On the interpretation and interpretability of quantitative structure–activity relationship models

Guha, Rajarshi

doi:10.1007/s10822-008-9240-5

Cited by 77 publications

(73 citation statements)

References 107 publications

(120 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas the latter is only recently more frequently addressed, selection of relevant descriptors has received considerable attention. [4][5][6][7][8] In quantitative structure-activity relationships it is straightforward to predict the effect of a particular variable. For example, a positive coefficient of the number of hydrogen-bond donors indicates that increasing their count will lead to higher binding affinity, whereas a negative sign causes a contrary effect.…”

Section: Introductionmentioning

confidence: 99%

Selecting Relevant Descriptors for Classification by Bayesian Estimates: A Comparison with Decision Trees and Support Vector Machines Approaches for Disparate Data Sets

Carbon-Mangels¹,

Hutter²

2011

Molecular Informatics

View full text Add to dashboard Cite

Classification algorithms suffer from the curse of dimensionality, which leads to overfitting, particularly if the problem is over-determined. Therefore it is of particular interest to identify the most relevant descriptors to reduce the complexity. We applied Bayesian estimates to model the probability distribution of descriptors values used for binary classification using n-fold cross-validation. As a measure for the discriminative power of the classifiers, the symmetric form of the Kullback-Leibler divergence of their probability distributions was computed. We found that the most relevant descriptors possess a Gaussian-like distribution of their values, show the largest divergences, and therefore appear most often in the cross-validation scenario. The results were compared to those of the LASSO feature selection method applied to multiple decision trees and support vector machine approaches for data sets of substrates and nonsubstrates of three Cytochrome P450 isoenzymes, which comprise strongly unbalanced compound distributions. In contrast to decision trees and support vector machines, the performance of Bayesian estimates is less affected by unbalanced data sets. This strategy reveals those descriptors that allow a simple linear separation of the classes, whereas the superior accuracy of decision trees and support vector machines can be attributed to nonlinear separation, which are in turn more prone to overfitting.

show abstract

Section: Introductionmentioning

confidence: 99%

Selecting Relevant Descriptors for Classification by Bayesian Estimates: A Comparison with Decision Trees and Support Vector Machines Approaches for Disparate Data Sets

Carbon-Mangels¹,

Hutter²

2011

Molecular Informatics

View full text Add to dashboard Cite

show abstract

“…But also for explanatory purposes and for decision support on how to make favorable structural modifications [37]. Bioclipse Decision Support provides several means for interpretations of models.…”

Section: Decision Supportmentioning

confidence: 99%

Open Source Drug Discovery with Bioclipse

Spjuth¹,

Carlsson²,

Alvarsson³

et al. 2012

Current Topics in Medicinal Chemistry

View full text Add to dashboard Cite

Abstract.We present the open source components for drug discovery that has been developed and integrated into the graphical workbench Bioclipse. Building on a solid open source cheminformatics core, Bioclipse has advanced functionality for managing and visualizing chemical structures and related information. The features presented here include QSAR/QSPR modeling, various predictive solutions such as decision support for chemical liability assessment, site-of-metabolism prediction, virtual screening, and knowledge discovery and integration. We demonstrate the utility of the described tools with examples from computational pharmacology, toxicology, and ADME. Bioclipse is used in both academia and industry, and is a good example of open source leading to new solutions for drug discovery.

show abstract

“…However, when a precise QSAR model is created, chemical interpretation generally becomes difficult. In particular, in the case of a non-linear model, the relationship between chemical descriptors and biological activity cannot be described explicitly, and chemical interpretation becomes challenging [31]. In this case, an inverse QSAR approach is attractive to design practical chemical structures.…”

Section: Examples Of De Novo Designmentioning

confidence: 99%

Atom Coloring for Chemical Interpretation and De Novo Design for Molecular Design

Hasegawa¹,

Migita²,

Funatsu³

2011

Knowledge-Oriented Applications in Data Mining

View full text Add to dashboard Cite

On the interpretation and interpretability of quantitative structure–activity relationship models

Cited by 77 publications

References 107 publications

Selecting Relevant Descriptors for Classification by Bayesian Estimates: A Comparison with Decision Trees and Support Vector Machines Approaches for Disparate Data Sets

Selecting Relevant Descriptors for Classification by Bayesian Estimates: A Comparison with Decision Trees and Support Vector Machines Approaches for Disparate Data Sets

Open Source Drug Discovery with Bioclipse

Atom Coloring for Chemical Interpretation and De Novo Design for Molecular Design

Contact Info

Product

Resources

About