Mercurial > repos > iuc > multiqc
changeset 16:bf675f34b056 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/multiqc commit bd94f00ad5d023ae392ca8fc2378fd5a78bed875"
| author | iuc |
|---|---|
| date | Sat, 16 May 2020 09:40:45 -0400 |
| parents | 3d93dd18d9f8 |
| children | 5e33b465d8d5 |
| files | multiqc.xml test-data/genome_results.txt test-data/qualimap_bamqc_genome_results.tabular |
| diffstat | 3 files changed, 179 insertions(+), 3 deletions(-) [+] |
line wrap: on
line diff
--- a/multiqc.xml Sat Jan 18 03:08:54 2020 -0500 +++ b/multiqc.xml Sat May 16 09:40:45 2020 -0400 @@ -1,7 +1,7 @@ -<tool id="multiqc" name="MultiQC" version="@WRAPPER_VERSION@.1"> +<tool id="multiqc" name="MultiQC" version="@WRAPPER_VERSION@+galaxy0"> <description>aggregate results from bioinformatics analyses into a single report</description> <macros> - <token name="@WRAPPER_VERSION@">1.7</token> + <token name="@WRAPPER_VERSION@">1.8</token> <token name="@ESCAPE_IDENTIFIER@"> <![CDATA[ #set identifier = re.sub('[^\s\w\-]', '_', str($file.element_identifier)) @@ -272,6 +272,28 @@ #elif str($repeat.software_cond.software) == "prokka" #set $pattern = "contigs:" @LN_FILES@ + #elif str($repeat.software_cond.software) == "qualimap" + #for $file in $repeat.software_cond.input + #if re.search("genome_results", str($file.element_identifier)) + sample="\$(grep 'bam file = ' $file | sed 's/bam file = //g' | sed 's: ::g')" && + dir_name="$software_dir/\${sample}" && + mkdir -p \${dir_name} && + filepath_1="\${dir_name}/genome_results.txt" && + ln -sf '$file' \${filepath_1} && + #elif re.search("coverage_histogram", str($file.element_identifier)) + nested_dir_name="\${dir_name}/raw_data_qualimapReport/" && + mkdir -p \${nested_dir_name} && + filepath_2="\${nested_dir_name}/coverage_histogram.txt" && + ln -sf '$file' \${filepath_2} && + #elif re.search("gc-content_distribution", str($file.element_identifier)) + nested_dir_name="\${dir_name}/raw_data_qualimapReport/" && + mkdir -p \${nested_dir_name} && + filepath_3="\${nested_dir_name}/mapped_reads_gc-content_distribution.txt" && + ln -sf '$file' \${filepath_3} && + #else + #pass + #end if + #end for #elif str($repeat.software_cond.software) == "quast" #for $k, $file in enumerate($repeat.software_cond.input) #set file_dir = os.path.join($software_dir, 'file_' + str($k)) @@ -499,6 +521,7 @@ <!--<option value="bbmap">BBMap</option>--> <option value="bcftools">Bcftools</option> <!--<option value="bcl2fastq">bcl2fastq</option>--> + <!--<option value="biobambam2">biobambam2</option>--> <!--<option value="biobloomtools">BioBloom Tools</option>--> <option value="bismark">Bismark</option> <!--<option value="bowtie1">Bowtie 1</option>--> @@ -515,6 +538,7 @@ <option value="fastp">fastp</option> <option value="fastqc">FastQC</option> <option value="featureCounts">featureCounts</option> + <!--<option value="fgbio">fgbio</option>--> <option value="flexbar">Flexbar</option> <option value="gatk">GATK</option> <!--<option value="goleft_indexcov">goleft indexcov</option>--> @@ -529,12 +553,14 @@ <!--<option value="leehom">leeHom</option>--> <option value="macs2">MACS2</option> <!--<option value="methylQA">methylQA</option>--> + <!--<option value="mosdepth">mostdepth</option>--> + <!--<option value="mtnucratio">mtnucratio</option>--> <!--<option value="peddy">Peddy</option>--> <option value="picard">Picard</option> <!--<option value="preseq">Preseq</option>--> <option value="prokka">Prokka</option> <!--<option value="qorts">QoRTs</option>--> - <!--<option value="qualimap">Qualimap (BamQC or RNASeq output)</option>--> + <option value="qualimap">Qualimap (BamQC or RNASeq output)</option> <option value="quast">QUAST</option> <!--<option value="rna_seqc">RNA-SeQC</option>--> <!--<option value="rsem">RSEM (rsem-calculate-regex output)</option>--> @@ -543,6 +569,8 @@ <option value="samblaster">Samblaster</option> <option value="samtools">Samtools</option> <!