Mercurial > repos > iuc > rna_starsolo
diff rg_rnaStarSolo.xml @ 13:9ee34ba73ebf draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rgrnastar commit ae6b59a8e52fd34e2347d1fd8d34129c36779266
| author | iuc |
|---|---|
| date | Fri, 17 Feb 2023 20:04:43 +0000 |
| parents | 79b885ce78d7 |
| children | 1cd2511a396e |
line wrap: on
line diff
--- a/rg_rnaStarSolo.xml Tue Nov 01 16:57:42 2022 +0000 +++ b/rg_rnaStarSolo.xml Fri Feb 17 20:04:43 2023 +0000 @@ -1,4 +1,4 @@ -<tool id="rna_starsolo" name="RNA STARSolo" version="@VERSION@" profile="20.01" license="MIT"> +<tool id="rna_starsolo" name="RNA STARSolo" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@" license="MIT"> <description>mapping, demultiplexing and gene quantification for single cell RNA-seq</description> <macros> <import>macros.xml</import> @@ -22,16 +22,20 @@ #if str($sc.solo_type) == "CB_UMI_Simple": @READSHANDLING@ - --soloCBwhitelist '$sc.soloCBwhitelist' + #if $sc.soloCBwhitelist: + --soloCBwhitelist '$sc.soloCBwhitelist' + #else + --soloCBwhitelist None + #end if ## 1 - check length of barcode, 0 - do not check ## Good for checking custom chemistries --soloBarcodeReadLength $sc.soloBarcodeReadLength - #if str($sc.params.chemistry) == "CR2": + #if str($sc.params.chemistry) == "Cv2": --soloCBstart 1 --soloCBlen 16 --soloUMIstart 17 --soloUMIlen 10 - #else if str($sc.params.chemistry) == "CR3": + #else if str($sc.params.chemistry) == "Cv3": --soloCBstart 1 --soloCBlen 16 --soloUMIstart 17 @@ -90,12 +94,20 @@ --soloCBwhitelist None #end if - --soloUMIfiltering $solo.soloUMIfiltering --soloStrand $solo.soloStrand --soloFeatures $solo.soloFeatures - --soloUMIdedup $sc.soloUMIdedup - --quantMode TranscriptomeSAM - --outSAMtype BAM Unsorted + --soloUMIdedup $sc.umidedup.soloUMIdedup + #if str($sc.umidedup.soloUMIdedup) == "1MM_CR": + --soloUMIfiltering $sc.umidedup.soloUMIfiltering + #end if + --quantMode TranscriptomeSAM $solo.quantModeGene + #set $tag_names = str($solo.outSAMattributes).replace(',', ' ') + --outSAMattributes $tag_names + #if "CB" in $tag_names or "UB" in $tag_names or str($outWig.outWigType) != 'None': + --outSAMtype BAM SortedByCoordinate + #else: + --outSAMtype BAM Unsorted + #end if #if str($solo.filter.filter_type) == "cellranger2": --soloCellFilter CellRanger2.2 $solo.filter.n_expected $solo.filter.max_perc $solo.filter.max_min_ratio @@ -109,24 +121,39 @@ ## Splice junctions are always under "raw" directory --soloOutFormatFeaturesGeneField3 '${solo.soloOutFormatFeaturesGeneField3}' + + ## Limits + @LIMITS@ + + ##outWig: + @OUTWIG@ ## Rename the the selected features directory && mv Solo.out/${solo.soloFeatures} Solo.out/soloFeatures ## put the barcodes and features stats into a single file && cat <(echo "Barcodes:") Solo.out/Barcodes.stats <(echo "Genes:") Solo.out/soloFeatures/Features.stats > '${output_stats}' - ## BAM sorting (logic copied from samtools_sort wrapper) - ## choosing BAM SortedByCoord appeared once to give fewer reads - ## than BAM Unsorted followed by a samtools sort - ## so better go with the latter? + + #if "CB" in $tag_names or "UB" in $tag_names or str($outWig.outWigType) != 'None': + ## recompress BAM output for smaller file size + && samtools view -b -o '$output_BAM' Aligned.sortedByCoord.out.bam + #else: + ## BAM sorting (logic copied from samtools_sort wrapper) + ## choosing BAM SortedByCoord appeared once to give fewer reads + ## than BAM Unsorted followed by a samtools sort + ## so better go with the latter? - && - ##compute the number of ADDITIONAL threads to be used by samtools (-@) - addthreads=\${GALAXY_SLOTS:-2} && (( addthreads-- )) && - ##compute the number of memory available to samtools sort (-m) - ##use only 75% of available: https://github.com/samtools/samtools/issues/831 - addmemory=\${GALAXY_MEMORY_MB_PER_SLOT:-768} && - ((addmemory=addmemory*75/100)) && - samtools sort -@ \$addthreads -m \$addmemory"M" -T "\${TMPDIR:-.}" -O bam -o '$output_BAM' Aligned.out.bam + && + ##compute the number of ADDITIONAL threads to be used by samtools (-@) + addthreads=\${GALAXY_SLOTS:-2} && (( addthreads-- )) && + ##compute the number of memory available to samtools sort (-m) + ##use only 75% of available: https://github.com/samtools/samtools/issues/831 + addmemory=\${GALAXY_MEMORY_MB_PER_SLOT:-768} && + ((addmemory=addmemory*75/100)) && + samtools sort -@ \$addthreads -m \$addmemory"M" -T "\${TMPDIR:-.