Applicability Domains and Consistent Structure Generation

Kaneko, Hiromasa; Funatsu, Kimito

doi:10.1002/minf.201600032

Cited by 6 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the use of particular descriptors (i. e. MCDs) or their design (i. e. Signature) permitted an easier compound generation step. Nevertheless, the applicability domain was also restricted to the training set [160] for those methodologies, prohibiting a more diverse generation and scaffold hopping.…”

Section: Discussionmentioning

confidence: 99%

Inverse‐QSPR for de novo Design: A Review

Gantzer

Creton

Nieto‐Draghi

2019

Molecular Informatics

View full text Add to dashboard Cite

The use of computer tools to solve chemistry‐related problems has given rise to a large and increasing number of publications these last decades. This new field of science is now well recognized and labelled Chemoinformatics. Among all chemoinformatics techniques, the use of statistical based approaches for property predictions has been the subject of numerous research reflecting both new developments and many cases of applications. The so obtained predictive models relating a property to molecular features – descriptors – are gathered under the acronym QSPR, for Quantitative Structure Property Relationships. Apart from the obvious use of such models to predict property values for new compounds, their use to virtually synthesize new molecules – de novo design – is currently a high‐interest subject. Inverse‐QSPR (i‐QSPR) methods have hence been developed to accelerate the discovery of new materials that meet a set of specifications. In the proposed manuscript, we review existing i‐QSPR methodologies published in the open literature in a way to highlight developments, applications, improvements and limitations of each.

show abstract

Section: Discussionmentioning

confidence: 99%

Inverse‐QSPR for de novo Design: A Review

Gantzer

Creton

Nieto‐Draghi

2019

Molecular Informatics

View full text Add to dashboard Cite

show abstract

“…Cao et al (2017) presented recently an ensemble PLS method for descriptor selection, outlier detection, applicability domain assessment and ensemble modeling in QSAR/QSPR modeling. Recent reviews show more detailed information regarding other available approaches (Kaneko and Funatsu, 2017;Sahigara et al, 2012). Principle 4 (appropriate measures of goodness-of-fit, robustness and predictivity) intends to simplify the overall set of principles distinguishing between internal and external validation.…”

Section: Validation Of Nano-qsar/qspr Modelsmentioning

confidence: 99%

Considerations of nano-QSAR/QSPR models for nanopesticide risk assessment within the European legislative framework

Villaverde¹,

Sevilla-Morán²,

López-Goti³

et al. 2018

Science of The Total Environment

View full text Add to dashboard Cite

“…However, it became clear that QSAR model performance was not consistent across molecules, as it was typically better for compounds whose molecular structures were adequately represented by training samples . In recent years, defining a model’s domain of applicability (DA) has been an area of active research in QSAR modeling. − The goal is to provide not only QSAR predictions but also the degree of confidence in the predictions based on the relationship of the new molecules to the domain. This is important because most end users of QSAR models do not have direct knowledge of the structural information on the training molecules from which the models were derived.…”

Section: Introductionmentioning

confidence: 99%

General Approach to Estimate Error Bars for Quantitative Structure–Activity Relationship Predictions of Molecular Activity

Liu

Glover

Feasel

et al. 2018

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Key requirements for quantitative structure-activity relationship (QSAR) models to gain acceptance by regulatory authorities include a defined domain of applicability (DA) and appropriate measures of goodness-of-fit, robustness, and predictivity. Hence, many DA metrics have been developed over the past two decades. The most intuitive are perhaps distance-to-model metrics, which are most commonly defined in terms of the mean distance between a molecule and its k nearest training samples. Detailed evaluations have shown that the variance of predictions by an ensemble of QSAR models may serve as a DA metric and can outperform distance-to-model metrics. Intriguingly, the performance of ensemble variance metric has led researchers to conclude that the error of predicting a new molecule does not depend on the input descriptors or machine-learning methods but on its distance to the training molecules. This implies that the distance to training samples may serve as the basis for developing a high-performance DA metric. In this article, we introduce a new Tanimoto distance-based DA metric called the sum of distance-weighted contributions (SDC), which takes into account contributions from all molecules in a training set. Using four acute chemical toxicity data sets of varying sizes and four other molecular property data sets, we demonstrate that SDC correlates well with the prediction error for all data sets regardless of the machine-learning methods and molecular descriptors used to build the QSAR models. Using the acute toxicity data sets, we compared the distribution of prediction errors with respect to SDC, the mean distance to k-nearest training samples, and the variance of random forest predictions. The results showed that the correlation with the prediction error was highest for SDC. We also demonstrate that SDC allows for the development of robust root mean squared error (RMSE) models and makes it possible to not only give a QSAR prediction but also provide an individual RMSE estimate for each molecule. Because SDC does not depend on a specific machine-learning method, it represents a canonical measure that can be widely used to estimate individual molecule prediction errors for any machine-learning method.

show abstract

Applicability Domains and Consistent Structure Generation

Cited by 6 publications

References 42 publications

Inverse‐QSPR for de novo Design: A Review

Inverse‐QSPR for de novo Design: A Review

Considerations of nano-QSAR/QSPR models for nanopesticide risk assessment within the European legislative framework

General Approach to Estimate Error Bars for Quantitative Structure–Activity Relationship Predictions of Molecular Activity

Contact Info

Product

Resources

About