Mercurial > repos > bgruening > alevin
diff alevin.xml @ 11:e661a3269313 draft
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/salmon commit 10ccc47885ce71e602d66e157bd475f1facbd042
author | bgruening |
---|---|
date | Mon, 05 Dec 2022 15:47:45 +0000 |
parents | e4c01dcece8b |
children | c9944a2600f1 |
line wrap: on
line diff
--- a/alevin.xml Thu Jul 22 14:05:58 2021 +0000 +++ b/alevin.xml Mon Dec 05 15:47:45 2022 +0000 @@ -1,5 +1,5 @@ -<tool id="alevin" name="Alevin" version="@VERSION@+@GALAXY_VERSION@" profile="@PROFILE_VERSION@"> - <description>Quantification and analysis of 3’ tagged-end single-cell sequencing data</description> +<tool id="alevin" name="Alevin" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE_VERSION@"> + <description>Quantification and analysis of 3-prime tagged-end single-cell sequencing data</description> <macros> <import>macros.xml</import> </macros> @@ -61,7 +61,10 @@ #end if -o ./output -p "\${GALAXY_SLOTS:-4}" - ${protocol} + ${protocol_cond.protocol} + #if $protocol_cond.protocol == '--indropV2' + --w1 '${protocol_cond.w1}' + #end if --tgMap ./alevinmap.tsv #if $whitelist: --whitelist '${optional.whitelist}' @@ -85,39 +88,40 @@ --keepCBFraction '${optional.keepCBFraction}' #end if ${optional.noDedup} - ${optional.dumpBfh} - ${optional.dumpFeatures} - ${optional.dumpUmiGraph} + #if 'dumpBfh' in $output_files: + --dumpBfh + #end if + #if 'dumpFeatures' in $output_files: + --dumpFeatures + #end if + #if 'dumpUmiGraph' in $output_files: + --dumpUmiGraph + #end if ${optional.dumpMtx} - #if $optional.lowRegionMinNumBarcodes: - --lowregionMinNumBarcodes '${optional.lowRegionMinNumBarcodes}' - #end if #if $optional.maxNumBarcodes: --maxNumBarcodes '${optional.maxNumBarcodes}' #end if #if $optional.freqThreshold: --freqThreshold '${optional.freqThreshold}' #end if - + ## && gunzip output/alevin/quants_tier_mat.gz -> the output is binary file #if $optional.dumpMtx != "--dumpMtx": && python '$__tool_directory__/vpolo_convert.py' -m #else: && gunzip output/alevin/quants_mat.mtx.gz #end if - #if $optional.dumpUmiGraph: + #if 'dumpUmiGraph' in $output_files: && python '$__tool_directory__/vpolo_convert.py' -u && sh '$__tool_directory__/umiout.sh' #end if - - && gunzip output/alevin/quants_tier_mat.gz - #if $optional.numCellBootstraps: - && gunzip output/alevin/quants_mean_mat.gz - && gunzip output/alevin/quants_var_mat.gz + ## those gzip file include binary datasets + ## #if $optional.numCellBootstraps: + ## && gunzip output/alevin/quants_mean_mat.gz + ## && gunzip output/alevin/quants_var_mat.gz + ## #end if + #if 'auxiliar_info' in $output_files + && tar -zcvf aux_info.tar.gz output/aux_info #end if - - && gunzip output/aux_info/fld.gz - && gunzip output/aux_info/observed_bias.gz - && gunzip output/aux_info/observed_bias_3p.gz ]]> </command> <inputs> @@ -128,8 +132,8 @@ <option value="unmated">Single-end</option> </param> <when value="paired"> - <param name="file1" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" help="CB+UMI raw sequence file(s)"/> - <param name="file2" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" help="Read-sequence file(s)"/> + <param name="file1" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" label="Mate pair 1" help="CB+UMI raw sequence file(s)"/> + <param name="file2" type="data" format="fastq,fastq.gz,fastqsanger.gz,fastq.bz2" label="Mate pair 2" help="Read-sequence file(s)"/> <expand macro="stranded_pe"/> </when> <when value="unmated"> @@ -137,91 +141,136 @@ <expand macro="stranded_se"/> </when> </conditional> - <param name="protocol" type="select"> - <option value="--dropseq">DropSeq Single Cell protocol</option> - <option value="--chromium">10x chromium v2 Single Cell protocol</option> - <option value="--chromiumV3">10x chromium v3 Single Cell protocol</option> - <option value="--gemcode">Gemcode v1 Single Cell protocol</option> - <option value="--celseq">CEL-Seq Single Cell protocol</option> - <option value="--celseq2">CEL-Seq2 Single Cell protocol</option> - </param> + <conditional name="protocol_cond"> + <param name="protocol" type="select" label="Type of single-cell protocol" help="In cases where single-cell protocol supports variable length cellbarcodes, alevin adds nucleotide padding to make the lengths uniform. Furthermore, the padding scheme ensures that there are no collisions added in the process."