}" -O bam -o '$output_BAM' Aligned.out.bam + #end if + ##outWig: + @OUTWIGOUTPUTS@ + ]]></command> <configfiles> <configfile name="manifest_file" > @@ -170,13 +197,13 @@ </when> <when value="without-gtf"> <expand macro="index_selection" with_gene_model="0" /> - <expand macro="@SJDBOPTIONS@" optional="false" /> + <expand macro="SJDBOPTIONS"/> </when> </conditional> </when> <when value="history"> <expand macro="ref_selection" /> - <expand macro="@SJDBOPTIONS@" optional="false"/> + <expand macro="SJDBOPTIONS"/> </when> </conditional> <conditional name="sc" > @@ -187,15 +214,15 @@ </param> <when value="CB_UMI_Simple"> <expand macro="input_selection" /> - <param format="txt,tsv" argument="--soloCBwhitelist" type="data" label="RNA-Seq Cell Barcode Whitelist"/> + <param format="txt,tsv" argument="--soloCBwhitelist" optional="True" type="data" label="RNA-Seq Cell Barcode Whitelist"/> <conditional name="params" > <param name="chemistry" type="select" label="Configure Chemistry Options"> - <option value="CR2" selected="true">Cell Ranger v2</option> - <option value="CR3">Cell Ranger v3</option> + <option value="Cv2" selected="true">Chromium chemistry v2</option> + <option value="Cv3">Chromium chemistry v3</option> <option value="custom">Custom</option> </param> - <when value="CR2" /> - <when value="CR3" /> + <when value="Cv2" /> + <when value="Cv3" /> <when value="custom" > <param argument="--soloCBstart" type="integer" min="1" value="1" label="Cell Barcode Start Base" /> <param argument="--soloCBlen" type="integer" min="1" value="16" label="Cell Barcode Length" /> @@ -219,11 +246,25 @@ </when> </conditional> <param argument="--soloBarcodeReadLength" type="boolean" truevalue="1" falsevalue="0" checked="true" label="Barcode Size is same size of the Read" help="Disable this if your R1 barcodes contain poly-T bases after the barcode sequence." /> - <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs."> - <expand macro="umidedup_options" /> - <option value="Exact" >Exact</option> - <option value="1MM_CR" >CellRanger2-4 algorithm</option> - </param> + <conditional name="umidedup"> + <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs."> + <expand macro="umidedup_options" /> + <option value="Exact" >Exact</option> + <option value="1MM_CR" >CellRanger2-4 algorithm</option> + </param> + <when value="1MM_All"/> + <when value="1MM_Directional_UMItools"/> + <when value="1MM_Directional"/> + <when value="Exact"/> + <when value="1MM_CR"> + <param argument="--soloUMIfiltering" type="select" label="Type of UMI filtering" > + <option value="-" selected="true">Remove UMIs with N and homopolymers (similar to CellRanger 2.2.0)</option> + <option value="MultiGeneUMI" >Remove lower-count UMIs that map to more than one gene</option> + <option value="MultiGeneUMI_All" >Remove all UMIs that map to more than one gene</option> + <option value="MultiGeneUMI_CR" >Remove lower-count UMIs that map to more than one gene, matching CellRanger > 3.0.0</option> + </param> + </when> + </conditional> <param argument="--soloCBmatchWLtype" type="select" label="Matching the Cell Barcodes to the WhiteList" help="Exact: only exact matches allowed; 1MM: only one match in whitelist with 1 mismatched base allowed. Allowed CBs have to have at least one read with exact match; 1MM_multi: multiple matches in whitelist with 1 mismatched base allowed, posterior probability calculation is used choose one of the matches; 1MM_multi_pseudocounts: same as 1MM_Multi, but pseudocounts of 1 are added to all whitelist barcodes."> <expand macro="cb_match_wl_common" /> @@ -252,23 +293,46 @@ </param> <param name="umi_end_anchor_pos" type="integer" value="0" label="0-based position of the UMI end with respect to the anchor base" /> <expand macro="solo_adapter_params" /> - <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs."> - <expand macro="umidedup_options" /> - <option value="Exact" >Exact</option> - <option value="1MM_CR" >CellRanger2-4 algorithm</option> - </param> + <conditional name="umidedup"> + <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs."