Mercurial > repos > iuc > multiqc
changeset 27:7591bce96601 draft default tip
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/multiqc commit 327834d2ea9b16f0f0264fa4e9b675a2277f2fee
| author | iuc |
|---|---|
| date | Tue, 18 Feb 2025 23:18:25 +0000 |
| parents | d2aaac19f42f |
| children | |
| files | bakta_plugin.xml bamtools_plugin.xml bbduk_plugin.xml checkm_plugin.xml diamond_plugin.xml freyja_plugin.xml gtdbtk_plugin.xml kraken_plugin.xml macros.xml megahit_plugin.xml metaphlan_plugin.xml multiqc.xml nonpareil_plugin.xml pairtools_plugin.xml picard_plugin.xml porechop_plugin.xml samtools_plugin.xml snippy_plugin.xml template_plugin.xml test-data/bakta.txt test-data/bbduk.txt test-data/checkm.tabular test-data/diamond.log test-data/freyja.tsv test-data/gtdbtk.tsv test-data/kraken_test0_report.tab test-data/megahit.txt test-data/metaphlan.txt test-data/nonpareil.json test-data/output_dedup_pairs.stats test-data/porechop.log test-data/snippy.txt |
| diffstat | 32 files changed, 3900 insertions(+), 7 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bakta_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,48 @@ +<macros> + <token name="@BAKTA_COMMAND@"><![CDATA[ + #set $pattern = "Bakta:" + #for $file in $repeat.software_cond.input + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, str($identifier) + '.txt') + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="bakta_form"> + <param name="input" type="data" format="txt" multiple="true" label="Output of Bakta" help="It should contain 'Bakta:'"/> + </xml> + <xml name="bakta_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="bakta"/> + <param name="input" value="bakta.txt"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="Bakta"/> + <has_text text="bakta_txt"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="bakta-Count"/> + <has_text text="bakta-Length"/> + <has_text text="bakta-CDSs"/> + <has_text text="1"/> + <has_text text="1330"/> + <has_text text="2"/> + <has_n_lines n="2"/> + <has_n_columns n="4"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- a/bamtools_plugin.xml Tue Feb 11 10:13:08 2025 +0000 +++ b/bamtools_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -1,6 +1,6 @@ <macros> <token name="@BAMTOOLS_COMMAND@"><![CDATA[ - #set $pattern = "Stats for BAM file(s)" + #set $pattern = "Stats for BAM file\(s\)" @LN_FILES@ ]]></token> <xml name="bamtools_form">
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bbduk_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,44 @@ +<macros> + <token name="@BBDUK_COMMAND@"><![CDATA[ + #set $pattern = "Executing jgi\.BBDuk" + @LN_FILES@ + ]]></token> + <xml name="bbduk_form"> + <param name="input" type="data" format="txt" multiple="true" label="Output of BBDuk" help="It should contain 'Executing jgi.BBDuk'"/> + </xml> + <xml name="bbduk_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="bbduk"/> + <param name="input" value="bbduk.txt"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="BBDuk"/> + <has_text text="BBDuk: Filtered Reads"/> + <has_text text="0.0"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="bbduk-Total_Removed_bases_percent"/> + <has_text text="bbduk-Total_Removed_bases"/> + <has_text text="bbduk-Total_Removed_reads_percent"/> + <has_text text="bbduk-Total_Removed_reads"/> + <has_text text="bbduk-Input_reads"/> + <has_n_lines n="2"/> + <has_n_columns n="6"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="2"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/checkm_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,37 @@ +<macros> + <token name="@CHECKM_COMMAND@"><![CDATA[ + #set $pattern = ".*Bin Id(?:\t| {3,})Marker lineage(?:\t| {3,})# genomes(?:\t| {3,})# markers(?:\t| {3,})# marker sets.