> + <option value="--dropseq">DropSeq Single Cell protocol</option> + <option value="--chromium">10x chromium v2 Single Cell protocol</option> + <option value="--chromiumV3">10x chromium v3 Single Cell protocol</option> + <option value="--gemcode">Gemcode v1 Single Cell protocol</option> + <option value="--celseq">CEL-Seq Single Cell protocol</option> + <option value="--celseq2">CEL-Seq2 Single Cell protocol</option> + <option value="--sciseq3">Sci-RNA-seq3 protocol</option> + <option value="--indropV2">InDrop v2 protocol</option> + <option value="--splitSeqV1">SplitSeqV1 protocol</option> + <option value="--splitSeqV2">SplitSeqV2 protocol</option> + </param> + <when value="--dropseq"/> + <when value="--chromium"/> + <when value="--chromiumV3"/> + <when value="--gemcode"/> + <when value="--celseq"/> + <when value="--celseq2"/> + <when value="--sciseq3"/> + <when value="--indropV2"> + <param argument="--w1" type="text" value="" label="w1 adapters"> + <sanitizer invalid_char=""> + <valid initial="string.letters"/> + </sanitizer> + <validator type="regex">[ATGC]+</validator> + </param> + </when> + <when value="--splitSeqV1"/> + <when value="--splitSeqV2"/> + </conditional> <param name="tgmap" type="data" format="tsv,tabular" label="Transcript to gene map file" help="Tsv with no header, containing two columns mapping each transcript present in the reference to the corresponding gene (the first column is a transcript and the second is the corresponding gene)."/> - <param name="allout" type="boolean" label="Retrieve all output files" truevalue="Yes" falsevalue="No" checked="false" help="If not selected, all log, info.txt, and json files output by Alevin will not be retrieved"/> - <section name="optional" title="Optional commands" expanded="false"> - <param name="whitelist" type="data" format="tsv,tabular" optional="true" label="Whitelist file" help="Explicitly specify whitelist CP for cell detection and CB sequence correction. If not specified, putative CBs generated."/> - <param name="noDedup" type="boolean" truevalue="--noDedup" falsevalue="" checked="false" help="Causes pipeline to only perform CB correction, then maps the read-sequences to the transcriptome generating the interim data-structure of CB-EqClass-UMI-count. Used in parallel with --dumpBarcodeEq or --dumpBfh for the purposes of obtaining raw information or debugging."/> - <param name="mrna" type="data" format="tsv" optional="true" help="Single column tsv of mitochondrial genes which are to be used as a feature for CB whitelising naive Bayes classification."/> - <param name="rrna" type="data" format="tsv" optional="true" help="Single column tsv of ribosomal genes which are to be used as a feature for CB whitelising naive Bayes classification."/> - <param name="dumpBfh" type="boolean" truevalue="--dumpBfh" falsevalue="" checked="false" help="Dumps the full CB-EqClass-UMI-count data-structure for the purposed of allowing raw data analysis and debugging."/> - <param name="dumpFeatures" type="boolean" truevalue="--dumpFeatures" falsevalue="" checked="false" help="Dumps all features used by the CB classification and their counts at each cell level. Generally, this is used for the purposes of debugging."/> - <param name="dumpUmiGraph" type="boolean" truevalue="--dumpUmiGraph" falsevalue="" checked="false" help="Dump the per-cell level umi graph"/> - <param name="dumpMtx" type="boolean" truevalue="--dumpMtx" falsevalue="" checked="false" help="Converts the default binary format of alevin for gene-count matrix into a human readable mtx (matrix market exchange) sparse format."/> - <param name="forceCells" type="integer" optional="true" help="Explicitly specify the number of cells."/> - <param name="expectCells" type="integer" optional="true" help="define a close upper bound on expected number of cells."