◽  
Kazuki Yamamoto
Keyword(s):  
Deep Learning ◽  
Web Service ◽  
Chemical Space ◽  
Computer Aided Drug Design ◽  
Web Based ◽  
Chemical Structures ◽  
Structural Formulas ◽  
Computer Aided ◽  
Novel Structures ◽  
The Web

Many computer-aided drug design (CADD) methods using deep learning have recently been proposed to explore the chemical space toward novel scaffolds efficiently. However, there is a tradeoff between the ease of generating novel structures and the chemical feasibility of structural formulas. To overcome the limitations of computational filtering, we have implemented a web-based software in which users can share and evaluate computer-generated compounds. The web service is available at https://sanitizer.chemical.space/.

scholarly journals Sanitize It Yourself: human-based sanitization checker against machine-generated chemical structures

2021 ◽  
Author(s):  
Naruki Yoshikawa ◽  
Kentaro Rikimaru ◽  
Kazuki Yamamoto
Keyword(s):  
Deep Learning ◽  
Drug Design ◽  
Web Application ◽  
Chemical Space ◽  
Computer Aided Drug Design ◽  
Chemical Structures ◽  
Structural Formulas ◽  
Computer Aided ◽  
Novel Structures

Many computer-aided drug design (CADD) methods using deep learning have recently been proposed to explore the chemical space toward novel scaffolds efficiently. However, there is a tradeoff between the ease of generating novel structures and the chemical feasibility of structural formulas. To overcome the limitations of computational filtering, we have implemented a web application that allows easy compound sanitization by humans. The application is available at https://sanitizer.chemical.space/.

A web-based 3D virtual display framework for warp-knitted seamless garment design

2018 ◽  
Vol 30 (3) ◽  
pp. 332-346
Author(s):  
Zhijia Dong ◽  
Gaoming Jiang ◽  
Guoming Huang ◽  
Honglian Cong
Keyword(s):  
Geometric Modeling ◽  
3D Model ◽  
Texture Mapping ◽  
Design System ◽  
Web Based ◽  
Content Type ◽  
Computer Aided ◽  
Virtual Display ◽  
Garment Design ◽  
The Web

Purpose The virtual display of 3D garment is one of the most important features in a computer-aided garment design system. The purpose of this paper is to present a novel web-based 3D virtual display framework for the online design of warp-knitted seamless garment using the latest WebGL and HTML5 technologies. Design/methodology/approach Based on the feature-based parametric 3D human body model, the 3D model of skin-tight warp-knitted seamless garment is established using the geometric modeling method. By applying plane parameterization technology, the 3D garment model is then projected into corresponding 2D prototype pattern and a texture-mapping relationship is obtained. Finally, an online 3D virtual display application framework for warp-knitted seamless garment is implemented on modern WebGL-enabled web browsers using the latest WebGL and HTML5 technologies, which allow garment designers to globally access without installing any additional software or plugin. Findings Based on the 2D/3D model of warp-knitted seamless garment, an online 3D virtual display application running on modern WebGL-enabled web browser is implemented using the latest Javascript, WebGL and HTML5 technologies, which is proven to be an effective way for building the web-based 3D garment CAD systems. Originality/value This paper provides a parametric design method for warp-knitted seamless garment 2D/3D model, and web-based online virtual display of 3D warp-knitted seamless garment is implemented for the first time, which establishes the foundation for the web-based online computer-aided warp-knitted seamless garment design system.

scholarly journals A Free Web-Based Protocol to Assist Structure-Based Virtual Screening Experiments

2019 ◽  
Vol 20 (18) ◽  
pp. 4648 ◽  
Author(s):  
Nathalie Lagarde ◽  
Elodie Goldwaser ◽  
Tania Pencheva ◽  
Dessislava Jereva ◽  
Ilza Pajeva ◽  
...  
Keyword(s):  
Drug Discovery ◽  
Virtual Screening ◽  
Web Service ◽  
Molecular Mechanics ◽  
In Silico ◽  
Chemical Biology ◽  
In Silico Screening ◽  
Web Based ◽  
Screening Experiments ◽  
The Web

Chemical biology and drug discovery are complex and costly processes. In silico screening approaches play a key role in the identification and optimization of original bioactive molecules and increase the performance of modern chemical biology and drug discovery endeavors. Here, we describe a free web-based protocol dedicated to small-molecule virtual screening that includes three major steps: ADME-Tox filtering (via the web service FAF-Drugs4), docking-based virtual screening (via the web service MTiOpenScreen), and molecular mechanics optimization (via the web service AMMOS2 [Automatic Molecular Mechanics Optimization for in silico Screening]). The online tools FAF-Drugs4, MTiOpenScreen, and AMMOS2 are implemented in the freely accessible RPBS (Ressource Parisienne en Bioinformatique Structurale) platform. The proposed protocol allows users to screen thousands of small molecules and to download the top 1500 docked molecules that can be further processed online. Users can then decide to purchase a small list of compounds for in vitro validation. To demonstrate the potential of this online-based protocol, we performed virtual screening experiments of 4574 approved drugs against three cancer targets. The results were analyzed in the light of published drugs that have already been repositioned on these targets. We show that our protocol is able to identify active drugs within the top-ranked compounds. The web-based protocol is user-friendly and can successfully guide the identification of new promising molecules for chemical biology and drug discovery purposes.

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 ◽  
Esben Jannik Bjerrum ◽  
Ola Engkvist ◽  
...  
Keyword(s):  
Deep Learning ◽  
De Novo ◽  
Chemical Space ◽  
Learning Method ◽  
Training Set ◽  
Generative Adversarial Network ◽  
Structure Generation ◽  
Adversarial Network ◽  
Molecule Design ◽  
Novel Structures

<p>Recently deep learning method has been used for generating novel structures. In the current study, we proposed a new deep learning method, LatentGAN, which combine an autoencoder and a generative adversarial neural network for doing de novo molecule design. We applied the method for structure generation in two scenarios, one is to generate random drug-like compounds and the other is to generate target biased compounds. Our results show that the method works well in both cases, in which sampled compounds from the trained model can largely occupy the same chemical space of the training set and still a substantial fraction of the generated compound are novel. The distribution of drug-likeness score for compounds sampled from LatentGAN is also similar to that of the training set.</p>

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 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 Application of the SwissDrugDesign Online Resources in Virtual Screening

2019 ◽  
Vol 20 (18) ◽  
pp. 4612 ◽  
Author(s):  
Antoine Daina ◽  
Vincent Zoete
Keyword(s):  
Virtual Screening ◽  
Small Molecules ◽  
Short Description ◽  
Online Resources ◽  
Computer Aided Drug Design ◽  
Web Based ◽  
Online Tools ◽  
Modeling Group ◽  
Computer Aided ◽  
Swiss Institute

SwissDrugDesign is an important initiative led by the Molecular Modeling Group of the SIB Swiss Institute of Bioinformatics. This project provides a collection of freely available online tools for computer-aided drug design. Some of these web-based methods, i.e., SwissSimilarity and SwissTargetPrediction, were especially developed to perform virtual screening, while others such as SwissADME, SwissDock, SwissParam and SwissBioisostere can find applications in related activities. The present review aims at providing a short description of these methods together with examples of their application in virtual screening, where SwissDrugDesign tools successfully supported the discovery of bioactive small molecules.

Sign in / Sign up

Export Citation Format

Share Document