> + <expand macro="umidedup_options" /> + <option value="Exact" >Exact</option> + <option value="1MM_CR" >CellRanger2-4 algorithm</option> + </param> + <when value="1MM_All"/> + <when value="1MM_Directional_UMItools"/> + <when value="1MM_Directional"/> + <when value="Exact"/> + <when value="1MM_CR"> + <param argument="--soloUMIfiltering" type="select" label="Type of UMI filtering" > + <option value="-" selected="true">Remove UMIs with N and homopolymers (similar to CellRanger 2.2.0)</option> + <option value="MultiGeneUMI" >Remove lower-count UMIs that map to more than one gene</option> + <option value="MultiGeneUMI_All" >Remove all UMIs that map to more than one gene</option> + <option value="MultiGeneUMI_CR" >Remove lower-count UMIs that map to more than one gene, matching CellRanger > 3.0.0</option> + </param> + </when> + </conditional> <param argument="--soloCBmatchWLtype" type="select" label="Matching the Cell Barcodes to the WhiteList" help="Exact: only exact matches allowed; 1MM: only one match in whitelist with 1 mismatched base allowed. Allowed CBs have to have at least one read with exact match; 1MM_multi: multiple matches in whitelist with 1 mismatched base allowed, posterior probability calculation is used choose one of the matches; 1MM_multi_pseudocounts: same as 1MM_Multi, but pseudocounts of 1 are added to all whitelist barcodes."> <expand macro="cb_match_wl_common" /> + <!-- should we add EditDist_2? --> </param> </when> <when value="SmartSeq"> <expand macro="input_selection_smart_seq" /> <param name="cell_ids" format="txt,tsv" type="data" label="File containing cell IDs of the samples. One ID per line in order of samples in the above collection."/> - <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs."> - <option value="Exact" >Exact</option> - <option value="NoDedup">Do not deduplicate UMIs</option> - </param> + <conditional name="umidedup"> + <param argument="--soloUMIdedup" type="select" label="UMI deduplication (collapsing) algorithm" help="All has all UMIs with 1 mismatch distance to each other collapsed, Directional follows the 'directional' method given in UMI-tools, Exact collapses only exactly matching UMIs."> + <expand macro="umidedup_options" /> + <option value="Exact" >Exact</option> + <option value="NoDedup" >CellRanger2-4 algorithm</option> + </param> + <when value="1MM_All"/> + <when value="1MM_Directional_UMItools"/> + <when value="1MM_Directional"/> + <when value="Exact"/> + <when value="NoDedup"/> + </conditional> </when> </conditional> <section name="solo" title="Advanced Settings" expanded="true"> @@ -281,11 +345,8 @@ <option value="Gene" selected="true">Gene: Count reads matching the Gene Transcript</option> <option value="SJ" >Splice Junctions: Count reads at exon-intron junctions</option> <option value="GeneFull" >Full: Count all reads overlapping genes' exons and introns</option> - </param> - <param argument="--soloUMIfiltering" type="select" label="Type of UMI filtering" > - <option value="-" selected="true">Remove UMIs with N and homopolymers (similar to CellRanger 2.2.0)</option> - <option value="MultiGeneUMI" >Remove lower-count UMIs that map to more than one gene</option> - <option value="MultiGeneUMI_CR" >Remove lower-count UMIs that map to more than one gene, matching CellRanger > 3.0.0</option> + <option value="GeneFull_ExonOverIntron" >Full: Count all reads overlapping genes' exons and introns: prioritize 100% overlap with exons</option> + <option value="GeneFull_Ex50pAS" >Full: Count all reads overlapping genes' exons and introns: prioritize 50% overlap with exons. Do not count reads with 100% exonic overlap in the antisense direction.</option> </param> <conditional name="filter" > <param name="filter_type" type="select" label="Cell filtering type and parameters" > @@ -298,6 +359,7 @@ <param name="n_expected" type="integer" min="1" value="3000" label="Number of expected cells" /> <param name="max_perc" type="float" min="0" max="1" value="0.99" label="Robust maximum percentile for UMI count" /> <param name="max_min_ratio" type="float" min="1" value="10" label="Maximum to minimum ratio for UMI count" /> + <param name="output_raw" type="boolean" checked="false" label="Output raw matrix in addition to filtered one" /> </when> <when value="emptydrops" > <param name="nExpectedCells" type="integer" min="1" value="3000" label="Number of expected cells" /> @@ -310,14 +372,31 @@ <param name="candMaxN" type="integer" value="20000" label="Number of extra barcodes after initial cell calling" /> <param name="FDR" type="float" value="0.01" label="Maximum adjusted p-value for determining a barcode as non-ambient" /> <param