/> - <param name="numCellBootstraps" type="integer" optional="true" help="Performs certain number of bootstrap and generate the mean and variance of the count matrix"/> - <param name="minScoreFraction" type="float" optional="true" help="This value controls the minimum allowed score for a mapping to be considered valid. It matters only when --validateMappings has been passed to Salmon. The maximum possible score for a fragment is ms = read_len * ma (or ms = (left_read_len + right_read_len) * ma for paired-end reads). + <param name="output_files" type="select" multiple="true" display="checkboxes" label="Extra output files"> + <option value="salmon_log">Salmon Quant log file</option> + <option value="fragment_length">Observed fragment length distribution</option> + <option value="auxiliar_info">Auxiliar info files</option> + <option value="dumpUmiGraph">Per cell level parsimonious Umi graph (--dumpUmiGraph)</option> + <option value="dumpFeatures">Features used by the CB classification and their counts at each cell level (--dumpFeatures)</option> + <option value="dumpBfh">Full CB-EC-UMI-count data-structure (--dumpBfh)</option> + <option value="commands">Commands info file</option> + </param> + <section name="optional" title="Advanced options" expanded="false"> + <param argument="--whitelist" type="data" format="tsv,tabular" optional="true" label="Whitelist file" help="Explicitly specify whitelist CP for cell detection and CB sequence correction. If not specified, putative CBs generated."/> + <param argument="--noDedup" type="boolean" truevalue="--noDedup" falsevalue="" checked="false" label="Skip deduplication step" help="Causes pipeline to only perform CB correction, then maps the read-sequences to the transcriptome generating the interim data-structure of CB-EqClass-UMI-count. Used in parallel with --dumpBarcodeEq or --dumpBfh for the purposes of obtaining raw information or debugging."/> + <param argument="--mrna" type="data" format="tsv" optional="true" label="Mito-RNA genes file" help="Single column tsv of mitochondrial genes which are to be used as a feature for CB whitelising naive Bayes classification."/> + <param argument="--rrna" type="data" format="tsv" optional="true" label="Ribosomal RNA file" help="Single column tsv of ribosomal genes which are to be used as a feature for CB whitelising naive Bayes classification."/> + <param argument="--dumpMtx" type="boolean" truevalue="--dumpMtx" falsevalue="" checked="false" label=" Dump cell v transcripts count matrix in MTX format" help="Converts the default binary format of alevin for gene-count matrix into a human readable mtx (matrix market exchange) sparse format."/> + <param argument="--forceCells" type="integer" min="0" optional="true" label="Number of cells" help="Explicitly specify the number of cells."/> + <param argument="--expectCells" type="integer" min="0" optional="true" label="Upper bound on expected number of cells" help="define a close upper bound on expected number of cells."/> + <param argument="--numCellBootstraps" type="integer" min="0" value="0" optional="true" label="Generate mean and variance for cell x gene matrix by boostrap" help="Performs certain number of bootstrap and generate the mean and variance of the count matrix"/> + <param argument="--minScoreFraction" type="float" optional="true" label="Minimum allowed score for a mapping" help="This value controls the minimum allowed score for a mapping to be considered valid. It matters only when --validateMappings has been passed to Salmon. The maximum possible score for a fragment is ms = read_len * ma (or ms = (left_read_len + right_read_len) * ma for paired-end reads). The argument to --minScoreFraction determines what fraction of the maximum score s a mapping must achieve to be potentially retained. For a minimum score fraction of f, only mappings with a score less than (f * s) will be kept. Mappings with lower scores will be considered as low-quality, and will be discarded."/> - <param name="keepCBFraction" type="float" optional="true" help="Fraction of cellular barcodes to keep (Between 0 and 1)."