I am trying to use Tximport to eventually use edgeR TMM normalization method. I am trying to get a normalization factor per species. For each species I have multiple tissue samples (Ie lung and kidney) and need to normalize across tissues. I have gene to orthogroup maps for each tissue and abundance files from Kallisto for each tissue. I am treating each tissue like a sample. Because I was aware of the fact that tximport needs to have the abundance files and tx2gene maps in the same order, I combined the abundance files for the tissues. For example, for the lung abundance file, it has the transcripts listed for the kidney but with 0 for all of the abundance information. Then I sorted and filled both abundance files and the tx2gene map so they have the same transcripts in the same order for all. I am still getting the error.

I followed the steps from:

https://bioconductor.org/packages/release/bioc/vignettes/tximport/inst/doc/tximport.html#Import_transcript-level_estimates

Thank you so much for your time!!

> library(readr)
> library(tximport)
> library(tximportData)
> tools:::.BioC_version_associated_with_R_version()
[1] ‘3.11’

> dir <- "/gpfs/scratch/nsipperly/RAPID/kallisto_1Nov2021/ZEROS/Mema"
> samples <- read.table(file.path(dir, "samples.txt"), header = TRUE)
> samples
       sample run
1 Mema_kidney   1
2   Mema_lung   1
> files <- file.path(dir, samples$sample, "abundance.tsv")
> names(files) <- paste0("sample", 1:2)
> all(file.exists(files))
[1] TRUE

> files
                                                                               sample1
"/gpfs/scratch/nsipperly/RAPID/kallisto_1Nov2021/ZEROS/Mema/Mema_kidney/abundance.tsv"
                                                                               sample2
  "/gpfs/scratch/nsipperly/RAPID/kallisto_1Nov2021/ZEROS/Mema/Mema_lung/abundance.tsv"

>
> tx2gene <- read_tsv("/gpfs/scratch/nsipperly/RAPID/kallisto_1Nov2021/ZEROS/Mema/MemaAlltissue2_tx2gene.sort.whole.tsv")

── Column specification ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
cols(
  TranscriptID = col_character(),
  Orthogroup = col_character()
)

> txi.kallisto.tsv <- tximport(files, type = "kallisto", tx2gene = tx2gene)
Note: importing `abundance.h5` is typically faster than `abundance.tsv`
reading in files with read_tsv
1 2 Error in tximport(files, type = "kallisto", tx2gene = tx2gene) :
  all(txId == raw[[txIdCol]]) is not TRUE
> traceback()
3: stop(simpleError(msg, call = if (p <- sys.parent(1L)) sys.call(p)))
2: stopifnot(all(txId == raw[[txIdCol]]))
1: tximport(files, type = "kallisto", tx2gene = tx2gene)

# include your problematic code here with any corresponding output 
# please also include the results of running the following in an R session 

> sessionInfo()
R version 4.0.2 (2020-06-22)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: CentOS Linux 7 (Core)

Matrix products: default
BLAS:   /gpfs/software/R-4.0.2/lib64/R/lib/libRblas.so
LAPACK: /gpfs/software/R-4.0.2/lib64/R/lib/libRlapack.so

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] tximportData_1.16.0 tximport_1.16.1     readr_1.4.0

loaded via a namespace (and not attached):
 [1] crayon_1.4.1    R6_2.5.1        lifecycle_0.2.0 magrittr_2.0.1
 [5] pillar_1.4.7    rlang_0.4.11    cli_3.0.1       rstudioapi_0.13
 [9] vctrs_0.3.5     ellipsis_0.3.1  glue_1.4.2      hms_0.5.3
[13] compiler_4.0.2  pkgconfig_2.0.3 tibble_3.0.4


#I made some dummy files for the post -- as instructed by the posting guide :) 

