Beware of Unreliable Q2! A Comparative Study of Regression Metrics for Predictivity Assessment of QSAR Models

Roberto Todeschini, Davide Ballabio, Francesca Grisoni

Research output: Contribution to journalArticleAcademicpeer-review

54 Citations (Scopus)

Abstract

Validation is an essential step of QSAR modeling, and it can be performed by both internal validation techniques (e.g., cross-validation, bootstrap) or by an external set of test objects, that is, objects not used for model development and/or optimization. The evaluation of model predictive ability is then completed by comparing experimental and predicted values of test molecules. When dealing with quantitative QSAR models, validation results are generally expressed in terms of Q2 metrics. In this work, four fundamental mathematical principles, which should be respected by any Q2 metric, are introduced. Then, the behavior of five different metrics (QF12, QF2 2, QF3 2, QCCC2, and QRm2) is compared and critically discussed. The conclusions highlight that only the QF32 metric satisfies all the stated conditions, while the remaining metrics show different theoretical flaws.

Original languageEnglish
Pages (from-to)1905-1913
Number of pages9
JournalJournal of Chemical Information and Modeling
Volume56
Issue number10
DOIs
Publication statusPublished - 24 Oct 2016
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2016 American Chemical Society.

Fingerprint

Dive into the research topics of 'Beware of Unreliable Q<sup>2</sup>! A Comparative Study of Regression Metrics for Predictivity Assessment of QSAR Models'. Together they form a unique fingerprint.

Cite this