In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines

Cao, Dong‐Sheng; Dong, Jie; Wang, Ningning; Wen, Ming; Deng, Baichuan; Zeng, Wenbin; Xu, Qingsong; Liang, Yi‐Zeng; Lu, Aiping; Chen, Alex F.

doi:10.1016/j.chemolab.2015.07.009

Cited by 20 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Liang's group, they introduced machine learning techniques into QSAR studies such as the kernel k‐nearest neighbor algorithm, particle swarm optimization‐combined multiple linear regression, and kernel fusion‐based support vector machine. In these works, they studied the relationships between molecular structures and toxicity, logD 7.4 , the inhibitory effect, and water solubility for a set of structurally diverse drugs …”

Section: Application In the Analysis Of Complex Systemsmentioning

confidence: 99%

Chemometrics in instrumental analysis of complex systems—in honor and memory of Yi‐Zeng Liang

Zhang

Yun

et al. 2018

Journal of Chemometrics

View full text Add to dashboard Cite

A true pioneer in the fields of chemometrics and analytical chemistry was lost with the passing of Yi-Zeng Liang in October 2016. This is an enormous loss to both the local and global community of chemometrics. Yi-Zeng Liang is recognized as one of the major players in China in the field of chemometrics. As a professor of chemometrics and analytical chemistry in Hunan University and Central South University, he made significant advances within instrumental analysis of complex systems. Liang inspired many students and visiting scholars. As Liang's former students, we have attempted to summarize Liang's contributions to the field over the past 30 years. This review covers different chemometric areas, signal preprocessing, multivariate curve resolution, and multivariate calibration and discusses the application of these methods in traditional Chinese medicine, metabolomics, proteomics, and quantitative structure-activity relationship research.

show abstract

Section: Application In the Analysis Of Complex Systemsmentioning

confidence: 99%

Chemometrics in instrumental analysis of complex systems—in honor and memory of Yi‐Zeng Liang

Zhang

Yun

et al. 2018

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…It is evident that the risk assessment for herbicides can provide a precaution against the corresponding pollution. In environmental risk assessment, knowledge of the acute toxicity and chronic toxicity is a basic need [23][24][25].…”

Section: Introductionmentioning

confidence: 99%

“…Development of in silico predictive methods that are designed to reduce and replace the use of animals to predict biological activity of chemical compounds is a widely explored area of predictive toxicology [24].…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network-based equation to predict the toxicity of herbicides on rats

Hamadache

Hanini

Benkortbi

et al. 2016

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

The use of herbicides is increasing around the world. The benefits achieved by the use of these herbicides are indisputable. Despite their importance in agriculture, herbicides can be dangerous to the environment and the human health, depending on their toxicity, and the degree of contamination. Also, it is essential and evident that the risk assessment of herbicides is an important task in the environmental protection. The objective of this work was to investigate and implement an Artificial Neural Network (ANN) model for the prediction of acute oral toxicity of 77 herbicides to rats. Internal and external validations of the model showed high 2 and 2 ̅̅̅ values, in the range 0.782 -0.997 for the training and the test. In addition, the major contribution of the current work was to develop artificial neural network-based equation to predict the toxicity of 13 other herbicides; the mathematical equation using the weights of the network gave very significant results, leading to an R 2 value of 0.959. The agreement between calculated and experimental values of acute toxicity confirmed the ability of ANN-based equation to predict the toxicity for herbicides that have not been tested as well as new herbicides.

show abstract

“…Molecular fingerprints are property profiles of a molecule, usually in forms of bit or count vectors with the vector elements indicating the existence or the frequencies of certain properties, respectively. Both molecular descriptors and fingerprints play a fundamental role in QSAR/SAR analysis, virtual molecule screening, similarity-based compound search, target molecule ranking, drug ADME/T prediction and the other drug discovery processes [ 2 – 12 ].…”

Section: Introductionmentioning

confidence: 99%

ChemDes: an integrated web-based platform for molecular descriptor and fingerprint computation

et al. 2015

Self Cite

View full text Add to dashboard Cite

Background Molecular descriptors and fingerprints have been routinely used in QSAR/SAR analysis, virtual drug screening, compound search/ranking, drug ADME/T prediction and other drug discovery processes. Since the calculation of such quantitative representations of molecules may require substantial computational skills and efforts, several tools have been previously developed to make an attempt to ease the process. However, there are still several hurdles for users to overcome to fully harness the power of these tools. First, most of the tools are distributed as standalone software or packages that require necessary configuration or programming efforts of users. Second, many of the tools can only calculate a subset of molecular descriptors, and the results from multiple tools need to be manually merged to generate a comprehensive set of descriptors. Third, some packages only provide application programming interfaces and are implemented in different computer languages, which pose additional challenges to the integration of these tools.Results A freely available web-based platform, named ChemDes, is developed in this study. It integrates multiple state-of-the-art packages (i.e., Pybel, CDK, RDKit, BlueDesc, Chemopy, PaDEL and jCompoundMapper) for computing molecular descriptors and fingerprints. ChemDes not only provides friendly web interfaces to relieve users from burdensome programming work, but also offers three useful and convenient auxiliary tools for format converting, MOPAC optimization and fingerprint similarity calculation. Currently, ChemDes has the capability of computing 3679 molecular descriptors and 59 types of molecular fingerprints.ConclusionChemDes provides users an integrated and friendly tool to calculate various molecular descriptors and fingerprints. It is freely available at http://www.scbdd.com/chemdes. The source code of the project is also available as a supplementary file.Graphical abstract:An overview of ChemDes. A platform for computing various molecular descriptors and fingerprints

show abstract

In silico toxicity prediction of chemicals from EPA toxicity database by kernel fusion-based support vector machines

Cited by 20 publications

References 43 publications

Chemometrics in instrumental analysis of complex systems—in honor and memory of Yi‐Zeng Liang

Chemometrics in instrumental analysis of complex systems—in honor and memory of Yi‐Zeng Liang

Artificial neural network-based equation to predict the toxicity of herbicides on rats

ChemDes: an integrated web-based platform for molecular descriptor and fingerprint computation

Contact Info

Product

Resources

About