/> - <param name="lowRegionMinNumBarcodes" type="integer" optional="true" help="Minimum number of cell barcodes to use fo learning low confidence region (defaults to 200)"/> - <param name="maxNumBarcodes" type="integer" optional="true" help="Maximum allowable limit to process the cell barcodes. Defaults to 100000"/> - <param name="freqThreshold" type="integer" optional="true" help="Minimum frequency for a barcode to be considered. Defaults to 10"/> + <param argument="--keepCBFraction" type="float" min="0" max="1" optional="true" label="Fraction of cellular barcodes to keep" help="Use 1 to quantify all"/> + <param argument="--maxNumBarcodes" type="integer" min="0" value="100000" label="Maximum allowable limit to process the cell barcodes" help="Default: 100000"/> + <param argument="--freqThreshold" type="integer" min="0" value="10" optional="true" label="Minimum frequency for a barcode to be considered" help="Default: 10"/> </section> </inputs> <outputs> - <data name="quants_mat_tsv" label="quants_mat.tsv" format="txt" from_work_dir="quants_mat.tsv"> + <data name="quants_mat_tsv" label="${tool.name} on ${on_string}: per-cell gene-count matrix (tabular)" format="txt" from_work_dir="quants_mat.tsv"> <filter>optional["dumpMtx"] is not True</filter> </data> - <data name="quants_mat_mtx" label="quants_mat.mtx" format="mtx" from_work_dir="output/alevin/quants_mat.mtx"> + <data name="quants_mat_mtx" label="${tool.name} on ${on_string}: per-cell gene-count matrix (MTX)" format="mtx" from_work_dir="output/alevin/quants_mat.mtx"> <filter>optional["dumpMtx"]</filter> </data> - <data name="raw_cb_frequency_txt" label="raw_cb_frequency.txt" format="txt" from_work_dir="output/alevin/raw_cb_frequency.txt"> - <filter>optional["dumpFeatures"]</filter> + <data name="quants_mat_gz" label="${tool.name} on ${on_string}: per-cell level gene-count matrix (binary)" format="gz" from_work_dir="output/alevin/quants_mat.gz"/> + <data name="quants_mat_cols_txt" label="${tool.name} on ${on_string}: column headers (gene-ids)" format="txt" from_work_dir="output/alevin/quants_mat_cols.txt"/> + <data name="quants_mat_rows_txt" label="${tool.name} on ${on_string}: row index (CB-ids)" format="txt" from_work_dir="output/alevin/quants_mat_rows.txt"/> + <data name="quants_tier_mat" label="${tool.name} on ${on_string}: tier categorization" format="gz" from_work_dir="output/alevin/quants_tier_mat.gz"/> + <data name="featureDump_txt" label="${tool.name} on ${on_string}: cell-level information (featureDump)" format="txt" from_work_dir="output/alevin/featureDump.txt"/> + <data name="raw_cb_frequency_txt" label="${tool.name} on ${on_string}: raw CB classification frequencies" format="txt" from_work_dir="output/alevin/raw_cb_frequency.txt"> + <filter>output_files and 'dumpFeatures' in output_files</filter> </data> - <data name="quants_mat_cols_txt" label="quants_mat_cols.txt" format="txt" from_work_dir="output/alevin/quants_mat_cols.txt"/> - <data name="quants_mat_rows_txt" label="quants_mat_rows.txt" format="txt" from_work_dir="output/alevin/quants_mat_rows.txt"/> - <data name="quants_tier_mat" label="quants_tier_mat" format="mtx" from_work_dir="output/alevin/quants_tier_mat"/> - <data name="alevin_log" label="alevin.log" format="txt" from_work_dir="output/alevin/alevin.log"> - <filter>allout</filter> + <data name="whitelist_txt" label="${tool.name} on ${on_string}: whitelist" format="txt" from_work_dir="output/alevin/whitelist.txt"/> + + <data name="auxiliar_files" label="${tool.name} on ${on_string}: auxiliar info files" format="tgz" from_work_dir="aux_info.tar.gz"> + <filter>output_files and 'auxiliar_info' in output_files</filter> </data> - <data name="featureDump_txt" label="featureDump.txt" format="txt" from_work_dir="output/alevin/featureDump.txt"/> - <data name="whitelist_txt" label="whitelist.txt" format="txt" from_work_dir="output/alevin/whitelist.txt"/> - <data name="bfh_txt" label="bfh.txt" format="txt" from_work_dir="output/alevin/bfh.txt"> - <filter>optional["dumpBfh"]</filter> + <data name="salmon_quant_log" format="txt" label="${tool.name} on ${on_string}: