Mercurial > repos > iuc > dada2_mergepairs
changeset 7:5c865a382933 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/dada2 commit c2f6071f729b74540354f4a9e7084c9ac468a135
| author | iuc |
|---|---|
| date | Mon, 07 Aug 2023 01:33:31 +0000 |
| parents | 84743da21318 |
| children | 06be32772107 |
| files | macros.xml test-data/gentest.R |
| diffstat | 2 files changed, 18 insertions(+), 17 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Fri Jun 30 07:56:20 2023 +0000 +++ b/macros.xml Mon Aug 07 01:33:31 2023 +0000 @@ -12,8 +12,8 @@ <xref type="bioconductor">dada2</xref> </xrefs> </xml> - <token name="@DADA2_VERSION@">1.20</token> - <token name="@WRAPPER_VERSION@">1</token> + <token name="@DADA2_VERSION@">1.28</token> + <token name="@WRAPPER_VERSION@">0</token> <xml name="version_command"> <version_command><![CDATA[ @@ -43,17 +43,18 @@ - uniques is a named integer vector (columns=ASVs, only one rows)--> <token name="@READ_FOO@"><![CDATA[ read.uniques <- function ( fname ) { - p <- read.table(fname, header=F, sep="\t") + x <- read.table(fname, header=F, sep="\t") n <-x[,2] names(n)<-x[,1] + return(n) } #def read_data($dataset) #if $dataset.is_of_type('dada2_sequencetable') - t(as.matrix( read.table('$dataset', header=T, sep="\t", row.names=1) )) + t(read.table('$dataset', header=T, sep="\t", row.names=1, check.names=FALSE)) #else if $dataset.is_of_type('dada2_uniques') read.uniques('$dataset') #else if $dataset.is_of_type('tabular') - read.table('$dataset', header=T, sep="\t", row.names=1) + read.table('$dataset', header=T, sep="\t", row.names=1, check.names=FALSE) #else readRDS('$dataset') #end if @@ -97,7 +98,7 @@ <!-- for filterAndTrim --> <xml name="trimmers"> - <section name="trim" title="Trimming parameters"> + <section name="trim" title="Trimming parameters" expanded="true"> <param argument="truncQ" type="integer" value="2" min="0" label="Truncate reads at quality threshold" help="Truncate reads at the first instance of a quality score less than or equal to this threshold"/> <param argument="trimLeft" type="integer" value="0" min="0" label="Trim start of each read" help="The number of nucleotides to remove from the start of each read."/> <param argument="trimRight" type="integer" value="0" min="0" label="Trim end of each read" help="The number of nucleotides to remove from the end of each read"/> @@ -105,7 +106,7 @@ </section> </xml> <xml name="filters"> - <section name="filter" title="Filtering parameters"> + <section name="filter" title="Filtering parameters" expanded="true"> <param argument="maxLen" type="integer" value="" optional="true" min="0" label="Remove long reads" help="Remove reads with length greater than this value. Default: no length threshold"/> <param argument="minLen" type="integer" value="20" min="0" label="Remove short reads" help="Remove reads with length less than this value. Default: 20"/> <param argument="maxN" type="integer" value="0" min="0" label="Remove reads with more Ns" help="Note that some of the subsequent dada pipeline steps do not allow Ns"/>
--- a/test-data/gentest.R Fri Jun 30 07:56:20 2023 +0000 +++ b/test-data/gentest.R Mon Aug 07 01:33:31 2023 +0000 @@ -11,9 +11,9 @@ print("filterAndTrim") for (i in seq_len(fwd)) { - ftout <- dada2::filterAndTrim(fwd[i], filt_fwd[i], rev[i], filt_rev[i]) - b <- paste(strsplit(fwd[i], ".", fixed = TRUE)[[1]][1], "tab", sep = ".") - write.table(ftout, b, quote = FALSE, sep = "\t", col.names = NA) + ftout <- dada2::filterAndTrim(fwd[i], filt_fwd[i], rev[i], filt_rev[i]) + b <- paste(strsplit(fwd[i], ".", fixed = TRUE)[[1]][1], "tab", sep = ".") + write.table(ftout, b, quote = FALSE, sep = "\t", col.names = NA) } # In the test only the 1st data set is used @@ -64,15 +64,15 @@ dada_fwd <- dada2::dada(filt_fwd, err_fwd) dada_rev <- dada2::dada(filt_rev, err_rev) for (id in sample_names) { - saveRDS(dada_fwd[[id]], file = paste("dada_", id, "_R1.Rdata", sep = "")) - saveRDS(dada_rev[[id]], file = paste("dada_", id, "_R2.Rdata", sep = "")) + saveRDS(dada_fwd[[id]], file = paste("dada_", id, "_R1.Rdata", sep = "")) + saveRDS(dada_rev[[id]], file = paste("dada_", id, "_R2.Rdata", sep = "")) } # merge pairs print("mergePairs") merged <- dada2::mergePairs(dada_fwd, filt_fwd, dada_rev, filt_rev) for (id in sample_names) { - saveRDS(merged[[id]], file = paste("mergePairs_", id, ".Rdata", sep = "")) + saveRDS(merged[[id]], file = paste("mergePairs_", id, ".Rdata", sep = "")) } @@ -85,8 +85,8 @@ df <- data.frame(length = as.numeric(names(reads_per_seqlen)), count = reads_per_seqlen) pdf("makeSequenceTable.pdf") ggplot(data = df, aes(x = length, y = count)) + - geom_col() + - theme_bw() + geom_col() + + theme_bw() bequiet <- dev.off() # remove bimera @@ -119,7 +119,7 @@ merged_nondef <- dada2::mergePairs(dada_fwd, filt_fwd, dada_rev, filt_rev, minOverlap = 8, maxMismatch = 1, justConcatenate = TRUE, trimOverhang = TRUE) for (id in sample_names) { - saveRDS(merged_nondef[[id]], file = paste("mergePairs_", id, "_nondefault.Rdata", sep = "")) + saveRDS(merged_nondef[[id]], file = paste("mergePairs_", id, "_nondefault.Rdata", sep = "")) } rb_dada_fwd <- dada2::removeBimeraDenovo(dada_fwd[["F3D0_S188_L001"]]) write.table(rb_dada_fwd, file = "removeBimeraDenovo_F3D0_dada_uniques.tab", quote = FALSE, sep = "\t", row.names = TRUE, col.names = FALSE) @@ -129,7 +129,7 @@ # SeqCounts get_n <- function(x) { - sum(dada2::getUniques(x)) + sum(dada2::getUniques(x)) } print("seqCounts ft")