Separation of data on the training and test set for modelling: a case study for modelling of five colour properties of a white pigment

Rajer-Kanduč, Karmen; Zupan, Jure; Majcen, Nineta

doi:10.1016/s0169-7439(02)00110-7

Cited by 124 publications

(43 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, the latter technique has proved very effective in several occasions in producing a representative data splitting [31,32]. A Kohonen neural network operates by mapping samples from an N-dimensional space onto a discrete 2-dimensional grid of neurons, so that object that have similar properties in the original space will map to the same or to neighboring nodes.…”

Section: How To Select Subsets Of Samples For Calibration and Validationmentioning

confidence: 99%

Validation of chemometric models – A tutorial

Westad

Marini

2015

Analytica Chimica Acta

288

164

View full text Add to dashboard Cite

Section: How To Select Subsets Of Samples For Calibration and Validationmentioning

confidence: 99%

Validation of chemometric models – A tutorial

Westad

Marini

2015

Analytica Chimica Acta

288

164

View full text Add to dashboard Cite

“…K-S design of the training set in ANN analysis has been shown to provide a better predictive performance than random selection and better or comparable results as compared with more sophisticated data partition methods [36,37].…”

Section: Data Partitionmentioning

confidence: 99%

Artificial neural network modelling of retention of pesticides in various octadecylsiloxane-bonded reversed-phase columns and water–acetonitrile mobile phase

D’Archivio

Maggi

Mazzeo

et al. 2009

Analytica Chimica Acta

View full text Add to dashboard Cite

“…Predictive accuracy of statistical learning systems is known to be strongly affected by the diversity of the samples used in the training and test sets [50,51]. The structural diversity of a dataset can be evaluated by calculating the diversity index (DI), the average value of the similarity between all the pairs of compounds in a dataset [52].…”

Section: Diversity Of the Datasetmentioning

confidence: 99%

Considerations and recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction

Sun

Fan

et al. 2008

J Comput Aided Mol Des

View full text Add to dashboard Cite

Quantitative structure-activity relationships (QSAR) methods are urgently needed for predicting ADME/T (absorption, distribution, metabolism, excretion and toxicity) properties to select lead compounds for optimization at the early stage of drug discovery, and to screen drug candidates for clinical trials. Use of suitable QSAR models ultimately results in lesser time-cost and lower attrition rate during drug discovery and development. In the case of ADME/T parameters, drug metabolism is a key determinant of metabolic stability, drug-drug interactions, and drug toxicity. QSAR models for predicting drug metabolism have undergone significant advances recently. However, most of the models used lack sufficient interpretability and offer poor predictability for novel drugs. In this review, we describe some considerations to be taken into account by QSAR for modeling drug metabolism, such as the accuracy/consistency of the entire data set, representation and diversity of the training and test sets, and variable selection. We also describe some novel statistical techniques (ensemble methods, multivariate adaptive regression splines and graph machines), which are not yet used frequently to develop QSAR models for drug metabolism. Subsequently, rational recommendations for developing predictable and interpretable QSAR models are made. Finally, the recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction, including in vivo hepatic clearance, in vitro metabolic stability, inhibitors and substrates of cytochrome P450 families, are briefly summarized.

show abstract

Separation of data on the training and test set for modelling: a case study for modelling of five colour properties of a white pigment

Cited by 124 publications

References 4 publications

Validation of chemometric models – A tutorial

Validation of chemometric models – A tutorial

Artificial neural network modelling of retention of pesticides in various octadecylsiloxane-bonded reversed-phase columns and water–acetonitrile mobile phase

Considerations and recent advances in QSAR models for cytochrome P450-mediated drug metabolism prediction

Contact Info

Product

Resources

About