Salmon log file" from_work_dir="output/logs/salmon_quant.log"> + <filter>output_files and 'salmon_log' in output_files</filter> + </data> + <data name="cmd_info" label="${tool.name} on ${on_string}: command info (JSON)" format="json" from_work_dir="output/cmd_info.json"> + <filter>output_files and 'commands' in output_files</filter> </data> - <data name="quants_mean_mat" label="quants_mean_mat" format="mtx" from_work_dir="output/alevin/quants_mean_mat"> - <filter>optional["numCellBootstraps"]</filter> + <data name="flenDist_txt" format="txt" label="${tool.name} on ${on_string}: observed fragment length distribution" from_work_dir="output/libParams/flenDist.txt"> + <filter>output_files and 'fragment_length' in output_files</filter> </data> - <data name="quants_var_mat" label="quants_var_mat" format="mtx" from_work_dir="output/alevin/quants_var_mat"> + <data name="bfh_txt" label="${tool.name} on ${on_string}: full CB-EC-UMI-count data-structure" format="txt" from_work_dir="output/alevin/bfh.txt"> + <filter>output_files and 'dumpBfh' in output_files</filter> + </data> + <data name="quants_mean_mat" label="${tool.name} on ${on_string}: count matrix mean file" format="gz" from_work_dir="output/alevin/quants_mean_mat.gz"> <filter>optional["numCellBootstraps"]</filter> </data> - <data name="quants_boot_rows_txt" label="quants_boot_rows.txt" format="txt" from_work_dir="output/alevin/quants_boot_rows.txt"> + <data name="quants_var_mat" label="${tool.name} on ${on_string}: count matrix variance file" format="gz" from_work_dir="output/alevin/quants_var_mat.gz"> + <filter>optional["numCellBootstraps"]</filter> + </data> + <data name="quants_boot_rows_txt" label="${tool.name} on ${on_string}: bootstraps rows" format="txt" from_work_dir="output/alevin/quants_boot_rows.txt"> <filter>optional["numCellBootstraps"]</filter> </data> - <data name="alevinmeta_info_json" format="json" label="meta_info.json" from_work_dir="output/aux_info/alevin_meta_info.json"> - <filter>allout</filter> - </data> - <data name="ambig_info_tsv" format="tsv" label="ambig_info.tsv" from_work_dir="output/aux_info/ambig_info.tsv"> - <filter>allout</filter> - </data> - <data name="meta_info_json" format="json" label="meta_info.json" from_work_dir="output/aux_info/meta_info.json"> - <filter>allout</filter> - </data> - <data name="expected_bias" format="txt" label="expected_bias" from_work_dir="output/aux_info/fld"/> - <data name="observed_bias" format="txt" label="observed_bias" from_work_dir="output/aux_info/observed_bias"/> - <data name="observed_bias_3p" format="txt" label="observed_bias_3p" from_work_dir="output/aux_info/observed_bias_3p"/> - <data name="flenDist_txt" format="txt" label="flenDist.txt" from_work_dir="output/libParams/flenDist.txt"/> - <data name="salmon_quant_log" format="txt" label="salmon_quant.log" from_work_dir="output/logs/salmon_quant.log"> - <filter>allout</filter> - </data> - <collection name="umigraphs" type="list" label="Umi graph PDFs"> - <filter>optional["dumpUmiGraph"]</filter> - <discover_datasets pattern="__name_and_ext__" ext="pdf" directory="fixed"/> + <collection name="umigraphs" type="list" label="${tool.name} on ${on_string}: UMI graph PDFs"> + <filter>output_files and 'dumpUmiGraph' in output_files</filter> + <discover_datasets pattern="(?P<name>.+)\.pdf" format="pdf" directory="fixed"/> </collection> - <data name="cmd_info.json" label="cmd_info.json" format="json" from_work_dir="output/cmd_info.json"> - <filter>allout</filter> - </data> </outputs> <tests> + <test expect_num_outputs="8"> + <conditional name="refTranscriptSource"> + <param name="TranscriptSource" value="history"/> + <section name="s_index"> + <param name="fasta" value="minitranscript.fa"/> + </section> + </conditional> + <conditional name="pairstraight"> + <param name="readselect" value="paired"/> + <param name="file1" value="fastqs/moreminifastq1.fastq.gz"/> + <param name="file2" value="fastqs/moreminifastq2.fastq.gz"/> + <param name="orientation" value="I"/> + <param name="strandedness" value="SR"/> + </conditional> + <conditional name="protocol_cond"> + <param