*" + #for $file in $repeat.software_cond.input + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, 'output_file') + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="checkm_form"> + <param name="input" type="data" format="tabular" multiple="true" label="Output of Checkm"/> + </xml> + <xml name="checkm_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="checkm"/> + <param name="input" value="checkm.tabular"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="CheckM"/> + <has_text text="Bin quality"/> + <has_text text="637000110"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/diamond_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,45 @@ +<macros> + <token name="@DIAMOND_COMMAND@"><![CDATA[ + #for $file in $repeat.software_cond.input + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, 'diamond.log') + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="diamond_form"> + <param name="input" type="data" format="txt" multiple="true" label="Log output of DIAMOND"/> + </xml> + <xml name="diamond_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="diamond"/> + <param name="input" value="diamond.log"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="DIAMOND"/> + <has_text text="Queries aligned"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="Sample"/> + <has_text text="diamond_0"/> + <has_text text="diamond-queries_aligned"/> + <has_text text="1"/> + <has_n_lines n="2"/> + <has_n_columns n="2"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/freyja_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,46 @@ +<macros> + <token name="@FREYJA_COMMAND@"><![CDATA[ + #set $pattern = "summarized\t\[" + #for $file in $repeat.software_cond.input + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, str($identifier) + '.tsv') + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="freyja_form"> + <param name="input" type="data" format="tsv" multiple="true" label="Output of Freyja" help="It should contain 'summarized\t['"/> + </xml> + <xml name="freyja_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="freyja"/> + <param name="input" value="freyja.tsv"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="Freyja Summary"/> + <has_text text="Top lineage"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="freyja-Top_lineage_freyja"/> + <has_text text="freyja-Top_lineage_freyja_percentage"/> + <has_text text="A"/> + <has_text text="57.89470000000878"/> + <has_n_lines n="2"/> + <has_n_columns n="3"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="1"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gtdbtk_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,32 @@ +<macros> + <token name="@GTDBTK_COMMAND@"><![CDATA[ + #set $pattern = "user_genome\tclassification\tclosest_genome_reference\tclosest_genome_reference_radius\tclosest_genome_taxonomy\tclosest_genome_ani" + @LN_FILES@ + ]]></token> + <xml name="gtdbtk_form"> + <param name="input" type="data" format="tsv" multiple="true" label="Output of GTDB-Tk" help="It should contain 'user_genome\tclassification\tclosest_genome_reference\tclosest_genome_reference_radius\tclosest_genome_taxonomy\tclosest_genome_ani'"/> + </xml> + <xml name="gtdbtk_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="gtdbtk"/> + <param name="input" value="gtdbtk.tsv"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="GTDB-Tk"/> + <has_text text="genome_1_fna_gz"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/kraken_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,43 @@ +<macros> + <token name="@KRAKEN_COMMAND@"><![CDATA[ + #set $pattern = "^\s{0,2}(\d{1,3}\.\d{1,2})\t(\d+)\t(\d+)\t((\d+)\t(\d+)\t)?([URDKPCOFGS-]\d{0,2})\t(\d+)(\s+)[root|unclassified]" + @LN_FILES@ + ]]></token> + <xml name="kraken_form"> + <param name="input" type="data" format="tabular" multiple="true" label="Output report of Kraken 1 or 2" /> + </xml> + <xml name="kraken_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="kraken"/> + <param name="input" value="kraken_test0_report.tab"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="General Statistics"/> + <has_text text="kraken_test0_report_tab"/> + <has_text text="100.0"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="kraken-pct_top_one"/> + <has_text text="kraken-pct_top_n"/> + <has_text text="100.0"/> + <has_text text="kraken_test0_report_tab"/> + <has_n_lines n="2"/> + <has_n_columns n="3"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- a/macros.xml Tue Feb 11 10:13:08 2025 +0000 +++ b/macros.xml Tue Feb 18 23:18:25 2025 +0000 @@ -1,6 +1,6 @@ <macros> <token name="@TOOL_VERSION@">1.27</token> - <token name="@VERSION_SUFFIX@">1</token> + <token name="@VERSION_SUFFIX@">2</token> <xml name="bio_tools"> <xrefs> <xref type="bio.tools">multiqc</xref> @@ -55,7 +55,7 @@ #set $file_path += '_' + str($file_paths.count($file_path)) #end if #set $file_paths += [$file_path] - grep -q '$pattern' $file || die "Module '${repeat.software_cond.software}: '$pattern' not found in the file '$identifier'" && + grep -Pq '$pattern' $file || die "Module '${repeat.software_cond.software}: '$pattern' not found in the file '$identifier'" && ln -s '$file' '$file_path' && ]]></token> <token name="@CREATE_REPEAT_DIR_1@">