--<option value="sargasso">Sargasso</option>--> + <!--<option value="seqyclean">SeqyClean</option>--> + <!--<option value="sexdeterrmine">SexDetErrmine</option>--> <!--<option value="skewer">Skewer</option>--> <option value="slamdunk">Slamdunk</option> <option value="snpeff">SnpEff</option> @@ -663,6 +691,9 @@ <when value="prokka"> <param name="input" type="data" format="txt" multiple="true" label="Output of Prokka" help="It should contain 'contigs:'"/> </when> + <when value="qualimap"> + <param name="input" type="data" format="txt,tabular,tsv" multiple="true" label="Output of Qualimap BamQC" help="First result input should be genome_coverage (default from tool output). Run the Flatten Collection tool to keep all output in one report" /> + </when> <when value="quast"> <param name="input" type="data" format="tabular,tsv" multiple="true" label="Output of Quast"/> </when> @@ -1100,6 +1131,12 @@ </repeat> <repeat name="results"> <conditional name="software_cond"> + <param name="software" value="qualimap" /> + <param name="input" value="genome_results.txt" /> + </conditional> + </repeat> + <repeat name="results"> + <conditional name="software_cond"> <param name="software" value="quast" /> <param name="input" value="quast.tsv" /> </conditional> @@ -1177,6 +1214,7 @@ <has_text text="picard-insertsize" /> <has_text text="picard-gcbias" /> <has_text text="prokka_plot" /> + <has_text text="qualimap" /> <has_text text="samblaster_duplicates" /> <has_text text="quast-stats" /> <has_text text="samtools-flagstat-dp" /> @@ -1197,6 +1235,7 @@ <element name="picard_dups" file="picard_dups_stats.tabular" compare="sim_size" delta="0"/> <element name="picard_insertSize" file="picard_insertSize_stats.tabular" compare="sim_size" delta="0"/> <element name="prokka" file="prokka_stats.tabular" compare="sim_size" delta="0"/> + <element name="qualimap_bamqc_genome_results" file="qualimap_bamqc_genome_results.tabular" compare="sim_size" delta="0"/> <element name="quast" file="quast_stats.tabular" compare="sim_size" delta="0"/> <element name="samblaster" file="samblaster_stats.tabular" compare="sim_size" delta="0"/> <element name="samtools_flagstat">
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/genome_results.txt Sat May 16 09:40:45 2020 -0400 @@ -0,0 +1,135 @@ +BamQC report +----------------------------------- + +>>>>>>> Input + + bam file = x_bam + outfile = results/genome_results.txt + + +>>>>>>> Reference + + number of bases = 1,817,261 bp + number of contigs = 1 + + +>>>>>>> Globals + + number of windows = 400 + + number of reads = 1,248,774 + number of mapped reads = 1,242,183 (99.47%) + number of supplementary alignments = 3,386 (0.27%) + number of secondary alignments = 0 + + number of mapped paired reads (first in pair) = 623,192 + number of mapped paired reads (second in pair) = 618,991 + number of mapped paired reads (both in pair) = 1,237,764 + number of mapped paired reads (singletons) = 4,419 + number of overlapping read pairs = 463,596 + + number of mapped bases = 366,875,582 bp + number of sequenced bases = 366,823,893 bp + number of aligned bases = 0 bp + number of duplicated reads (estimated) = 673,527 + duplication rate = 47.01% + + +>>>>>>> Insert size + + mean insert size = 1,097.678 + std insert size = 27,365.2401 + median insert size = 524 + + +>>>>>>> Mapping quality + + mean mapping quality = 58.4552 + + +>>>>>>> ACTG content + + number of A's = 109,576,306 bp (29.87%) + number of C's = 73,524,910 bp (20.04%) + number of T's = 111,308,231 bp (30.34%) + number of G's = 72,414,446 bp (19.74%) + number of N's = 0 bp (0%) + + GC percentage = 39.78% + + +>>>>>>> Mismatches and indels + + general error rate = 0.0098 + number of mismatches = 3,560,959 + number of insertions = 7,229 + mapped reads