Results

Here, we present the main results of the study.  In order to obtain them we have used the following R code:
library(netbenchmark)
top20.aupr <- netbenchmark( methods="all", local.noise=20,
                                                     global.noise=10, noiseType=c("normal","lognormal"),
                                                     seed=1108) 

Boxplots of performance. Each box represents the statistics of a method with the ranking performance across all datasources of the package, the smaller the rank the better. The white dot represents the median of the distribution, the box goes form the first to third quartile, while whiskers are lines drawn from the ends of the box to the maximum and minimum of the data excluding outliers that are represented with a mark outside the whiskers.

Performances of the various GRN inference methods on the datasources.  AUPR in the top 20% of the possible connections with a undirected evaluation for each GRN inference method on the different datasources of the benchmark with a 20% local Gaussian noise and 10% of global lognormal noise. The best statistically significant results tested with a Wilcoxon test are highlighted for each datasource.
Subpages (1): References