varSelRF statistics

Tool stats & trends

Looking to identify usage trends or leading experts?


varSelRF specifications


Unique identifier OMICS_14607
Name varSelRF
Software type Package/Module
Interface Command line interface
Restrictions to use None
Input data The gene expression data, the class labels.
Output data The bootstrapped estimates of prediction error rate, assessments of the stability of the solutions, clickable tables link to additional information for each gene (GO terms, PubMed citations, KEGG pathways).
Operating system Unix/Linux
Programming languages Python, R
License GNU General Public License version 3.0, GNU General Public License version 2.0
Computer skills Advanced
Version 0.7-8
Stability Stable
parallel, randomforest, R(≥2.0.0)
Source code URL
Maintained Yes




No version available



  • person_outline Ramón Diaz-Uriarte

Publication for varSelRF

varSelRF citations


Rapid and easy detection of low level resistance to vancomycin in methicillin resistant Staphylococcus aureus by matrix assisted laser desorption ionization time of flight mass spectrometry

PLoS One
PMCID: 5844673
PMID: 29522576
DOI: 10.1371/journal.pone.0194212
call_split See protocol

[…] ssifier was constructed from the matrix after variable selection; in this procedure, a combination of peaks yielding the smallest out-of-bag error rate was selected by an algorithm implemented in the varSelRF package []. This algorithm iteratively fitted random forests to the data, building a new forest after discarding a fraction of peaks with the smallest variable importance. The graphical user […]


Signaling protein signature predicts clinical outcome of non small cell lung cancer

BMC Cancer
PMCID: 5840771
PMID: 29510676
DOI: 10.1186/s12885-018-4104-4
call_split See protocol

[…] were assigned as training sets by computer-generated random numbers. Random forest algorithm was used to identify protein signatures in the training sets []. The procedure was implemented using the R varSelRF package with parameters “ntree = 5000, ntreeIterat = 2000, vars.drop.frac = 0.2”, which was built upon the randomForest package [, ]. The set of proteins with the smallest out-of-bag error ra […]


Predicting Lameness in Sheep Activity Using Tri Axial Acceleration Signals

PMCID: 5789307
PMID: 29324700
DOI: 10.3390/ani8010012
call_split See protocol

[…] o systematically assess the usefulness and identify the most important features for discriminating different activities, RF ranking of importance was performed. The R libraries ‘randomForest’ [] and ‘varSelRF’ [] were used to identify the relative importance of the fourteen features based on their Gini index, which is used to measure the error across the RF ensemble of trees. Within ‘randomForest’ […]


Leaf herbivory imposes fitness costs mediated by hummingbird and insect pollinators

PLoS One
PMCID: 5718403
PMID: 29211805
DOI: 10.1371/journal.pone.0188408

[…] he predictor variables. Tentative identification of the peaks was made using the NIST mass spectrum data base (). We conducted the RF analysis in several stages using the packages randomForest [] and varSelRF [] in R version 3.1.2 []. First, we conducted an RF classification analysis for all six groups (locally-induced, systemically-induced, and control for both leaves and flowers) and visually ex […]


Bacteriome and mycobiome associations in oral tongue cancer

PMCID: 5722561
PMID: 29228609
DOI: 10.18632/oncotarget.21921

[…] es [, ]. Backwards iterative variable selection and evaluation of the stability of the model (OOB error rate and variable importances) was performed using 1000 bootstrapped samples through R package ‘varSelRF’ with default settings except set to 0 []. Nine tumor/non-tumor pairs were excluded from the analysis due to insufficient bacterial sequence counts (<50 reads). Analysis across groups on […]


Metabolite and transcript markers for the prediction of potato drought tolerance

Plant Biotechnol J
PMCID: 5866952
PMID: 28929574
DOI: 10.1111/pbi.12840
call_split See protocol

[…] and mtry set to default (=p, where p is the number of predictors). Variable importance was estimated by the varImp function and is based on the Gini index. The number of predictors was reduced by the varSelRF function of the R‐package varSelRF (Díaz‐Uriarte, ) to minimize the out‐of‐bag (OOB) error rate (a measure for the prediction error that uses bootstrap aggregating, also called bagging). Iter […]


Looking to check out a full list of citations?

varSelRF institution(s)
Statistical Computing Team, Structural Biology and Biocomputing Programme, Spanish National Cancer Center (CNIO), Madrid, Spain
varSelRF funding source(s)
This work was supported by Fundación de Investigación Médica Mutua Madrileña and Project TIC2003-09331-C02-02 of the Spanish Ministry of Education and Science (MEC) and partially supported by the Ramón y Cajal programme of the Spanish MEC.

varSelRF reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review varSelRF