BaTFLED3D: Bayesian Tensor Factorization Linked to External Data

BaTFLED is a machine learning algorithm designed to make predictions and determine interactions in data that varies along three independent modes. For example BaTFLED was developed to predict the growth of cell lines when treated with drugs at different doses. The first mode corresponds to cell lines and incorporates predictors such as cell line genomics and growth conditions. The second mode corresponds to drugs and incorporates predictors indicating known targets and structural features. The third mode corresponds to dose and there are no dose-specific predictors (although the algorithm is capable of including predictors for the third mode if present). See 'BaTFLED3D_vignette.rmd' for a simulated example.

Version: 0.2.1
Depends: R (≥ 3.2.2)
Imports: foreach, R6, iterators, rTensor, RColorBrewer
Suggests: doMC, doParallel, knitr, rmarkdown
Published: 2017-04-02
Author: Nathan Lazar [aut, cre]
Maintainer: Nathan Lazar <nathan.lazar at>
License: CC BY-NC-SA 4.0
NeedsCompilation: no
Materials: README
CRAN checks: BaTFLED3D results


Reference manual: BaTFLED3D.pdf
Vignettes: BaTFLED3D_vignette
Package source: BaTFLED3D_0.2.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X El Capitan binaries: r-release: BaTFLED3D_0.2.1.tgz
OS X Mavericks binaries: r-oldrel: BaTFLED3D_0.2.1.tgz
Old sources: BaTFLED3D archive


Please use the canonical form to link to this page.