FSelector statistics

Tool stats & trends

Looking to identify usage trends or leading experts?

Protocols

FSelector specifications

Information


Unique identifier OMICS_28730
Name FSelector
Software type Application/Script
Interface Command line interface
Restrictions to use None
Input format CSV, ARFF, LibSVM
Output format CSV, ARFF, LibSVM
Operating system Unix/Linux, Mac OS, Windows
Programming languages Ruby
License MIT License
Computer skills Advanced
Version 1.4.0
Stability Stable
Maintained Yes

Download


github.png

Versioning


No version available

Documentation


Maintainers


  • person_outline Stephen H. Bryant
  • person_outline Yanli Wang
  • person_outline Tiejun Cheng

Additional information


http://www.rubydoc.info/gems/fselector/frames

Publication for FSelector

FSelector citations

 (13)
call_split

Transcriptome Wide Annotation of m5C RNA Modifications Using Machine Learning

2018
Front Plant Sci
PMCID: 5915569
PMID: 29720995
DOI: 10.3389/fpls.2018.00519
call_split See protocol

[…] ze L from 5- to 43-nt and feature number from 2 to 4*L+106. The feature subset was selected according to the feature importance estimated using the information gain approach implemented in R package “FSelector” (Cheng et al., ). The detailed process of model optimization is given in Figure . We initialize AUC matrix (“AUCMatrix”) and feature matrix (“FMatrix”) as two empty sets (Lines 1-2). Then f […]

library_books

A new scheme for strain typing of methicillin resistant Staphylococcus aureus on the basis of matrix assisted laser desorption ionization time of flight mass spectrometry by using machine learning approach

2018
PLoS One
PMCID: 5849341
PMID: 29534106
DOI: 10.1371/journal.pone.0194289

[…] Briefly, we used five-fold cross validation for training (four folds) and validating (one fold) the ML models. Feature selection was performed in the training set of each five-fold iteration by using FSelector (0.21) package of R software (version 3.3.2, R Foundation for Statistical Computing, http://www.r-project.org/). Features were selected using random forest algorithm. Most discriminative fea […]

library_books

Discovery and validation of a colorectal cancer classifier in a new blood test with improved performance for high risk subjects

2017
PMCID: 5526294
PMID: 28769740
DOI: 10.1186/s12014-017-9163-z

[…] guage running in Unix and OSX environments []. The grid search code was developed in-house, and run parallelized across multiple compute servers. Most feature selection algorithms were drawn from the FSelector package []; some were constructed using the randomForest [] or glmnet [] packages. Classifier algorithms were drawn from the randomForest [], glmnet [], e1071 [], kknn [], and mboost [] pack […]

library_books

A clustering based approach for efficient identification of microRNA combinatorial biomarkers

2017
BMC Genomics
PMCID: 5374636
PMID: 28361698
DOI: 10.1186/s12864-017-3498-8

[…] S and consistency-based methods determine the number of selected features automatically. For other methods, we chose the subsets consisting of top 2, 3 and 4 features in the assessment. The R package FSelector [] was adopted to implement these eight methods in the comparison experiments.Most feature selection methods shown in Table are filtering methods, except that BFS is a wrapper method, and t […]

call_split

Metabolic Fingerprint of PS3 Induced Resistance of Grapevine Leaves against Plasmopara viticola Revealed Differences in Elicitor Triggered Defenses

2017
Front Plant Sci
PMCID: 5306141
PMID: 28261225
DOI: 10.3389/fpls.2017.00101
call_split See protocol

[…] 2i datasets, it was shown a great improvement of the classification models applying before them the Relief algorithm. This chooses the features that can be most distinguished between classes (Package FSelector, Rstudio Inc., Version 0.99.896). […]

call_split

Analysis of gene expression to predict dynamics of future hypertension incidence in type 2 diabetic patients

2016
BMC Proc
PMCID: 5133526
PMID: 27980621
DOI: 10.1186/s12919-016-0015-z
call_split See protocol

[…] K-fold cross-validation. All calculations were performed using Rstudio with additional packages like foreach, doParallel, plyr, reshape2, ggplot2, illuminaHumanv1.db, kinship2, Matrix, coxme, caret, FSelector. KING software was used to determine kinship coefficients from available genotype data (variant call format [VCF] files). […]

Citations

Looking to check out a full list of citations?

FSelector institution(s)
Computational Biology Branch, National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, MD, USA
FSelector funding source(s)
Supported by Intramural Research Program of the National Institutes of Health, National Library of Medicine.

FSelector reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review FSelector