Protocols

RF-ACE specifications

Information


Unique identifier OMICS_28804
Name RF-ACE
Alternative name Random Forests with Artificial Contrast Ensembles
Software type Package/Module
Interface Command line interface
Restrictions to use None
Operating system Unix/Linux, Windows
Programming languages C++, MATLAB, Python, R, Shell (Bash)
License Apache License version 2.0
Computer skills Advanced
Version 1.0.8
Stability Stable
Requirements
Rcpp
Maintained Yes

Download


download.png

Versioning


No version available

Maintainers


  • person_outline Timo Erkkila
  • person_outline Kari Torkkola

Additional information


https://www.genome.gov/multimedia/slides/tcga1/tcga1_erkkila.pdf

RF-ACE citations

 (2)
call_split

Robustness of Random Forest based gene selection methods

2014
BMC Bioinformatics
PMCID: 3897925
PMID: 24410865
DOI: 10.1186/1471-2105-15-8
call_split See protocol

[…] Both the RF-ACE [,] and Boruta [] algorithms are based on the idea first introduced by []. That is, they extend the information system with shadows, which are artificial features created by permuting the order […]

library_books

An eQTL biological data visualization challenge and approaches from the visualization community

2012
BMC Bioinformatics
PMCID: 3355334
PMID: 22607587
DOI: 10.1186/1471-2105-13-S8-S8

[…] This entry applied Regulome Explorer[] to the problem of elucidating multivariate nonlinear relationships within the contest data. The team applied a decision tree approach, supported by the RF-ACE[] machine learning algorithm for discovering multivariate associations. Dimensional reduction was accomplished by growing an ensemble of decision trees, and rejecting features that did not part […]

RF-ACE reviews

star_border star_border star_border star_border star_border
star star star star star

Be the first to review RF-ACE