name="protocol" value="--chromium"/> + </conditional> + <param name="tgmap" value="minitxp.tsv"/> + <param name="output_files" value="dumpFeatures"/> + <section name="optional"> + <param name="keepCBFraction" value="1"/> + <param name="freqThreshold" value="5"/> + <param name="dumpMtx" value="true"/> + </section> + <output name="quants_mat_mtx" file="alevin_mat_01.mtx" ftype="mtx" sort="true"/> + </test> <test expect_num_outputs="11"> <conditional name="refTranscriptSource"> <param name="TranscriptSource" value="history"/> @@ -236,15 +285,45 @@ <param name="orientation" value="I"/> <param name="strandedness" value="SR"/> </conditional> - <param name="protocol" value="--chromium"/> + <conditional name="protocol_cond"> + <param name="protocol" value="--chromium"/> + </conditional> <param name="tgmap" value="minitxp.tsv"/> + <param name="output_files" value="dumpFeatures"/> <section name="optional"> <param name="keepCBFraction" value="1"/> - <param name="dumpFeatures" value="Yes"/> + <param name="numCellBootstraps" value="2"/> <param name="freqThreshold" value="5"/> - <param name="dumpMtx" value="Yes"/> + <param name="dumpMtx" value="true"/> </section> - <output name="quants_mat_mtx" file="alevin_mat.mtx" ftype="mtx" sort="true" lines_diff="62"/> + <output name="quants_mat_mtx" file="alevin_mat_02.mtx" ftype="mtx" sort="true"/> + </test> + <test expect_num_outputs="8"> + <conditional name="refTranscriptSource"> + <param name="TranscriptSource" value="history"/> + <section name="s_index"> + <param name="fasta" value="minitranscript.fa"/> + </section> + </conditional> + <conditional name="pairstraight"> + <param name="readselect" value="paired"/> + <param name="file1" value="fastqs/moreminifastq1.fastq.gz"/> + <param name="file2" value="fastqs/moreminifastq2.fastq.gz"/> + <param name="orientation" value="I"/> + <param name="strandedness" value="SR"/> + </conditional> + <conditional name="protocol_cond"> + <param name="protocol" value="-\-indropV2"/> + <param name="w1" value="ATCAT"/> + </conditional> + <param name="tgmap" value="minitxp.tsv"/> + <param name="output_files" value="dumpFeatures"/> + <section name="optional"> + <param name="keepCBFraction" value="1"/> + <param name="freqThreshold" value="5"/> + <param name="dumpMtx" value="true"/> + </section> + <output name="quants_mat_mtx" file="alevin_mat_indropV2.mtx" ftype="mtx" sort="true"/> </test> <test expect_num_outputs="14"> <conditional name="refTranscriptSource"> @@ -260,16 +339,35 @@ <param name="orientation" value="I"/> <param name="strandedness" value="SR"/> </conditional> - <param name="protocol" value="--chromium"/> + <conditional name="protocol_cond"> + <param name="protocol" value="--chromium"/> + </conditional> <param name="tgmap" value="minitxp.tsv"/> + <param name="output_files" value="dumpFeatures,salmon_log,fragment_length,auxiliar_info,dumpUmiGraph,dumpBfh,commands"/> <section name="optional"> - <param name="keepCBFraction" value="1"/> - <param name="dumpFeatures" value="Yes"/> - <param name="numCellBootstraps" value="2"/> - <param name="freqThreshold" value="5"/> - <param name="dumpMtx" value="Yes"/> + <param name="dumpMtx" value="true"/> </section> - <output name="quants_mat_mtx" file="alevin_mat.mtx" ftype="mtx" sort="true" lines_diff="62"/> + <output name="quants_mat_mtx" file="alevin_mat.mtx" ftype="mtx" sort="true"/> + <output name="salmon_quant_log" ftype="txt"> + <assert_contents> + <has_text text="Index contained 322 targets"/> + <has_text text="Counted 14 total reads in the equivalence classes"/> + </assert_contents> + </output> + <output name="flenDist_txt" file="length_distribution.txt" ftype="txt"/> + <output name="auxiliar_files" ftype="tgz"> + <assert_contents> + <has_size value="1898" delta="100"/> + </assert_contents> + </output> + <output_collection name="umigraphs" type="list" count="14"> + <element name="AGTGGGATCTTAACCT"> + <assert_contents> + <has_size value="4017" delta="1000"/> + </assert_contents> + </element> + </output_collection> + <output name="bfh_txt" file="full_data_structure.txt" ftype="txt"/> </test> </tests> <help><![CDATA[