This is a test version of Biostars. For the public version, visit https://www.biostars.org.
problem with BioMM package

I'm learning how to use the BioMM package from Bioconductor just for making some predictions about cancer types based on epigenomic data, but when I follow the tutorial (https://bioconductor.org/packages/devel/bioc/vignettes/BioMM/inst/doc/BioMMtutorial.html) I have a problem with the part of the code that should plot some data: instead of getting the plot I just get an output with this:

posFeature: 50
null device 
          1

The code I use is exactly the same as the one used in the tutorial:

library(BioMM)
library(BiocParallel)
library(parallel)
library(ranger)
library(rms)
library(glmnet)
library(e1071)
library(pROC)
library(vioplot)
library(variancePartition)
library(CMplot)

## Pathway level data or stage-2 data prepared by reconBySupervised()
stage2dataA <- readRDS(system.file("extdata", "/stage2dataA.rds", 
                                   package="BioMM"))
head(stage2dataA[, 1:5]) 
dim(stage2dataA)

### Alternatively, 'stage2dataA' can be created by the following code:
## Parameters  
classifier <- "randForest" 
predMode <- "probability" 
paramlist <- list(ntree=300, nthreads=40)  
param1 <- MulticoreParam(workers = 1)
param2 <- MulticoreParam(workers = 10)  

set.seed(123)
## This will take a bit longer to run
stage2dataA <- reconBySupervised(trainDataList=pathlist, testDataList=NULL,
                                 resample="BS", dataMode="allTrain",
                                 repeatA=25, repeatB=1, nfolds=10,
                                 FSmethod=NULL, cutP=0.1, fdr=NULL, FScore=param1,
                                 classifier, predMode, paramlist,
                                 innerCore=param2, outFileA=NULL, outFileB=NULL)

param <- MulticoreParam(workers = 1)  
plotVarExplained(data=stage2dataA, posF=TRUE), 
                 core=param, horizontal=FALSE, fileName=NULL)

Please, does someone have any idea about what I'm doing wrong or if something is missing?

Thank you so much.

bioconductor r genomics machine learning

0 answers

No answers yet.

Log in to answer this question.