Upgrade mircounts tools (#666)

* Upgrade conda packages. IUC format * lint R, py and xml codes * update tests in Mississippi * add expect_num_outputs * reduce test sizes
ARTbio · Feb 10, 2024 · 5eb8570 · 5eb8570
1 parent 2661225
commit 5eb8570
Show file tree

Hide file tree

Showing 21 changed files with 6,059 additions and 572,650 deletions.
diff --git a/tools/mircounts/coverage_plotting.R b/tools/mircounts/coverage_plotting.R
@@ -10,9 +10,10 @@ hlp_output <- "--output\tFILE\tFile to output the pdf to\n"
 hlp <- paste(hlp_description, hlp_usage, hlp_dataframe, hlp_type, hlp_output, sep = "\n")
 
 # Setup R error handling to go to stderr
-options(show.error.messages = F,
+options(show.error.messages = FALSE,
     error = function() {
-        cat(geterrmessage(), file = stderr()); q("no", 1, F)
+        cat(geterrmessage(), file = stderr())
+        q("no", 1, FALSE)
     }
 )
 
@@ -26,7 +27,7 @@ option_list <- list(
     make_option(c("-t", "--type"), type = "character", default = "relative",
                 help = "Type of plotting, either relative or absoute coverage values (default = 'relative')"),
     make_option(c("-o", "--output"), type = "character", help = "File to output the pdf to")
-    )
+)
 parser <- OptionParser(usage = "%prog [options] file", option_list = option_list)
 args <- parse_args(parser)
 
@@ -35,22 +36,26 @@ if (!("dataframe" %in% names(args)) || !("output" %in% names(args))) {
 }
 
 # Plot
-coverage <- read.delim(args$dataframe, header = T)
+coverage <- read.delim(args$dataframe, header = TRUE)
 if (args$type == "relative") {
-    graph <- xyplot(Norm_count ~ Norm_offset | Mir_hairpin, data = coverage, col = c("darkblue"), type = "l", lwd = 1.5,
-                   scales = list(x = list(cex = .5), y = list(cex = .5)), par.strip.text = list(cex = .5),
-                   strip = strip.custom(which.given = 1, bg = "lightblue"), layout = c(4, 15),
-                   as.table = T, xlab = "Normalized Counts", ylab = "Normalized coordinates",
-                   main = "miRNA coverage maps")
+    graph <- xyplot(
+        Norm_count ~ Norm_offset | Mir_hairpin, data = coverage, col = c("darkblue"), type = "l", lwd = 1.5,
+        scales = list(x = list(cex = .5), y = list(cex = .5)), par.strip.text = list(cex = .5),
+        strip = strip.custom(which.given = 1, bg = "lightblue"), layout = c(4, 15),
+        as.table = TRUE, xlab = "Normalized Counts", ylab = "Normalized coordinates",
+        main = "miRNA coverage maps"
+    )
 } else {
-    graph <- xyplot(Count ~ Offset | Mir_hairpin, data = coverage, col = c("darkblue"), type = "l", lwd = 1.5,
-                   scales = list(x = list(cex = .5), y = list(cex = .5)), par.strip.text = list(cex = .5),
-                   strip = strip.custom(which.given = 1, bg = "lightblue"), layout = c(4, 15),
-                   as.table = T, xlab = "Counts", ylab = "Coordinates",
-                   main = "miRNA coverage plots")
+    graph <- xyplot(
+        Count ~ Offset | Mir_hairpin, data = coverage, col = c("darkblue"), type = "l", lwd = 1.5,
+        scales = list(x = list(cex = .5), y = list(cex = .5)), par.strip.text = list(cex = .5),
+        strip = strip.custom(which.given = 1, bg = "lightblue"), layout = c(4, 15),
+        as.table = TRUE, xlab = "Counts", ylab = "Coordinates",
+        main = "miRNA coverage plots"
+    )
 }
 
