Mercurial > repos > iuc > tximport

comparison tximport.R @ 3:915a9dd57e1a draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/tximport commit 5f8e6e70a9d82331367f7a052a76a04c47c5144e
author iuc
date Sat, 28 Sep 2024 16:33:10 +0000
parents 3e2f1aef1aac
children
comparison
equal deleted inserted replaced
2:865d5bc8f531 3:915a9dd57e1a
1 # setup R error handling to go to stderr 1 # setup R error handling to go to stderr
2 options(show.error.messages = F, error = function() { 2 options(show.error.messages = F, error = function() {
3 cat(geterrmessage(), file = stderr()); q("no", 1, F) 3 cat(geterrmessage(), file = stderr())
4 q("no", 1, F)
4 }) 5 })
5 6
6 # we need that to not crash galaxy with an UTF8 error on German LC settings. 7 # we need that to not crash galaxy with an UTF8 error on German LC settings.
7 loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8") 8 loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8")
8 9
10 options(stringAsFactors = FALSE, useFancyQuotes = FALSE) 11 options(stringAsFactors = FALSE, useFancyQuotes = FALSE)
11 args <- commandArgs(trailingOnly = TRUE) 12 args <- commandArgs(trailingOnly = TRUE)
12 13
13 # get options, using the spec as defined by the enclosed list. 14 # get options, using the spec as defined by the enclosed list.
14 # we read the options from the default: commandArgs(TRUE). 15 # we read the options from the default: commandArgs(TRUE).
15 spec <- matrix(c( 16 spec <- matrix(
16 "help", "h", 0, "logical", 17 c(
17 "out_file", "o", 1, "character", 18 "help", "h", 0, "logical",
18 "countsFiles", "n", 1, "character", 19 "out_file", "o", 1, "character",
19 "countsFromAbundance", "r", 1, "character", 20 "countsFiles", "n", 1, "character",
20 "format", "v", 1, "character", 21 "countsFromAbundance", "r", 1, "character",
21 "gff_file", "H", 0, "character", 22 "format", "v", 1, "character",
22 "tx2gene", "f", 0, "character", 23 "gff_file", "H", 0, "character",
23 "geneIdCol", "l", 0, "character", 24 "tx2gene", "f", 0, "character",
24 "txIdCol", "p", 1, "character", 25 "geneIdCol", "l", 0, "character",
25 "abundanceCol", "i", 0, "character", 26 "txIdCol", "p", 1, "character",
26 "countsCol", "y", 1, "character", 27 "abundanceCol", "i", 0, "character",
27 "lengthCol", "x", 1, "character"), 28 "countsCol", "y", 1, "character",
28 byrow = TRUE, ncol = 4) 29 "lengthCol", "x", 1, "character"
30 ),
31 byrow = TRUE, ncol = 4
32 )
29 33
30 opt <- getopt(spec) 34 opt <- getopt(spec)
31 35
32 # if help was asked for print a friendly message 36 # if help was asked for print a friendly message
33 # and exit with a non-zero error code 37 # and exit with a non-zero error code
34 if (!is.null(opt$help)) { 38 if (!is.null(opt$help)) {
35 cat(getopt(spec, usage = TRUE)) 39 cat(getopt(spec, usage = TRUE))
36 q(status = 1) 40 q(status = 1)
37 }
38
39 if (is.null(opt$gff_file) & is.null(opt$tx2gene)) {
40 cat("A GFF/GTF file or a tx2gene table is required\n")
41 q(status = 1)
42 } 41 }
43 42
44 if (opt$format == "none") { #custom format 43 if (is.null(opt$gff_file) & is.null(opt$tx2gene)) {
44 cat("A GFF/GTF file or a tx2gene table is required\n")
45 q(status = 1)
46 }
47
48 if (opt$format == "none") { # custom format
45 if (is.null(opt$txIdCol) | is.null(opt$abundanceCol) | is.null(opt$countsCol) | is.null(opt$lengthCol)) { 49 if (is.null(opt$txIdCol) | is.null(opt$abundanceCol) | is.null(opt$countsCol) | is.null(opt$lengthCol)) {
46 cat("If you select a custom format for the input files you need to specify the column names\n") 50 cat("If you select a custom format for the input files you need to specify the column names\n")
