Entering edit mode
Dear Michael,
I have not been able to run tximeta properly. I have read #38 but could not get any clue.
The quant.sf files were generated by the latest nf-core RNA-seq pipeline (3.12.0), as the pipeline did not save the Salmon index, I generated it myself. Salmon used by nf-core is version 1.10.1, and my own version is 1.10.2 (I was not able to install 1.10.1).
Also, I downgraded dbplyr myself as I've got Error in `db_collect(). The error goes away after the downgrading.
So, the current errors I'm facing are as below:
First, I've got couldn't find matching transcriptome, returning non-ranged SummarizedExperiment when I run:
> se <- tximeta(coldata)
importing quantifications
reading in files with read_tsv
1 2 3 4 5 6
couldn't find matching transcriptome, returning non-ranged SummarizedExperiment
If I modify the code, it still cannot run through:
> setwd("/Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/Tximeta/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon/")
> dir <- "/Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon/"
> subfolder_names <- c("0hr_REP1", "0hr_REP2", "0hr_REP3", "24hr_REP1", "24hr_REP2", "24hr_REP3")
> files <- file.path(dir, subfolder_names, "quant.sf")
> file.exists(files)
[1] TRUE TRUE TRUE TRUE TRUE TRUE
> tx2gene <- read_tsv("/Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon/salmon_tx2gene.tsv")
Rows: 142698 Columns: 3
Column specification
Delimiter: "\t"
chr (3): ENSMUST00000193812, ENSMUSG00000102693, 4933401J01Rik
Use `spec()` to retrieve the full column specification for this data.
Specify the column types or set `show_col_types = FALSE` to quiet this message.
> coldata <- data.frame(files = files, names = subfolder_names, condition = c("A", "A", "A", "B", "B", "B"), stringsAsFactors = FALSE)
> coldata
files
1 /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon//0hr_REP1/quant.sf
2 /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon//0hr_REP2/quant.sf
3 /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon//0hr_REP3/quant.sf
4 /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon//24hr_REP1/quant.sf
5 /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon//24hr_REP2/quant.sf
6 /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/nf-core/output_GRCm38.p6/star_salmon/gene_level/star_salmon//24hr_REP3/quant.sf
names condition
1 0hr_REP1 A
2 0hr_REP2 A
3 0hr_REP3 A
4 24hr_REP1 B
5 24hr_REP2 B
6 24hr_REP3 B
> indexDir <- "/Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/Salmon/index/"
> fastaFTP <- "/Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/Tximeta/nf-core/output_GRCm38.p6/star_salmon/gene_level/genome/genome.transcripts.fa"
> gtfFTP <- "ftp://ftp.ensembl.org/pub/release-102/gtf/mus_musculus/Mus_musculus.GRCm38.102.gtf.gz"
> jsonFile <- file.path("/Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/Salmon/index/GRCm38.p6.json")
>
> makeLinkedTxome(indexDir=indexDir,
+ source="LocalEnsembl", organism="Mus musculus",
+ release="102", genome="GRCm38",
+ fasta=fastaFTP, gtf=gtfFTP)
