REPOSITORY QDB RESOURCES NEWS CONTACTS

Aptula, A.O.; Jeliazkova, N.G.; Schultz, T.W.; Cronin, M.T.D. The Better Predictive Model: High q2 for the Training Set or Low Root Mean Square Error of Prediction for the Test Set?. QSAR Comb. Sci. 2005, 24, 3, 385–396.

QsarDB Repository

Aptula, A.O.; Jeliazkova, N.G.; Schultz, T.W.; Cronin, M.T.D. The Better Predictive Model: High q2 for the Training Set or Low Root Mean Square Error of Prediction for the Test Set?. QSAR Comb. Sci. 2005, 24, 3, 385–396.

QDB archive DOI: 10.15152/QDB.83   DOWNLOAD

QsarDB content

Property MOA: Mode of action

Compounds: 250 | Models: 0 | Predictions: 0

Property pIGC50: 40-h Tetrahymena toxicity as log(1/IGC50) [log(L/mmol)]

Compounds: 250 | Models: 0 | Predictions: 0

Citing

When citing this QDB archive, please also include the original article:

Metadata

Show full item record

Title: Aptula, A.O.; Jeliazkova, N.G.; Schultz, T.W.; Cronin, M.T.D. The Better Predictive Model: High q2 for the Training Set or Low Root Mean Square Error of Prediction for the Test Set?. QSAR Comb. Sci. 2005, 24, 3, 385–396.
Abstract: The process of validation of computational models (e.g., QSARs) may become the most important step in their development. Different requirements for the reliability and predictability of QSAR models have been described in the literature. Despite these formal recommendations there are few practical rules as to when to cease adding variables to a QSAR (i.e., what is an appropriate level of complexity of the model). In this work the influence of model complexity to statistical fit and error have been investigated using toxicity data for 200 phenols to the ciliated protozoan Tetrahymena pyriformis when applying a test set of a further 50 compounds. The results from this investigation showed that some important factors play a role in the definition of a good and reliable QSAR. These include the fact that q2 is not a good criterion for a model predictivity; that outliers should not necessarily be deleted as this may reduce the chemical space of the model; the number of descriptors in a multivariate model should be chosen carefully to avoid model under- and over-estimation; and that an appropriate number of dimensions is required for PLS modelling.
URI: http://hdl.handle.net/10967/83
http://dx.doi.org/10.15152/QDB.83
Date: 2012-05-23


Files in this item

Name Description Format Size View
109925323.qdb.zip n/a application/x-zip 11.22Kb View/Open

This item appears in the following Collection(s)

Show full item record