netbenchmark-package {netbenchmark} | R Documentation |
For a given list of network inference algorithms, netbenchmark
performs a benchmark
between them. It makes use of five different big gene datasources, it relies on a random subsampling of
each one of the datasource and noise addition in order to generate the datasets.
This package is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International.
Pau Bellot, Catharina Olsen, Patrick E Meyer, with contributions from Alexandre Irrthum
Maintainer: Pau Bellot <pau.bellot@upc.edu>
Pau Bellot, Catharina Olsen, Philippe Salembier, Albert Oliveras-Verges, and Patrick E Meyer. NetBenchmark: A Bioconductor Package for Reproducible Benchmarks of Gene Regulatory Network Inference. Submitted, 2015.
## Not run: AUPR20.list<-netbenchmark(datasources.names=c("syntren300", "rogers1000"),datasets.num=7) AUPR20.300exp.list<-netbenchmark(methods=c("aracne.wrap","mrnet.wrap", "GeneNet.wrap"),datasources.names=c("syntren300","rogers1000"), experiments=300,global.noise=10,noiseType="lognormal") AUPR20.n30.list<-netbenchmark(methods=c("all.fast","mrnet.wrap", "Genie3.wrap"),eval="AUROC",local.noise=30) ## End(Not run)