 # PDF output
 pdf(file = args$output, paper = "special", height = 11.69, width = 8.2677)
-plot(graph, newpage = T)
+plot(graph, newpage = TRUE)
 dev.off()
diff --git a/tools/mircounts/mircounts.xml b/tools/mircounts/mircounts.xml
@@ -1,42 +1,47 @@
-<tool id="mircounts" name="miRcounts" version="1.5.1">
+<tool id="mircounts" name="miRcounts" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
     <description> Counts miRNA alignments from small RNA sequence data</description>
+    <macros>
+        <token name="@TOOL_VERSION@">1.6</token>
+        <token name="@VERSION_SUFFIX@">0</token>
+        <token name="@PROFILE@">23.0</token>
+    </macros>
     <requirements>
-        <requirement type="package" version="1.34=ha1f6473_0">tar</requirement>
-        <requirement type="package" version="1.3.0=py39h176da8b_2">bowtie</requirement>
-        <requirement type="package" version="1.12=h9aed4be_1">samtools</requirement>
-        <requirement type="package" version="0.16.0.1=py39h051187c_3">pysam</requirement>
-        <requirement type="package" version="1.6.6=r40h6115d3f_1">r-optparse</requirement>
-        <requirement type="package" version="0.20_44=r40hcfec24a_0">r-lattice</requirement>
+        <requirement type="package" version="1.34">tar</requirement>
+        <requirement type="package" version="1.3.1">bowtie</requirement>
+        <requirement type="package" version="1.19.2">samtools</requirement>
+        <requirement type="package" version="0.22.0">pysam</requirement>
+        <requirement type="package" version="1.7.4">r-optparse</requirement>
+        <requirement type="package" version="0.22_5">r-lattice</requirement>
     </requirements>
     <stdio>
         <exit_code range="1:" level="warning" description="Tool exception" />
     </stdio>
     <command detect_errors="exit_code"><![CDATA[
         tar -xf  '$__tool_directory__'/mirbase.tar.gz &&
         python '$__tool_directory__'/mature_mir_gff_translation.py
-                                                --gff_path mirbase/${mirbase_version}/genomes/${genomeKey}.gff3
-                                                --output $gff3 && ## transcode the mature miR genome coordinates into coordinates relative to the corresponding "miRNA_primary_transcript".
+                                                --gff_path mirbase/'${mirbase_version}'/genomes/'${genomeKey}'.gff3
+                                                --output '$gff3' && ## transcode mature miR genome coordinates relative to "miRNA_primary_transcript"
         python '$__tool_directory__'/format_fasta_hairpins.py
-                                                --hairpins_path mirbase/${mirbase_version}/hairpin.fa.gz
-                                                --basename ${genomeKey}
+                                                --hairpins_path mirbase/'${mirbase_version}'/hairpin.fa.gz
+                                                --basename '${genomeKey}'
                                                 --output hairpin.fa &&
         #if $cutadapt.cutoption == "yes":
-            python '$__tool_directory__'/yac.py --input $cutadapt.input
+            python '$__tool_directory__'/yac.py --input '$cutadapt.input'
                                                 --output clipped_input.fastq
                                                 --output_format fastq
-                                                --adapter_to_clip $cutadapt.clip_source.clip_sequence
-                                                --min $cutadapt.min
-                                                --max $cutadapt.max
-                                                --Nmode $cutadapt.Nmode &&
+                                                --adapter_to_clip '$cutadapt.clip_source.clip_sequence'
+                                                --min '$cutadapt.min'
+                                                --max '$cutadapt.max'
+                                                --Nmode '$cutadapt.Nmode' &&
         #else:
             ln -f -s '$cutadapt.clipped_input' clipped_input.fastq &&
         #end if
         bowtie-build hairpin.fa hairpin &&
-        bowtie -v $v -M 1 --best --strata --norc -p \${GALAXY_SLOTS:-4} --sam hairpin -q clipped_input.fastq | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o '$output' &&
+        bowtie -v '$v' -M 1 --best --strata --norc -p \${GALAXY_SLOTS:-4} --sam hairpin -q clipped_input.fastq | samtools sort -@ \${GALAXY_SLOTS:-4} -O bam -o '$output' &&
         samtools index $output &&
-        python '$__tool_directory__'/mircounts.py --alignment $output --gff $gff3 --quality_threshold 10 --pre_mirs $pre_mir_count_file --mirs $mir_count_file --lattice $coverage_dataframe
+        python '$__tool_directory__'/mircounts.py --alignment '$output' --gff '$gff3' --quality_threshold 10 --pre_mirs '$pre_mir_count_file' --mirs '$mir_count_file' --lattice '$coverage_dataframe'