writing linkedTxome to /Users/hinmanmak/Library/CloudStorage/OneDrive-KarolinskaInstitutet/Maria_Lab/Citrullination_project/NGS/Christina/RNA-seq/P12516/Analysis/Salmon/index/.json
linkedTxome is same as already in bfc
> se <- tximeta(coldata, skipMeta=TRUE, tx2gene = tx2gene)
reading in files with read_tsv
1 2 3 4 5 6
> suppressPackageStartupMessages(library(SummarizedExperiment))
> colData(se)
DataFrame with 6 rows and 2 columns
names condition
<character> <character>
0hr_REP1 0hr_REP1 A
0hr_REP2 0hr_REP2 A
0hr_REP3 0hr_REP3 A
24hr_REP1 24hr_REP1 B
24hr_REP2 24hr_REP2 B
24hr_REP3 24hr_REP3 B
> assayNames(se)
[1] "counts" "abundance" "length"
> rowRanges(se)
NULL
> seqinfo(se)
Error in (function (classes, fdef, mtable) :
unable to find an inherited method for function 'seqinfo' for signature '"SummarizedExperiment"'
>
>sessionInfo( )
R version 4.3.1 (2023-06-16)
Platform: aarch64-apple-darwin20 (64-bit)
Running under: macOS Ventura 13.2.1
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-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
time zone: Europe/Stockholm
tzcode source: internal
attached base packages:
[1] stats4 stats graphics grDevices utils datasets methods base
other attached packages:
[1] SummarizedExperiment_1.30.2 Biobase_2.60.0 GenomicRanges_1.52.1
[4] GenomeInfoDb_1.36.4 IRanges_2.34.1 S4Vectors_0.38.2
[7] BiocGenerics_0.46.0 MatrixGenerics_1.12.3 matrixStats_1.0.0
[10] readr_2.1.4 dplyr_1.1.3 tximeta_1.18.3
loaded via a namespace (and not attached):
[1] tidyselect_1.2.0 blob_1.2.4 filelock_1.0.2
[4] Biostrings_2.68.1 bitops_1.0-7 lazyeval_0.2.2
[7] fastmap_1.1.1 RCurl_1.98-1.12 BiocFileCache_2.8.0
[10] GenomicAlignments_1.36.0 promises_1.2.1 XML_3.99-0.14
[13] digest_0.6.33 mime_0.12 lifecycle_1.0.3
[16] ProtGenerics_1.32.0 ellipsis_0.3.2 KEGGREST_1.40.1
[19] interactiveDisplayBase_1.38.0 RSQLite_2.3.2 magrittr_2.0.3
[22] compiler_4.3.1 rlang_1.1.1 progress_1.2.2
[25] tools_4.3.1 utf8_1.2.4 yaml_2.3.7
[28] rtracklayer_1.60.1 prettyunits_1.2.0 S4Arrays_1.0.6
[31] bit_4.0.5 curl_5.1.0 DelayedArray_0.26.7
[34] xml2_1.3.5 abind_1.4-5 BiocParallel_1.34.2
[37] purrr_1.0.2 withr_2.5.2 grid_4.3.1
[40] fansi_1.0.5 xtable_1.8-4 biomaRt_2.56.1
[43] cli_3.6.1 crayon_1.5.2 generics_0.1.3
[46] rstudioapi_0.15.0 tzdb_0.4.0 httr_1.4.7
[49] rjson_0.2.21 DBI_1.1.3 cachem_1.0.8
[52] stringr_1.5.0 zlibbioc_1.46.0 parallel_4.3.1
[55] AnnotationDbi_1.62.2 AnnotationFilter_1.24.0 BiocManager_1.30.22
[58] XVector_0.40.0 restfulr_0.0.15 vctrs_0.6.4
[61] Matrix_1.6-1.1 jsonlite_1.8.7 hms_1.1.3
[64] bit64_4.0.5 ensembldb_2.24.1 GenomicFeatures_1.52.2
[67] glue_1.6.2 codetools_0.2-19 stringi_1.7.12
[70] BiocVersion_3.17.1 later_1.3.1 BiocIO_1.10.0
[73] tibble_3.2.1 pillar_1.9.0 rappdirs_0.3.3
[76] htmltools_0.5.6.1 GenomeInfoDbData_1.2.10 R6_2.5.1
[79] dbplyr_2.3.4 tximport_1.28.0 vroom_1.6.4
[82] lattice_0.22-5 shiny_1.7.5.1 AnnotationHub_3.8.0
[85] png_0.1-8 Rsamtools_2.16.0 memoise_2.0.1
[88] httpuv_1.6.12 Rcpp_1.0.11 pkgconfig_2.0.3
Thanks very much for helping!