with insertion percentage = 0.56% + number of deletions = 14,669 + mapped reads with deletion percentage = 1.15% + homopolymer indels = 46.92% + + +>>>>>>> Coverage + + mean coverageData = 201.8838X + std coverageData = 112.2733X + paired-end adapted mean coverage = 177.4988X + + There is a 99.81% of reference with a coverageData >= 1X + There is a 99.77% of reference with a coverageData >= 2X + There is a 99.74% of reference with a coverageData >= 3X + There is a 99.7% of reference with a coverageData >= 4X + There is a 99.66% of reference with a coverageData >= 5X + There is a 99.6% of reference with a coverageData >= 6X + There is a 99.53% of reference with a coverageData >= 7X + There is a 99.41% of reference with a coverageData >= 8X + There is a 99.3% of reference with a coverageData >= 9X + There is a 99.21% of reference with a coverageData >= 10X + There is a 99.11% of reference with a coverageData >= 11X + There is a 98.99% of reference with a coverageData >= 12X + There is a 98.87% of reference with a coverageData >= 13X + There is a 98.76% of reference with a coverageData >= 14X + There is a 98.63% of reference with a coverageData >= 15X + There is a 98.5% of reference with a coverageData >= 16X + There is a 98.35% of reference with a coverageData >= 17X + There is a 98.16% of reference with a coverageData >= 18X + There is a 97.97% of reference with a coverageData >= 19X + There is a 97.79% of reference with a coverageData >= 20X + There is a 97.59% of reference with a coverageData >= 21X + There is a 97.37% of reference with a coverageData >= 22X + There is a 97.16% of reference with a coverageData >= 23X + There is a 96.95% of reference with a coverageData >= 24X + There is a 96.71% of reference with a coverageData >= 25X + There is a 96.48% of reference with a coverageData >= 26X + There is a 96.24% of reference with a coverageData >= 27X + There is a 95.99% of reference with a coverageData >= 28X + There is a 95.73% of reference with a coverageData >= 29X + There is a 95.49% of reference with a coverageData >= 30X + There is a 95.23% of reference with a coverageData >= 31X + There is a 94.99% of reference with a coverageData >= 32X + There is a 94.75% of reference with a coverageData >= 33X + There is a 94.51% of reference with a coverageData >= 34X + There is a 94.27% of reference with a coverageData >= 35X + There is a 94.01% of reference with a coverageData >= 36X + There is a 93.8% of reference with a coverageData >= 37X + There is a 93.55% of reference with a coverageData >= 38X + There is a 93.31% of reference with a coverageData >= 39X + There is a 93.04% of reference with a coverageData >= 40X + There is a 92.77% of reference with a coverageData >= 41X + There is a 92.52% of reference with a coverageData >= 42X + There is a 92.27% of reference with a coverageData >= 43X + There is a 91.99% of reference with a coverageData >= 44X + There is a 91.72% of reference with a coverageData >= 45X + There is a 91.44% of reference with a coverageData >= 46X + There is a 91.17% of reference with a coverageData >= 47X + There is a 90.9% of reference with a coverageData >= 48X + There is a 90.64% of reference with a coverageData >= 49X + There is a 90.4% of reference with a coverageData >= 50X + There is a 90.15% of reference with a coverageData >= 51X + + +>>>>>>> Coverage per contig + + NZ_CP031250.1 1817261 366875582 201.88381415768015 112.27329056357358 + +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/qualimap_bamqc_genome_results.tabular Sat May 16 09:40:45 2020 -0400 @@ -0,0 +1,2 @@ +Sample bam_file total_reads mapped_reads mapped_bases sequenced_bases mean_insert_size median_insert_size mean_mapping_quality general_error_rate percentage_aligned +x_bam x_bam 1248774.0 1242183.0 366875582.0 366823893.0 1097.678 524.0 58.4552 0.0098 99.4722023360512