name="simN" type="integer" value="10000" label="Number of log likelihood simulations" /> + <param name="output_raw" type="boolean" checked="false" label="Output raw matrix in addition to filtered one" /> </when> <when value="topcells" > <param name="n_cells" type="integer" min="1" value="3000" label="Number of top cells to report sorted by UMI count" /> + <param name="output_raw" type="boolean" checked="false" label="Output raw matrix in addition to filtered one" /> </when> - <when value="no_filter" /> + <when value="no_filter"> + <param name="output_raw" type="hidden" value="true" /> + </when> </conditional> <param argument="--soloOutFormatFeaturesGeneField3" type="text" value="Gene Expression" label="Field 3 in the Genes output." help="Input '-' to remove the 3rd column from the output." /> + <param argument="--outSAMattributes" type="select" display="checkboxes" multiple="true" optional="true" + label="Read alignment tags to include in the BAM output"> + <expand macro="common_SAM_attributes"/> + <option value="CR">CR Cellular barcode sequence bases (uncorrected)</option> + <option value="CY">CY Phred quality of the cellular barcode sequence in the CR tag</option> + <option value="GX">GX Gene ID</option> + <option value="GN">GN Gene name</option> + <option value="CB">CB Cell identifier (corrected)</option> + <option value="UB">UB UMI (corrected)</option> + </param> + <param name="quantModeGene" type="boolean" truevalue="GeneCounts" falsevalue="" checked="false" label="Output global gene count" help="Can be used by MultiQC" /> + <expand macro="limits" /> </section> + <expand macro="outWig"/> </inputs> <outputs> <data format="txt" name="output_log" label="${tool.name} on ${on_string}: log" from_work_dir="Log.final.out"> @@ -333,7 +412,7 @@ <!-- soloCellFilter set to None, if SJ is selected for soloFeatures --> <data format="tsv" name="output_genes" label="${tool.name} on ${on_string}: Genes raw" from_work_dir="Solo.out/soloFeatures/raw/features.tsv" > - <filter>solo['filter']['filter_type'] == "no_filter" or solo['soloFeatures'] == "SJ" </filter> + <filter>solo['filter']['output_raw'] or solo['soloFeatures'] == "SJ" </filter> </data> <data format="tsv" name="output_genes_filtered" label="${tool.name} on ${on_string}: Genes filtered" from_work_dir="Solo.out/soloFeatures/filtered/features.tsv" > @@ -341,7 +420,7 @@ </data> <data format="tsv" name="output_barcodes" label="${tool.name} on ${on_string}: Barcodes raw" from_work_dir="Solo.out/soloFeatures/raw/barcodes.tsv" > - <filter>solo['filter']['filter_type'] == "no_filter" or solo['soloFeatures'] == "SJ" </filter> + <filter>solo['filter']['output_raw'] or solo['soloFeatures'] == "SJ" </filter> </data> <data format="tsv" name="output_barcodes_filtered" label="${tool.name} on ${on_string}: Barcodes filtered" from_work_dir="Solo.out/soloFeatures/filtered/barcodes.tsv" > @@ -349,7 +428,7 @@ </data> <data format="mtx" name="output_matrix" label="${tool.name} on ${on_string}: Matrix Gene Counts raw" from_work_dir="Solo.out/soloFeatures/raw/matrix.mtx" > - <filter>solo['soloFeatures'] == "Gene" and solo['filter']['filter_type'] == "no_filter" </filter> + <filter>solo['soloFeatures'] == "Gene" and solo['filter']['output_raw'] </filter> <expand macro="dbKeyActions" /> </data> <data format="mtx" name="output_matrix_filtered" label="${tool.name} on ${on_string}: Matrix Gene Counts filtered" @@ -364,18 +443,24 @@ </data> <data format="mtx" name="output_matrixGeneFull" label="${tool.name} on ${on_string}: Matrix Full Gene Counts raw" from_work_dir="Solo.out/soloFeatures/raw/matrix.mtx" > - <filter>solo['soloFeatures'] == "GeneFull" and solo['filter']['filter_type'] == "no_filter" </filter> + <filter>"GeneFull" in solo['soloFeatures'] and solo['filter']['output_raw'] </filter> <expand macro="dbKeyActions" /> </data> <data format="mtx" name="output_matrixGeneFull_filtered" label="${tool.name} on ${on_string}: Matrix Full Gene Counts filtered" from_work_dir="Solo.out/soloFeatures/filtered/matrix.mtx" > - <filter>solo['soloFeatures'] == "GeneFull" and solo['filter']['filter_type'] != "no_filter" </filter> + <filter>"GeneFull" in solo['soloFeatures'] and solo['filter']['filter_type'] != "no_filter" </filter> <expand macro="dbKeyActions" /> </data> <data format="bam" name="output_BAM" label="${tool.name} on ${on_string}: Alignments" > <expand macro="dbKeyActions" /> </data> <data format="txt" name="output_stats" label="${tool.name} on ${on_string}: Barcode/Feature Statistic Summaries"/> + <data name="reads_per_gene" format="tabular" label="${tool.name} on ${on_string}: combined reads per gene" from_work_dir="ReadsPerGene.out.tab"> + <filter>solo['quantModeGene']</filter> + <expand macro="dbKeyActions" /> + <expand macro="outCountActions" /> + </data> + <expand macro="outWigOutputs"/> </outputs> <!