         #if $plotting.plottingOption == 'yes':
-            && Rscript '$__tool_directory__'/coverage_plotting.R --dataframe $coverage_dataframe --type $plotting.display --output $latticePDF
+            && Rscript '$__tool_directory__'/coverage_plotting.R --dataframe '$coverage_dataframe' --type '$plotting.display' --output '$latticePDF'
         #end if
     ]]></command>
     <inputs>
@@ -135,12 +140,12 @@
         </data>
     </outputs>
     <tests>
-        <test>
-            <param name="cutoption" value="no" />
+        <test expect_num_outputs="6">
+            <param name="cutoption" value="no"/>
             <param name="v" value="1"/>
             <param name="genomeKey" value="aga"/>
             <param name="mirbase_version" value="22"/>
-            <param name="clipped_input" value="aga.fastqsanger" ftype="fastqsanger"/>
+            <param name="clipped_input" value="aga.fastqsanger.gz" ftype="fastqsanger.gz"/>
             <param name="plottingOption" value="yes"/>
             <param name="display" value="relative"/>
             <param name="output_premir_counts" value="True"/>
@@ -152,8 +157,8 @@
             <output name="latticePDF" file="aga_mir_coverage.pdf" ftype="pdf" />
             <output name="coverage_dataframe" file="aga_lattice_dataframe.tab" ftype="tabular" />
         </test>
-        <test>
-            <param name="cutoption" value="yes" />
+        <test expect_num_outputs="6">
+            <param name="cutoption" value="yes"/>
             <param name="min" value="18"/>
             <param name="max" value="32"/>
             <param name="Nmode" value="reject"/>
@@ -173,8 +178,8 @@
             <output name="latticePDF" file="mouse_mir_coverage.pdf" ftype="pdf" />
             <output name="coverage_dataframe" file="mouse_lattice_dataframe.tab" ftype="tabular" />
         </test>
-        <test>
-            <param name="cutoption" value="yes" />
+        <test expect_num_outputs="4">
+            <param name="cutoption" value="yes"/>
             <param name="min" value="15"/>
             <param name="max" value="25"/>
             <param name="Nmode" value="reject"/>
@@ -191,8 +196,8 @@
             <output name="pre_mir_count_file" file="pre_mirs_unclipped_count.22.tab" ftype="tabular" />
             <output name="mir_count_file" file="mirs_unclipped_count.22.tab" ftype="tabular" />
         </test>
-         <test>
-            <param name="cutoption" value="yes" />
+         <test expect_num_outputs="4">
+            <param name="cutoption" value="yes"/>
             <param name="min" value="15"/>
             <param name="max" value="25"/>
             <param name="Nmode" value="reject"/>
@@ -209,8 +214,8 @@
             <output name="pre_mir_count_file" file="pre_mirs_unclipped_count.tab" ftype="tabular" />
             <output name="mir_count_file" file="mirs_unclipped_count.tab" ftype="tabular" />
         </test>
-        <test>
-            <param name="cutoption" value="yes" />
+        <test expect_num_outputs="6">
+            <param name="cutoption" value="yes"/>
             <param name="min" value="15"/>
             <param name="max" value="25"/>
             <param name="Nmode" value="reject"/>
@@ -230,8 +235,8 @@
             <output name="latticePDF" file="mir_unclipped_coverage.pdf" ftype="pdf"/>
             <output name="coverage_dataframe" file="lattice_unclipped_dataframe.tab" ftype="tabular" />
         </test>
-        <test>
-            <param name="cutoption" value="no" />
+        <test expect_num_outputs="6">
+            <param name="cutoption" value="no"/>
             <param name="v" value="1"/>
             <param name="genomeKey" value="dme"/>
             <param name="mirbase_version" value="21"/>
@@ -259,7 +264,7 @@
 
 This tool uses a species-specific GFF3 file generated from mirBase_ to guide the parsing of a bam file of small RNA alignments.
 
-.. _mirBase: ftp://mirbase.org/pub/mirbase/
+.. _mirBase: https://mirbase.org/download/
 
 ------
 

diff --git a/tools/mircounts/test-data/aga.22.gff3 b/tools/mircounts/test-data/aga.22.gff3
@@ -11,7 +11,7 @@
 # rather a predicted stem-loop portion that includes the precursor 
 # miRNA. Mature sequences have type "miRNA".
 #
-# generated by mature_mir_gff_translation.py                             2021-05-09 00:34:02.737449
+# generated by mature_mir_gff_translation.py                             2024-02-10 17:38:20.268084
 #
 aga-bantam	.	miRNA_primary_transcript	1	111	.	+	.	ID=MI0001599;Alias=MI0001599;Name=aga-bantam
 aga-bantam	.	miRNA	70	92	.	+	.	ID=MIMAT0001494;Alias=MIMAT0001494;Name=aga-bantam;Derives_from=MI0001599;Parent_mir_Name=aga-bantam

diff --git a/tools/mircounts/test-data/aga.bam b/tools/mircounts/test-data/aga.bam