Hi!

I am trying to read the following files into a raw MethylKit. However I am getting an error.

The error is: Error in if (is.na(treatment)) stop("Treatment vector is missing.") : the condition has length > 1

Has anyone else had this issue?

These are my codes

setwd("/Volumes/One Touch/3.1.Cout")
library(methylKit)
library(xlsx)

sampleinfo <- read.xlsx("/Volumes/One Touch/3.1.Cout/sampleinfo.xlsx",sheetName = "1")
head(sampleinfo)
 #  grade        id treatment1 treatment2
 #1 Normal 02-T17325          0          0
#2  CIN1 02-T17380          0          0
#3  CIN1 02-T17397          0          0
#4  Normal 02-T17407          0          0
#5  Normal 02-T17411          0          0
#6 Normal 02-T17451          0          0

file_list2 <- list(paste0(sampleinfo$id,".met.txt.gz"))
myobj <-  methRead(file_list2,
                    sample.id=sampleinfo$id,
                    context = "CpG",
                    assembly="hg19",
                    treatment=sampleinfo$treatment1
  )


# Received list of locations.
Error in if (is.na(treatment)) stop("Treatment vector is missing.") : 
  the condition has length > 1


sessionInfo( )

#R version 4.3.1 (2023-06-16)
#Platform: x86_64-apple-darwin20 (64-bit)
#Running under: macOS Big Sur 11.7.10

#Matrix products: default
#BLAS:   /System/Library/Frameworks/Accelerate.framework/Versions/A/Frameworks/vecLib.framework/Versions/A/libBLAS.dylib 
#LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib;  LAPACK version 3.11.0

attached base packages:
[1] stats4    stats     graphics  grDevices utils     datasets  methods  
[8] base     

other attached packages:
 [1] xlsx_0.6.5                        BSgenome.Hsapiens.UCSC.hg19_1.4.3
 [3] BSgenome_1.70.2                   rtracklayer_1.62.0               
 [5] BiocIO_1.12.0                     Biostrings_2.70.3                
 [7] XVector_0.42.0                    methylKit_1.28.0                 
 [9] GenomicRanges_1.54.1              GenomeInfoDb_1.38.8              
[11] IRanges_2.36.0                    S4Vectors_0.40.2                 
[13] BiocGenerics_0.48.1              

loaded via a namespace (and not attached):
 [1] tidyselect_1.2.1            dplyr_1.1.4                
 [3] R.utils_2.12.3              bitops_1.0-7               
 [5] RCurl_1.98-1.14             GenomicAlignments_1.38.2   
 [7] XML_3.99-0.16.1             lifecycle_1.0.4            
 [9] survival_3.5-8              statmod_1.5.0              
[11] magrittr_2.0.3              compiler_4.3.1             
[13] rlang_1.1.3                 tools_4.3.1                
[15] utf8_1.2.4                  yaml_2.3.8                 
[17] data.table_1.15.4           S4Arrays_1.2.1             
[19] mclust_6.1                  DelayedArray_0.28.0        
[21] plyr_1.8.9                  abind_1.4-5                
[23] BiocParallel_1.36.0         HDF5Array_1.30.1           
[25] numDeriv_2016.8-1.1         R.oo_1.26.0                
[27] grid_4.3.1                  fansi_1.0.6                
[29] colorspace_2.1-0            Rhdf5lib_1.24.2            
[31] ggplot2_3.5.0               scales_1.3.0               
[33] gtools_3.9.5                iterators_1.0.14           
[35] MASS_7.3-60.0.1             SummarizedExperiment_1.32.0
[37] bbmle_1.0.25.1              cli_3.6.2                  
[39] mvtnorm_1.2-4               crayon_1.5.2               
[41] generics_0.1.3              rstudioapi_0.16.0          
[43] reshape2_1.4.4              rjson_0.2.21               
[45] DelayedMatrixStats_1.24.0   bdsmatrix_1.3-7            
[47] rhdf5_2.46.1                qvalue_2.34.0              
[49] stringr_1.5.1               zlibbioc_1.48.2            
[51] splines_4.3.1               parallel_4.3.1             
[53] BiocManager_1.30.22         restfulr_0.0.15            
[55] matrixStats_1.2.0           vctrs_0.6.5                
[57] methrix_1.16.0              glmnet_4.1-8               
[59] Matrix_1.6-5                fastseg_1.48.0             
[61] foreach_1.5.2               limma_3.58.1               
[63] glue_1.7.0                  emdbook_1.3.13             
[65] codetools_0.2-19            rJava_1.0-11               
[67] stringi_1.8.3               shape_1.4.6.1              
[69] gtable_0.3.4                munsell_0.5.0              
[71] tibble_3.2.1                pillar_1.9.0               
[73] xlsxjars_0.6.1              rhdf5filters_1.14.1        
[75] GenomeInfoDbData_1.2.11     R6_2.5.1                   
[77] sparseMatrixStats_1.14.0    lattice_0.22-6             
[79] Biobase_2.62.0              R.methodsS3_1.8.2          
[81] Rsamtools_2.18.0            Rcpp_1.0.12                
[83] fastJT_1.0.6                coda_0.19-4.1              
[85] SparseArray_1.2.4           MatrixGenerics_1.14.0      
[87] pkgconfig_2.0.3

Best wishes,

Shimin

The argument for sample.id, if you pass a list of samples, must also be a list.

## from the examples
> file.list=list(
              system.file("extdata", "test1.myCpG.txt", package = "methylKit"),
              system.file("extdata", "test2.myCpG.txt", package = "methylKit"),
              system.file("extdata", "control1.myCpG.txt", package = "methylKit"),
              system.file("extdata", "control2.myCpG.txt", package = "methylKit") 
              )
> d.f <- data.frame(id = c("test1","test2","ctl1","ctl2"), treatment = c(1,1,0,0))

> myobj <- methRead(file.list, d.f$id, "hg18", treatment = d.f$treatment)
Received list of locations.
Error in if (is.na(treatment)) stop("Treatment vector is missing.") : 
  the condition has length > 1

> myobj <- methRead(file.list, as.list(d.f$id), "hg18", treatment = d.f$treatment)
Received list of locations.
Reading file.
Reading file.
Reading file.
Reading file.