-- Generating test data that is big enough for STARsolo to detect and small enough for Galaxy to test requires careful modification of input FASTA and GTF data, @@ -386,7 +471,8 @@ here: https://gist.github.com/mtekman/149a7c52fd73e5d8ebe49f5a27b0743d --> <tests> - <test expect_num_outputs="6"> + <test expect_num_outputs="7"> + <!-- test 1 --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" /> @@ -403,9 +489,11 @@ </conditional> <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> <conditional name="params"> - <param name="chemistry" value="CR3" /> + <param name="chemistry" value="Cv3" /> </conditional> - <param name="soloUMIdedup" value="1MM_All" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> </conditional> <section name="solo" > <conditional name="filter"> @@ -413,35 +501,47 @@ </conditional> <param name="soloStrand" value="Forward" /> <param name="soloFeatures" value="Gene" /> + <param name="quantModeGene" value="true" /> </section> <output name="output_barcodes" > <assert_contents> <!-- first and last line --> <has_line line="AAACCTGAGCGCTCCA" /> <has_line line="TTTGGTTAGTGGGCTA" /> + <has_n_lines n="394" /> </assert_contents> </output> <output name="output_genes"> <assert_contents> <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" /> <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" /> + <has_n_lines n="14" /> </assert_contents> </output> <output name="output_matrix" > <assert_contents> <has_line_matching expression="14\s+394\s+7" /> <has_line_matching expression="4\s+381\s+1" /> + <has_n_lines n="10" /> </assert_contents> </output> <output name="output_stats" > <assert_contents> - <has_line_matching expression="\s+nUnmapped\s+5823" /> - <has_line_matching expression="\s+nUMIs\s+8" /> + <has_line_matching expression="\s+noUnmapped\s+5823" /> + <has_line_matching expression="\s+yesUMIs\s+8" /> </assert_contents> </output> <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" /> + <output name="reads_per_gene" > + <assert_contents> + <has_line_matching expression="ENSG00000279493\s+0\s+0\s+0" /> + <has_line_matching expression="ENSG00000275464\s+38\s+1\s+40" /> + </assert_contents> + </output> </test> - <test expect_num_outputs="6"><!-- same as above, but using custom --> + <test expect_num_outputs="6"> + <!-- test 2 --> + <!-- same as above, but using custom and no reads_per_gene--> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" /> @@ -471,31 +571,37 @@ </section> <output name="output_barcodes_filtered" > <assert_contents> + <!-- first and last line --> <has_line line="ACACCGGTCTAACGGT" /> <has_line line="TTCTCAATCCACGTTC" /> + <has_n_lines n="7" /> </assert_contents> </output> <output name="output_genes_filtered"> <assert_contents> <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" /> <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" /> + <has_n_lines n="14" /> </assert_contents> </output> <output name="output_matrix_filtered" > <assert_contents> <has_line_matching expression="14\s+7\s+7" /> <has_line_matching expression="4\s+7\s+1" /> + <has_n_lines n="10" /> </assert_contents> </output> <output name="output_stats" > <assert_contents> - <has_line_matching expression="\s+nUnmapped\s+5823" /> - <has_line_matching expression="\s+nUMIs\s+8" /> + <has_line_matching expression="\s+noUnmapped\s+5823" /> + <has_line_matching expression="\s+yesUMIs\s+8" /> </assert_contents> </output> <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" /> </test> - <test expect_num_outputs="6"><!-- Multiple repeats test --> + <test expect_num_outputs="6"> + <!-- test 3 --> + <!-- Multiple repeats test --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" /> @@ -512,9 +618,11 @@ </conditional> <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> <conditional name="params"> - <param name="chemistry" value="CR3" /> + <param name="chemistry" value="Cv3" /> </conditional> - <param name="soloUMIdedup" value="1MM_All" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> </conditional> <section name="solo" > <param name="soloStrand" value="Forward" /> @@ -524,11 +632,17 @@ <assert_contents> <has_line line="ACACCGGTCTAACGGT" /> <has_line line="TTCTCAATCCACGTTC" /> + <has_n_lines n="7" /> </assert_contents> </output> - <!