Random Forest:  A Classification and Regression Tool for Compound Classification and QSAR Modeling

Svetnik, Vladimir; Liaw, Andy; Tong, Charles; Culberson, Joseph; Sheridan, Robert P.; Feuston, Bradley P.

doi:10.1021/ci034160g

Cited by 2,926 publications

(2,029 citation statements)

References 27 publications

Supporting

Mentioning

1,992

Contrasting

Unclassified

Order By: Relevance

“…Data from our OCT1 HTS experiment were used as a training set to construct a binary structure−activity relationship (SAR) model correlating molecular features of 1780 compounds from the Pharmacon library with their inhibitory activities, discretized into two classes: inhibitors and noninhibitors. The Random Forest (RF) algorithm 33 was employed to build an ensemble classifier (SAR-I). We evaluated the accuracy of the SAR-I model (i.e., the area under the receiver operating characteristic curve (auROC)) by 100 repeated cross-validation runs ( Figure 7A).…”

Section: ■ Resultsmentioning

confidence: 99%

Discovery of Competitive and Noncompetitive Ligands of the Organic Cation Transporter 1 (OCT1; SLC22A1)

et al. 2017

View full text Add to dashboard Cite

Organic cation transporter 1 (OCT1) plays a critical role in the hepatocellular uptake of structurally diverse endogenous compounds and xenobiotics. Here we identified competitive and noncompetitive OCT1-interacting ligands in a library of 1780 prescription drugs by combining in silico and in vitro methods. Ligands were predicted by docking against a comparative model based on a eukaryotic homologue. In parallel, high-throughput screening (HTS) was conducted using the fluorescent probe substrate ASP+ in cells overexpressing human OCT1. Thirty competitive OCT1 ligands, defined as ligands predicted in silico as well as found by HTS, were identified. Of the 167 ligands identified by HTS, five were predicted to potentially cause clinical drug interactions. Finally, virtual screening of 29 332 metabolites predicted 146 competitive OCT1 ligands, of which an endogenous neurotoxin, 1-benzyl-1,2,3,4-tetrahydroisoquinoline, was experimentally validated. In conclusion, by combining docking and in vitro HTS, competitive and noncompetitive ligands of OCT1 can be predicted.

show abstract

Section: ■ Resultsmentioning

confidence: 99%

Discovery of Competitive and Noncompetitive Ligands of the Organic Cation Transporter 1 (OCT1; SLC22A1)

et al. 2017

View full text Add to dashboard Cite

show abstract

“…More applications of random forests can be found in other different fields like quantitative structure-activity relationship modeling [42], nuclear magnetic resonance spectroscopy [31], or clinical decision supports in medicine in general [11].…”

Section: Some Other Related Applicationsmentioning

confidence: 99%

Random Forest for Bioinformatics

2012

Ensemble Machine Learning

590

344

View full text Add to dashboard Cite

“…These steps are repeated until a defined number of trees are created. 107 This eventually leads to a forest of regression trees.…”

Section: Qspr Modelsmentioning

confidence: 99%

Are the Sublimation Thermodynamics of Organic Molecules Predictable?

McDonagh

Palmer

Mourik

et al. 2016

J. Chem. Inf. Model.

View full text Add to dashboard Cite

We compare a range of computational methods for the prediction of sublimation thermodynamics (enthalpy, entropy and free energy of sublimation). These include a model from theoretical chemistry that utilizes crystal lattice energy minimization (with the DMACRYS program) and QSPR models generated by both machine learning (Random Forest and Support Vector Machines) and regression (Partial Least Squares) methods. Using these methods we investigate the predictability of the enthalpy, entropy and free energy of sublimation, with consideration of whether such a method may be able to improve solubility prediction schemes. Previous work has suggested that the major source of error in solubility prediction schemes involving a thermodynamic cycle via the solid state is in the modeling of the free energy change away from the solid state. Yet contrary to this conclusion other work has found that the inclusion of terms such as the enthalpy of sublimation in QSPR methods 2 does not improve the predictions of solubility. We suggest the use of theoretical chemistry terms, detailed explicitly in the methods section, as descriptors for the prediction of the enthalpy and free energy of sublimation. A dataset of 158 molecules with experimental sublimation thermodynamics values and some CSD refcodes has been collected from the literature and is provided with their original source references.

show abstract

Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling

Cited by 2,926 publications

References 27 publications

Discovery of Competitive and Noncompetitive Ligands of the Organic Cation Transporter 1 (OCT1; SLC22A1)

Discovery of Competitive and Noncompetitive Ligands of the Organic Cation Transporter 1 (OCT1; SLC22A1)

Random Forest for Bioinformatics

Are the Sublimation Thermodynamics of Organic Molecules Predictable?

Contact Info

Product

Resources

About