One-class classification as a novel method of ligand-based virtual screening: The case of glycogen synthase kinase 3β inhibitors

Karpov, Pavel; Osolodkin, Dmitry I.; Baskin, Igor I.; Palyulin, V. A.; Зефиров, Н. С.

doi:10.1016/j.bmcl.2011.09.051

Cited by 27 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prediction rates obtained here were as poor as with the public datasets; these results were unsatisfactory and this suggests the unsuitability of one‐class SVM for our research work using these specific datasets. Although in recent years some good results have been obtained with one‐class SVM,22 the mathematical function of one‐class classification was unable to substitute the information about the negative data left in our datasets. With one‐class SVM we obtained lower prediction rates for 1A2 and 2D6 for both private and public validation datasets.…”

Section: Model Performances For Each Methods and Each Dataset: Public mentioning

confidence: 87%

New QSAR Models for Human Cytochromes P450, 1A2, 2D6 and 3A4 Implicated in the Metabolism of Drugs. Relevance of Dataset on Model Development.

Martinez-Sanz

Bonnet

Lozano

et al. 2013

Molecular Informatics

View full text Add to dashboard Cite

Cover PictureMolecular Informatics publishes research that will deepen our understanding about information storage and processing on the molecular level, signaling and regulation of biological and chemical systems including cellular systems and macromolecular assemblies, modeling of molecular interactions and networks, and the design of molecular modulators that exhibit desired biochemical and pharmacological effects. Various aspects of this transdisciplinary scientific area are depicted on the cover: Cells with their nuclei and membranes (image courtesy of Dr. A. Schreiner and E. Resch), models of receptor-ligand interactions, and an artistic representation of "biological information" as multiple bit-codes presented on a right-handed helix. -577Molecular Informatics is a peer-reviewed, international forum for publication of high-quality, interdisciplinary research on all molecular aspects of bio/cheminformatics and computer-assisted molecular design. Molecular Informatics presents methodological innovations that will lead to a deeper understanding of ligand-receptor interactions, macromolecular complexes, molecular networks, design concepts and processes that demonstrate how ideas and design concepts lead to molecules with a desired structure or function, preferably including experimental validation. The journal's scope includes but is not limited to the fields of drug discovery and chemical biology, protein and nucleic acid engineering and design, the design of nanomolecular structures, strategies for modeling of macromolecular assemblies, molecular networks and systems, pharmaco-and chemogenomics, computer-assisted screening strategies, as well as novel technologies for the de novo design of biologically active molecules. As a unique feature Molecular Informatics publishes so-called "Methods Corner" reviewtype articles which feature important technological concepts and advances.

show abstract

Section: Model Performances For Each Methods and Each Dataset: Public mentioning

confidence: 87%

New QSAR Models for Human Cytochromes P450, 1A2, 2D6 and 3A4 Implicated in the Metabolism of Drugs. Relevance of Dataset on Model Development.

Martinez-Sanz

Bonnet

Lozano

et al. 2013

Molecular Informatics

View full text Add to dashboard Cite

show abstract

“…33 developed and tested on a series of the inhibitors of glycogen synthase kinase. 34 It outperformed alternative approaches based on pharmacophore hypotheses and molecular docking in a retrospective study.…”

Section: Backpropagation Neural Networkmentioning

confidence: 99%

A renaissance of neural networks in drug discovery

Baskin

Winkler

Tetko

2016

Expert Opinion on Drug Discovery

Self Cite

195

143

View full text Add to dashboard Cite

Neural networks continue to grow in importance for drug discovery. Recent developments in deep learning suggests further improvements may be gained in the analysis of large chemical data sets. It's anticipated that neural networks will be more widely used in drug discovery in the future, and applied in non-traditional areas such as drug delivery systems, biologically compatible materials, and regenerative medicine.

show abstract

“…Therefore, artificial neural networks have been used successfully in drug design [127,128]. Also, classification and regression methods based on neural networks and support vector machines can be used as valuable tools to develop new drugs [129,130].…”

Section: Trends Of Machine Learning Techniques In Drug Designmentioning

confidence: 99%

Machine Learning Techniques and Drug Design

Gertrudes¹,

Maltarollo²,

Silva

et al. 2012

CMC

150

View full text Add to dashboard Cite

The interest in the application of machine learning techniques (MLT) as drug design tools is growing in the last decades. The reason for this is related to the fact that the drug design is very complex and requires the use of hybrid techniques. A brief review of some MLT such as self-organizing maps, multilayer perceptron, bayesian neural networks, counter-propagation neural network and support vector machines is described in this paper. A comparison between the performance of the described methods and some classical statistical methods (such as partial least squares and multiple linear regression) shows that MLT have significant advantages. Nowadays, the number of studies in medicinal chemistry that employ these techniques has considerably increased, in particular the use of support vector machines. The state of the art and the future trends of MLT applications encompass the use of these techniques to construct more reliable QSAR models. The models obtained from MLT can be used in virtual screening studies as well as filters to develop/discovery new chemicals. An important challenge in the drug design field is the prediction of pharmacokinetic and toxicity properties, which can avoid failures in the clinical phases. Therefore, this review provides a critical point of view on the main MLT and shows their potential ability as a valuable tool in drug design.

show abstract

One-class classification as a novel method of ligand-based virtual screening: The case of glycogen synthase kinase 3β inhibitors

Cited by 27 publications

References 19 publications

New QSAR Models for Human Cytochromes P450, 1A2, 2D6 and 3A4 Implicated in the Metabolism of Drugs. Relevance of Dataset on Model Development.

New QSAR Models for Human Cytochromes P450, 1A2, 2D6 and 3A4 Implicated in the Metabolism of Drugs. Relevance of Dataset on Model Development.

A renaissance of neural networks in drug discovery

Machine Learning Techniques and Drug Design

Contact Info

Product

Resources

About