-- BAM output is huge, we don't need to test here --> + <output name="output_BAM" > + <assert_contents> + <has_size value="166147" delta="600" /> + </assert_contents> + </output> </test> - <test expect_num_outputs="6"> + <test expect_num_outputs="10"> + <!-- test 4 --> <!-- Test with paired collection --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> @@ -550,24 +664,35 @@ </conditional> <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> <conditional name="params"> - <param name="chemistry" value="CR3" /> + <param name="chemistry" value="Cv3" /> </conditional> - <param name="soloUMIdedup" value="1MM_All" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> </conditional> <section name="solo" > <param name="soloStrand" value="Forward" /> <param name="soloFeatures" value="Gene" /> </section> + <conditional name="outWig"> + <param name="outWigType" value="bedGraph" /> + </conditional> <output name="output_barcodes_filtered" > <assert_contents> <has_line line="ACACCGGTCTAACGGT" /> <has_line line="TTCTCAATCCACGTTC" /> + <has_n_lines n="7" /> </assert_contents> </output> <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" /> + <output name="signal_unique_str1" file="Signal.Unique.str1.out.bg" /> + <output name="signal_uniquemultiple_str1" file="Signal.UniqueMultiple.str1.out.bg" /> + <output name="signal_unique_str2" file="Signal.Unique.str2.out.bg" /> + <output name="signal_uniquemultiple_str2" file="Signal.UniqueMultiple.str2.out.bg" /> </test> - <test expect_num_outputs="6"> - <!-- Test soloFeatures, soloCBmatchWLtype, soloCellFilter, soloOutFormatFeaturesGeneField3, soloUMIfiltering --> + <test expect_num_outputs="9"> + <!-- test 5 --> + <!-- Test soloFeatures, soloCBmatchWLtype, soloCellFilter, soloOutFormatFeaturesGeneField3 --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" /> @@ -585,17 +710,19 @@ <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> <param name="soloCBmatchWLtype" value="1MM_multi_pseudocounts" /> <conditional name="params"> - <param name="chemistry" value="CR3" /> + <param name="chemistry" value="Cv3" /> </conditional> - <param name="soloUMIdedup" value="1MM_All" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> </conditional> <section name="solo" > - <param name="soloUMIfiltering" value="MultiGeneUMI" /> <param name="soloStrand" value="Forward" /> <param name="soloFeatures" value="GeneFull" /> <conditional name="filter"> <param name="filter_type" value="topcells" /> <param name="n_cells" value="5" /> + <param name="output_raw" value="true" /> </conditional> <param name="soloOutFormatFeaturesGeneField3" value="Dummy Text" /> </section> @@ -604,22 +731,48 @@ <!-- first and last line --> <has_line line="AGACGTTCAAGGCTCC" /> <has_line line="TCAACGAAGCTAGTGG" /> + <has_n_lines n="6" /> </assert_contents> </output> <output name="output_genes_filtered" > <assert_contents> <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Dummy\s+Text" /> <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Dummy\s+Text" /> + <has_n_lines n="14" /> </assert_contents> </output> <output name="output_matrixGeneFull_filtered" > <assert_contents> <has_line_matching expression="14\s+6\s+14" /> <has_line_matching expression="10\s+6\s+1" /> + <has_n_lines n="17" /> + </assert_contents> + </output> + <output name="output_barcodes" > + <assert_contents> + <!-- first and last line --> + <has_line line="AAACCTGAGCGCTCCA" /> + <has_line line="TTTGGTTAGTGGGCTA" /> + <has_n_lines n="394" /> + </assert_contents> + </output> + <output name="output_genes"> + <assert_contents> + <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Dummy\s+Text" /> + <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Dummy\s+Text" /> + <has_n_lines n="14" /> + </assert_contents> + </output> + <output name="output_matrix" > + <assert_contents> + <has_line_matching expression="14\s+394\s+195" /> + <has_line_matching expression="3\s+1\s+1" /> + <has_n_lines n="198" /> </assert_contents> </output> </test> <test expect_num_outputs="6"> + <!-- test 6 --> <!