Hi keegan,

thanks for the fast reply! I have troubles even with the first line - somehow my DmrSeq worked without the package BiocManager. Installed it, the output is 

> BiocManager::valid()

* sessionInfo()

R version 3.5.1 (2018-07-02)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 18.04.1 LTS

Matrix products: default
BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.7.1
LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.7.1

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] BiocManager_1.30.2

loaded via a namespace (and not attached):
[1] compiler_3.5.1 tools_3.5.1   

Bioconductor version '3.7'

  * 15 packages out-of-date
  * 0 packages too new

create a valid installation with

  BiocManager::install(c(
    "edgeR", "evaluate", "fansi", "GenomicFeatures", "graph", "mime", "plotrix",
    "R6", "rstudioapi"
  ), update = TRUE, ask = FALSE)

more details: BiocManager::valid()$too_new, BiocManager::valid()$out_of_date

Warning message:
15 packages out-of-date; 0 packages too new 

The code that leads to error is:

library(data.table)
library(gplots)
files <- list.files(pattern = "\\.cov.gz$")

readBismarkFile <- function(fileName) {
  bismarkCoverage = fread(paste('zcat', fileName) ,stringsAsFactors = F)
  bismarkCoverage = bismarkCoverage[,-4]
  colnames(bismarkCoverage) = c("chr", "start", "end", paste(fileName, "meth"), paste(fileName, "unmeth"))
  return(bismarkCoverage)
}

bismarkCoverageFinal = NA
for (file in files) {
  if is.na(bismarkCoverageFinal)){
    bismarkCoverageFinal = readBismarkFile(file)
    print(colnames(bismarkCoverageFinal))
  } else {
    if (file != "S_12.bismark.cov.gz")
      bismarkCoverageFinal = merge(bismarkCoverageFinal, readBismarkFile(file), by=c("chr","start","end"))
    print(colnames(bismarkCoverageFinal))
  }
}

bismarkCoverageFinal = as.data.frame(bismarkCoverageFinal)
### BASIC STATS
nrow(bismarkCoverageFinal)
vec <-  c(seq(from=4, to=ncol(bismarkCoverageFinal), by=2))
sampleMeth <- as.matrix(bismarkCoverageFinal[ , vec])
vec = vec + 1
sampleCov <- as.matrix(bismarkCoverageFinal[ , vec])

### DMR SEQ
library(dmrseq)
M <- sampleMeth
Cov <- sampleCov + sampleMeth
chr <- as.character(bismarkCoverageFinal[,1])
pos <- bismarkCoverageFinal[,2]
celltype <- pData(BS.chr21)$CellType
sampleNames <- paste("S", 1:11, sep="_")

bs <- BSseq(chr = chr, pos = pos,
            M = M, Cov = Cov, 
            sampleNames = sampleNames)

colours = rep("red", ncol(forDistance))
colours[c(1,9,11)] = "darkblue"
colours [c(3,5,7)] = "darkred"
pData(bs)$CellType <- colours

testCovariate <- "CellType"

blocks <- dmrseq(bs=bs[1:1000000,],
                 cutoff = 0.05,
                 testCovariate=testCovariate,
                 block = TRUE,
                 minInSpan = 50,
                 bpSpan = 1e3,
                 maxGapSmooth = 1e3,
                 maxGap = 5e3)

I think that the error is random and happens due to some incorrect permutations. So there is no "safe" settings - sometimes I lucky to not to get the error, sometimes I am not. And of course it takes a lot of time, each computation, so it is really nervous - waiting for the end of computations while this error may appear close to the end of the process and ruin everything =) I will send you the data if my department will allow it...unfortunately these are unpublished data...

Also,

I have tried to install and run analysis in two ways:

- installing `dmrseq` from GitHub

- installing `dmrseq` from Bioconductor