Neural networks for effect prediction in environmental and health issues using large datasets

Kaiser, Klaus L.E.

doi:10.1002/qsar.200390010

Cited by 19 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, the performance of QSAR models can be improved when a prediction space is defined or warnings are SAR and QSAR in Environmental Research 691 provided if the chemical domain covered is not represented by the substance [33][34][35]. Thus, the AD tool can improve evaluation of the reliability, even using the existing models.…”

Section: Resultsmentioning

confidence: 99%

Comparison ofin silicomodels for prediction ofDaphnia magnaacute toxicity

Golbamaki

Cassano

Lombardo

et al. 2014

SAR and QSAR in Environmental Research

View full text Add to dashboard Cite

Eight in silico modelling packages were evaluated and compared for the prediction of Daphnia magna acute toxicity from the viewpoint of the European legislation on chemicals, REACH. We tested the following models: Discovery Studio (DS) TOPKAT, ACD/Tox Suite, ADMET Predictor, ECOSAR (Ecological Structure Activity Relationships), TerraQSAR, T.E.S.T. (Toxicity Estimation Software Tool) and two models implemented in VEGA on 480 industrial compounds for 48-h median lethal concentrations (LC50) to D. magna, matching them with experimental values. The quality of the estimates was compared using a standard statistical review and an additional classification approach in which the hazard predictions were grouped using well-defined regulatory criteria. The regression parameters, correlation coefficient being the most influential, showed that four models (ADMET Predictor, DS TOPKAT, TerraQSAR and VEGA DEMETRA) had similar reliability. These performed better than the others, but the coefficient of determination was still low (r2 around 0.6), considering that at least half the predicted compounds were inside the training sets. Additionally, we grouped the results in four defined toxicity classes. TerraQSAR™ gave 60% of correct classifications, followed by DS TOPKAT, ADMET Predictor™ and VEGA DEMETRA, with 56%, 54% and 48%, respectively. These results highlight the challenges associated with developing reliable and easily applied acceptability criteria for the regulatory use of QSAR models to D. magna acute toxicity.

show abstract

Section: Resultsmentioning

confidence: 99%

Comparison ofin silicomodels for prediction ofDaphnia magnaacute toxicity

Golbamaki

Cassano

Lombardo

et al. 2014

SAR and QSAR in Environmental Research

View full text Add to dashboard Cite

show abstract

“…The interest of artificial neural networks and/or SVMs to model the endocrine activity of chemicals has been also stressed by Kaiser (2003), Marini et al (2005) and .…”

Section: Models Computed From 2d Descriptorsmentioning

confidence: 99%

Endocrine Toxicology

2016

View full text Add to dashboard Cite

“…For the fast screening of potential estrogens, many binary classification QSAR models have been developed [13,[33][34][35][36][37][38][39][40][41][42][43].…”

Section: Classification Modelsmentioning

confidence: 99%

“…Kaiser and Niculescu [42,43] developed the relationship between the estrogen receptor binding and the molecular structure of chemicals using the probabilistic neural network (PNN) methodology with structural fragment descriptors for 1,000 compounds (steroids and not), by using a cross validation of leave-20%-out and an external set of 118 chemicals. They obtained good sub-models, developed on sub-sets, defined by certain structural conditions (for instance, carboxylic esters) with a standard deviation error of 0.28 for the training chemicals and 0.20 for the test ones.…”

Section: Classification Modelsmentioning

confidence: 99%

The Applications of Machine Learning Algorithms in the Modeling of Estrogen-Like Chemicals

Liu

Yao²,

Gramatica³

2009

CCHTS

View full text Add to dashboard Cite

Increasing concern is being shown by the scientific community, government regulators, and the public about endocrine-disrupting chemicals that, in the environment, are adversely affecting human and wildlife health through a variety of mechanisms, mainly estrogen receptor-mediated mechanisms of toxicity. Because of the large number of such chemicals in the environment, there is a great need for an effective means of rapidly assessing endocrine-disrupting activity in the toxicology assessment process. When faced with the challenging task of screening large libraries of molecules for biological activity, the benefits of computational predictive models based on quantitative structure-activity relationships to identify possible estrogens become immediately obvious. Recently, in order to improve the accuracy of prediction, some machine learning techniques were introduced to build more effective predictive models. In this review we will focus our attention on some recent advances in the use of these methods in modeling estrogen-like chemicals. The advantages and disadvantages of the machine learning algorithms used in solving this problem, the importance of the validation and performance assessment of the built models as well as their applicability domains will be discussed.

show abstract

Neural networks for effect prediction in environmental and health issues using large datasets

Cited by 19 publications

References 21 publications

Comparison ofin silicomodels for prediction ofDaphnia magnaacute toxicity

Comparison ofin silicomodels for prediction ofDaphnia magnaacute toxicity

Endocrine Toxicology

The Applications of Machine Learning Algorithms in the Modeling of Estrogen-Like Chemicals

Contact Info

Product

Resources

About