-- Emptydrops filtering --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> @@ -637,9 +790,11 @@ </conditional> <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> <conditional name="params"> - <param name="chemistry" value="CR3" /> + <param name="chemistry" value="Cv3" /> </conditional> - <param name="soloUMIdedup" value="1MM_All" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> </conditional> <section name="solo" > <conditional name="filter"> @@ -663,29 +818,33 @@ <!-- first and last line --> <has_line line="ACACCGGTCTAACGGT" /> <has_line line="TTCTCAATCCACGTTC" /> + <has_n_lines n="7" /> </assert_contents> </output> <output name="output_genes_filtered"> <assert_contents> <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" /> <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" /> + <has_n_lines n="14" /> </assert_contents> </output> <output name="output_matrix_filtered" > <assert_contents> <has_line_matching expression="14\s+7\s+7" /> <has_line_matching expression="4\s+7\s+1" /> + <has_n_lines n="10" /> </assert_contents> </output> <output name="output_stats" > <assert_contents> - <has_line_matching expression="\s+nUnmapped\s+5823" /> - <has_line_matching expression="\s+nUMIs\s+8" /> + <has_line_matching expression="\s+noUnmapped\s+5823" /> + <has_line_matching expression="\s+yesUMIs\s+8" /> </assert_contents> </output> <output name="output_BAM" value="filtered3.bam" compare="sim_size" delta="600" /> </test> <test expect_num_outputs="6"> + <!-- test 7 --> <!-- Test soloType CB_UMI_Complex --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> @@ -722,7 +881,9 @@ <param name="soloAdapterSequence" value="GAGTGATTGCTTGTGACGCCTT" /> <param name="soloAdapterMismatchesNmax" value="1" /> <param name="clipAdapterType" value="CellRanger4" /> - <param name="soloUMIdedup" value="1MM_All" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> <param name="soloCBmatchWLtype" value="1MM" /> </conditional> <output name="output_barcodes_filtered" > @@ -730,28 +891,32 @@ <!-- first and last line --> <has_line line="ACAACGTGG_AAACCTCC" /> <has_line line="ATTCCAGAC_TTCGCTGG" /> + <has_n_lines n="33" /> </assert_contents> </output> <output name="output_genes_filtered"> <assert_contents> <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" /> <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" /> + <has_n_lines n="14" /> </assert_contents> </output> <output name="output_matrix_filtered" > <assert_contents> <has_line_matching expression="14\s+33\s+36" /> <has_line_matching expression="2\s+33\s+1" /> + <has_n_lines n="39" /> </assert_contents> </output> <output name="output_stats" > <assert_contents> - <has_line_matching expression="\s+nExactMatch\s+791" /> - <has_line_matching expression="\s+nUMIs\s+36" /> + <has_line_matching expression="\s+yesWLmatchExact\s+791" /> + <has_line_matching expression="\s+yesUMIs\s+36" /> </assert_contents> </output> </test> <test expect_num_outputs="6"> + <!-- test 8 --> <!-- Test soloType SmartSeq --> <conditional name="refGenomeSource"> <param name="geneSource" value="history" /> @@ -824,7 +989,9 @@ </param> </conditional> <param name="cell_ids" value="smartseq.cellids.txt" /> - <param name="soloUMIdedup" value="Exact" /> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="Exact" /> + </conditional> </conditional> <section name="solo" > <param name="soloStrand" value="Unstranded" /> @@ -837,24 +1004,152 @@ <assert_contents> <has_line line="CSC6_D02" /> <not_has_text text="MGH26_A02" /> + <has_n_lines n="3" /> </assert_contents> </output> <output name="output_genes_filtered"> <assert_contents> <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" /> <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" /> + <has_n_lines n="14" /> </assert_contents> </output> <output name="output_matrix_filtered" > <assert_contents> <has_line_matching expression="14\s+3\s+10" /> <has_line_matching expression="12\s+3\s+1" /> + <has_n_lines n="13" /> </assert_contents> </output> <output name="output_stats" > <assert_contents> - <has_line_matching expression="\s+nExactMatch\s+9000" /> - <has_line_matching expression="\s+nUMIs\s+32" /> + <has_line_matching expression="\s+yesWLmatchExact\s+9000" /> + <has_line_matching expression="\s+yesUMIs\s+32" /> + </assert_contents> + </output> + </test> + <test expect_num_outputs="6"> + <!-- test 9 --> + <!