47 q(status = 1) 51 q(status = 1)
48 } 52 }
49 } 53 }
50 54
51 if (is.null(opt$countsFiles)) { 55 if (is.null(opt$countsFiles)) {
52 cat("'countsFiles' is required\n") 56 cat("'countsFiles' is required\n")
53 q(status = 1) 57 q(status = 1)
54 } 58 }
55 59
56 60
57 # load samples from tab file 61 # load samples from tab file
58 samples_df <- read.table(opt$countsFiles, sep = "\t", header = TRUE) 62 samples_df <- read.table(opt$countsFiles, sep = "\t", header = TRUE)
73 }) 77 })
74 txdb <- makeTxDbFromGFF(opt$gff_file) 78 txdb <- makeTxDbFromGFF(opt$gff_file)
75 k <- keys(txdb, keytype = "TXNAME") 79 k <- keys(txdb, keytype = "TXNAME")
76 tx2gene <- select(txdb, keys = k, columns = "GENEID", keytype = "TXNAME") 80 tx2gene <- select(txdb, keys = k, columns = "GENEID", keytype = "TXNAME")
77 # Remove 'transcript:' from transcript IDs (when gffFile is a GFF3 from Ensembl and the transcript does not have a Name) 81 # Remove 'transcript:' from transcript IDs (when gffFile is a GFF3 from Ensembl and the transcript does not have a Name)
78 tx2gene$TXNAME <- sub("^transcript:", "", tx2gene$TXNAME) # nolint 82 tx2gene$TXNAME <- sub("^transcript:", "", tx2gene$TXNAME) # nolint
79
80 } else { 83 } else {
81 tx2gene <- read.table(opt$tx2gene, header = FALSE) 84 tx2gene <- read.table(opt$tx2gene, header = FALSE)
82 } 85 }
83 86
84 87
85 88
86 ## 89 ##
87 if (is.null(opt$geneIdCol)) { ## there is a tx2gene table 90 if (is.null(opt$geneIdCol)) { ## there is a tx2gene table
88 if (opt$format == "none") { #predefined format 91 if (opt$format == "none") { # predefined format
89 txi_out <- tximport(files, type = "none", txIdCol = opt$txIdCol, abundanceCol = opt$abundanceCol, countsCol = opt$countsCol, lengthCol = opt$lengthCol, tx2gene = tx2gene, countsFromAbundance = opt$countsFromAbundance) 92 txi_out <- tximport(files, type = "none", txIdCol = opt$txIdCol, abundanceCol = opt$abundanceCol, countsCol = opt$countsCol, lengthCol = opt$lengthCol, tx2gene = tx2gene, countsFromAbundance = opt$countsFromAbundance)
90 } else { 93 } else {
91 txi_out <- tximport(files, type = opt$format, tx2gene = tx2gene, countsFromAbundance = opt$countsFromAbundance) 94 txi_out <- tximport(files, type = opt$format, tx2gene = tx2gene, countsFromAbundance = opt$countsFromAbundance)
92 } 95 }
93 } else { # the gene_ID is a column in the counts table 96 } else { # the gene_ID is a column in the counts table
94 if (opt$format == "none") { #predefined format 97 if (opt$format == "none") { # predefined format
95 txi_out <- tximport(files, type = "none", geneIdCol = opt$geneIdCol, txIdCol = opt$txIdCol, abundanceCol = opt$abundanceCol, countsCol = opt$countsCol, lengthCol = opt$lengthCol, tx2gene = tx2gene, countsFromAbundance = opt$countsFromAbundance) 98 txi_out <- tximport(files, type = "none", geneIdCol = opt$geneIdCol, txIdCol = opt$txIdCol, abundanceCol = opt$abundanceCol, countsCol = opt$countsCol, lengthCol = opt$lengthCol, tx2gene = tx2gene, countsFromAbundance = opt$countsFromAbundance)
96 } else { 99 } else {
97 txi_out <- tximport(files, type = opt$format, geneIdCol = opt$geneIdCol, countsFromAbundance = opt$countsFromAbundance) 100 txi_out <- tximport(files, type = opt$format, geneIdCol = opt$geneIdCol, countsFromAbundance = opt$countsFromAbundance)
98 } 101 }
99
100 } 102 }
101 # write count as table 103 # write count as table
102 write.table(txi_out$counts, file = opt$out_file, row.names = TRUE, col.names = TRUE, quote = FALSE, sep = "\t") 104 write.table(txi_out$counts, file = opt$out_file, row.names = TRUE, col.names = TRUE, quote = FALSE, sep = "\t")