Knowledge-Based Expert Systems for Toxicity and Metabolism Prediction: DEREK, StAR and METEOR

Greene, Nigel; Judson, Philip N.; Langowski, J. J.; Marchant, Carol A.

doi:10.1080/10629369908039182

Cited by 215 publications

(123 citation statements)

References 13 publications

Supporting

Mentioning

114

Contrasting

Unclassified

Order By: Relevance

“…Preclinical tools such as, DEREK, METEOR [9], and MetabolExpert [10], which can predict metabolism or reactive metabolite formation, can be used to sieve out potential toxicant early. However, they may sometimes give high false positive or false negative rates in their predictions [11].…”

Section: Introductionmentioning

confidence: 99%

Mixed learning algorithms and features ensemble in hepatotoxicity prediction

Liew

Lim

Yap

2011

J Comput Aided Mol Des

101

View full text Add to dashboard Cite

Drug-induced liver injury, although infrequent, is an important safety concern that can lead to fatality in patients and failure in drug developments. In this study, we have used an ensemble of mixed learning algorithms and mixed features for the development of a model to predict hepatic effects. This robust method is based on the premise that no single learning algorithm is optimum for all modelling problems. An ensemble model of 617 base classifiers was built from a diverse set of 1,087 compounds. The ensemble model was validated internally with five-fold cross-validation and 25 rounds of y-randomization. In the external validation of 120 compounds, the ensemble model had achieved an accuracy of 75.0%, sensitivity of 81.9% and specificity of 64.6%. The model was also able to identify 22 of 23 withdrawn drugs or drugs with black box warning against hepatotoxicity. Dronedarone which is associated with severe liver injuries, announced in a recent FDA drug safety communication, was predicted as hepatotoxic by the ensemble model. It was found that the ensemble model was capable of classifying positive compounds (with hepatic effects) well, but less so on negatives compounds when they were structurally similar. The ensemble model built in this study is made available for public use.

show abstract

Section: Introductionmentioning

confidence: 99%

Mixed learning algorithms and features ensemble in hepatotoxicity prediction

Liew

Lim

Yap

2011

J Comput Aided Mol Des

101

View full text Add to dashboard Cite

show abstract

“…Для своей работы система использует алгоритм программы PASS. Среди других экспертных систем надо отметить программы TIMES [40], METEOR [41], META [42].…”

Section: рисунокunclassified

Computer-based substrate specifity prediction for cytochrome P450

et al. 2010

View full text Add to dashboard Cite

Cytochrome P450 is important class of enzymes metabolizing numerous drugs. The composition and activity of these enzymes are determined the drug distribution in organism, its pharmacological and toxic effect. Thus the prediction of the behaviour of compounds in organism is essential for discovery and development of new drugs in the early stages of this process. The different isoforms of cytochrome P450 can oxidized wide range of chemical compounds and their substrate specifity do not correlate with their taxonomical classification. The main methods of cytochrome P450 substrate specifity prediction is reviewed. These methods divided based on primary informations that used: prediction based on amino acid sequences, ligand-based (pharmacophore and QSAR models) and structure-based (molecular docking, affinity prediction) methods. The common problem of cytochrome P450 substrate prediction and advantage and disadvantages of these methods are discussed.

show abstract

“…For the prediction of individual toxicological endpoints there exist specific software packages. An example of this is DEREK [47], which not only provides a substructure alert, but also background information about liable compounds triggering the alerts and the literature references responsible for the alert.…”

Section: Unwanted Structural Elementsmentioning

confidence: 99%