-- Test outSAMattributes --> + <conditional name="refGenomeSource"> + <param name="geneSource" value="history" /> + <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" /> + <param name="genomeSAindexNbases" value="4" /> + <param name="sjdbOverhang" value="100" /> + <param name="sjdbGTFfile" value="filtered3.Homo_sapiens.GRCh38.100.chr21.gtf" ftype="gtf"/> + </conditional> + <conditional name="sc" > + <param name="solo_type" value="CB_UMI_Simple" /> + <conditional name="input_types"> + <param name="use" value="repeat" /> + <param name="input1" value="pbmc_1k_v2_L001.R1.10k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="pbmc_1k_v2_L001.R2.10k.fastq.gz" ftype="fastqsanger.gz" /> + </conditional> + <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> + <conditional name="params"> + <param name="chemistry" value="Cv3" /> + </conditional> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_All" /> + </conditional> + </conditional> + <section name="solo" > + <conditional name="filter"> + <param name="filter_type" value="no_filter" /> + </conditional> + <param name="soloStrand" value="Forward" /> + <param name="soloFeatures" value="Gene" /> + <param name="outSAMattributes" value="NH,HI,AS,nM,GX,GN,CB,UB" /> + </section> + <output name="output_barcodes" > + <assert_contents> + <!-- first and last line --> + <has_line line="AAACCTGAGCGCTCCA" /> + <has_line line="TTTGGTTAGTGGGCTA" /> + <has_n_lines n="394" /> + </assert_contents> + </output> + <output name="output_genes"> + <assert_contents> + <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Gene\s+Expression" /> + <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Gene\s+Expression" /> + <has_n_lines n="14" /> + </assert_contents> + </output> + <output name="output_matrix" > + <assert_contents> + <has_line_matching expression="14\s+394\s+7" /> + <has_line_matching expression="4\s+381\s+1" /> + <has_n_lines n="10" /> + </assert_contents> + </output> + <output name="output_stats" > + <assert_contents> + <has_line_matching expression="\s+noUnmapped\s+5823" /> + <has_line_matching expression="\s+yesUMIs\s+8" /> + </assert_contents> + </output> + <output name="output_BAM" > + <assert_contents> + <has_size value="153108" delta="600" /> + </assert_contents> + </output> + </test> + <test expect_num_outputs="6"> + <!-- test 10 --> + <!-- Test soloFeatures --> + <conditional name="refGenomeSource"> + <param name="geneSource" value="history" /> + <param name="genomeFastaFiles" value="filtered3.Homo_sapiens.GRCh38.dna.chromosome.21.fa.gz" /> + <param name="genomeSAindexNbases" value="4" /> + <param name="sjdbOverhang" value="100" /> + <param name="sjdbGTFfile" value="filtered3.Homo_sapiens.GRCh38.100.chr21.gtf" ftype="gtf"/> + </conditional> + <conditional name="sc" > + <param name="solo_type" value="CB_UMI_Simple" /> + <conditional name="input_types"> + <param name="use" value="repeat" /> + <param name="input1" value="pbmc_1k_v2_L001.R1.10k.fastq.gz" ftype="fastqsanger.gz" /> + <param name="input2" value="pbmc_1k_v2_L001.R2.10k.fastq.gz" ftype="fastqsanger.gz" /> + </conditional> + <param name="soloCBwhitelist" value="filtered.barcodes.txt" /> + <param name="soloCBmatchWLtype" value="1MM_multi_pseudocounts" /> + <conditional name="params"> + <param name="chemistry" value="Cv3" /> + </conditional> + <conditional name="umidedup"> + <param name="soloUMIdedup" value="1MM_CR" /> + <param name="soloUMIfiltering" value="MultiGeneUMI" /> + </conditional> + </conditional> + <section name="solo" > + <param name="soloStrand" value="Forward" /> + <param name="soloFeatures" value="GeneFull_ExonOverIntron" /> + <conditional name="filter"> + <param name="filter_type" value="no_filter" /> + </conditional> + <param name="soloOutFormatFeaturesGeneField3" value="Dummy Text" /> + </section> + <output name="output_barcodes" > + <assert_contents> + <!-- first and last line --> + <has_line line="AAACCTGAGCGCTCCA" /> + <has_line line="TTTGGTTAGTGGGCTA" /> + <has_n_lines n="394" /> + </assert_contents> + </output> + <output name="output_genes" > + <assert_contents> + <has_line_matching expression="ENSG00000279493\s+FP565260\.4\s+Dummy\s+Text" /> + <has_line_matching expression="ENSG00000279064\s+FP236315\.1\s+Dummy\s+Text" /> + <has_n_lines n="14" /> + </assert_contents> + </output> + <output name="output_matrixGeneFull" > + <assert_contents> + <has_line_matching expression="14\s+394\s+104" /> + <has_line_matching expression="10\s+2\s+1" /> + <has_n_lines n="107" /> </assert_contents> </output> </test>