#Mema_kidney/abundance.tsv

target_id   length  eff_length  est_counts  tpm
Mema_kidney_Transcript_1003.p1  2865    2589.74 409 4.35504
Mema_kidney_Transcript_100606.p1    255 39.3322 117433  82331.8
Mema_kidney_Transcript_1006.p2  597 322.318 272.241 23.2913
Mema_kidney_Transcript_100754.p1    258 40.1783 16  10.9813
Mema_kidney_Transcript_1007.p1  3048    2772.74 5229    52.0037
Mema_kidney_Transcript_1011.p2  528 253.775 1012    109.966
Mema_kidney_Transcript_1012.p1  1941    1665.74 919 15.2136
Mema_kidney_Transcript_1015.p1  2769    2493.74 889 9.83049
Mema_kidney_Transcript_1019.p1  534 259.732 1420    150.761
Mema_lung_Transcript_979.p1 0   0   0   0
Mema_lung_Transcript_98263.p1   0   0   0   0
Mema_lung_Transcript_9828.p2    0   0   0   0
Mema_lung_Transcript_983.p1 0   0   0   0
Mema_lung_Transcript_985.p2 0   0   0   0
Mema_lung_Transcript_991.p1 0   0   0   0
Mema_lung_Transcript_9938.p1    0   0   0   0
Mema_lung_Transcript_9959.p2    0   0   0   0
Mema_lung_Transcript_995.p1 0   0   0   0
Mema_lung_Transcript_996.p1 0   0   0   0

#Mema_lung/abundance.tsv

target_id   length  eff_length  est_counts  tpm
Mema_kidney_Transcript_1003.p1  0   0   0   0
Mema_kidney_Transcript_100606.p1    0   0   0   0
Mema_kidney_Transcript_1006.p2  0   0   0   0
Mema_kidney_Transcript_100754.p1    0   0   0   0
Mema_kidney_Transcript_1007.p1  0   0   0   0
Mema_kidney_Transcript_1011.p2  0   0   0   0
Mema_kidney_Transcript_1012.p1  0   0   0   0
Mema_kidney_Transcript_1015.p1  0   0   0   0
Mema_kidney_Transcript_1019.p1  0   0   0   0
Mema_lung_Transcript_979.p1 1995    1764.51 819 29.9187
Mema_lung_Transcript_98263.p1   264 84.4105 55  42
Mema_lung_Transcript_9828.p2    609 380.972 1161.26 196.48
Mema_lung_Transcript_983.p1 2904    2673.51 3513    84.6992
Mema_lung_Transcript_985.p2 366 160.345 27  10.8541
Mema_lung_Transcript_991.p1 828 597.667 1179    127.156
Mema_lung_Transcript_9938.p1    414 200.22  149 47.9691
Mema_lung_Transcript_9959.p2    288 100.964 16  10.215
Mema_lung_Transcript_995.p1 1455    1224.51 630 33.1636
Mema_lung_Transcript_996.p1 1395    1164.51 442 24.4659

#/gpfs/scratch/nsipperly/RAPID/kallisto_1Nov2021/ZEROS/Mema/MemaAlltissue2_tx2gene.sort.whole.tsv

TranscriptID    Orthogroup
Mema_kidney_Transcript_1003.p1  OG0010091
Mema_kidney_Transcript_100606.p1    OG0014354
Mema_kidney_Transcript_1006.p2  OG0002057
Mema_kidney_Transcript_100754.p1    OG0027137
Mema_kidney_Transcript_1007.p1  OG0009085
Mema_kidney_Transcript_1011.p2  OG0004785
Mema_kidney_Transcript_1012.p1  OG0007052
Mema_kidney_Transcript_1015.p1  OG0002164
Mema_kidney_Transcript_1019.p1  OG0003830
Mema_lung_Transcript_979.p1 OG0002798
Mema_lung_Transcript_98263.p1   OG0002166
Mema_lung_Transcript_9828.p2    OG0006178
Mema_lung_Transcript_983.p1 OG0008817
Mema_lung_Transcript_985.p2 OG0010503
Mema_lung_Transcript_991.p1 OG0006243
Mema_lung_Transcript_9938.p1    OG0013741
Mema_lung_Transcript_9959.p2    OG0001898
Mema_lung_Transcript_995.p1 OG0008495
Mema_lung_Transcript_996.p1 OG0010962

I think what this is saying

all(txId == raw[[txIdCol]]) is not TRUE

Is that some of the files are quantified against a different index than others. tximport can only import files with a shared index.