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/megahit_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,44 @@ +<macros> + <token name="@MEGAHIT_COMMAND@"><![CDATA[ + #set $pattern = " - MEGAHIT v" + @LN_FILES@ + ]]></token> + <xml name="megahit_form"> + <param name="input" type="data" format="txt" multiple="true" label="Output of MEGAHIT" help="It should contain ' - MEGAHIT v'"/> + </xml> + <xml name="megahit_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="megahit"/> + <param name="input" value="megahit.txt"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="MEGAHIT"/> + <has_text text="NGS read assembler"/> + <has_text text="Metrics and run statistics from MEGAHIT run logs"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="megahit-megahit_contigs"/> + <has_text text="megahit-megahit_avg_contig"/> + <has_text text="megahit-megahit_n50"/> + <has_text text="576"/> + <has_text text="1"/> + <has_n_lines n="2"/> + <has_n_columns n="4"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/metaphlan_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,46 @@ +<macros> + <token name="@METAPHLAN_COMMAND@"><![CDATA[ + #set $pattern = "#clade_name\tNCBI_tax_id\trelative_abundance\t" + #for $file in $repeat.software_cond.input + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, str($identifier) + '.txt') + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="metaphlan_form"> + <param name="input" type="data" format="txt" multiple="true" label="Output of MetaPhlAn" help="It should contain '#clade_name\tNCBI_tax_id\trelative_abundance\t'"/> + </xml> + <xml name="metaphlan_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="metaphlan"/> + <param name="input" value="metaphlan.txt"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="MetaPhlAn"/> + <has_text text="Top taxa"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="metaphlan-Moraxella_lacunata"/> + <has_text text="metaphlan-Top"/> + <has_text text="22.57968"/> + <has_text text="100.00001000000002"/> + <has_n_lines n="2"/> + <has_n_columns n="3"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="7"/> + </test> + </xml> +</macros>
--- a/multiqc.xml Tue Feb 11 10:13:08 2025 +0000 +++ b/multiqc.xml Tue Feb 18 23:18:25 2025 +0000 @@ -23,6 +23,19 @@ <import>star_plugin.xml</import> <import>trimmomatic_plugin.xml</import> <import>vcftools_plugin.xml</import> + <import>kraken_plugin.xml</import> + <import>diamond_plugin.xml</import> + <import>bakta_plugin.xml</import> + <import>freyja_plugin.xml</import> + <import>checkm_plugin.xml</import> + <import>pairtools_plugin.xml</import> + <import>porechop_plugin.xml</import> + <import>snippy_plugin.xml</import> + <import>metaphlan_plugin.xml</import> + <import>bbduk_plugin.xml</import> + <import>megahit_plugin.xml</import> + <import>nonpareil_plugin.xml</import> + <import>gtdbtk_plugin.xml</import> <import>sambamba_plugin.xml</import> </macros> <expand macro="bio_tools"/> @@ -144,6 +157,32 @@ @TRIMMOMATIC_COMMAND@ #elif str($repeat.software_cond.software) == "vcftools" @VCFTOOLS_COMMAND@ + #elif str($repeat.software_cond.software) == "kraken" + @KRAKEN_COMMAND@ + #elif str($repeat.software_cond.software) == "diamond" + @DIAMOND_COMMAND@ + #elif str($repeat.software_cond.software) == "bakta" + @BAKTA_COMMAND@ + #elif str($repeat.software_cond.software) == "freyja" + @FREYJA_COMMAND@ + #elif str($repeat.software_cond.software) == "checkm" + @CHECKM_COMMAND@ + #elif str($repeat.software_cond.software) == "pairtools" + @PAIRTOOLS_COMMAND@ + #elif str($repeat.software_cond.software) == "porechop" + @PORECHOP_COMMAND@ + #elif str($repeat.software_cond.software) == "snippy" + @SNIPPY_COMMAND@ + #elif str($repeat.software_cond.software) == "metaphlan" + @METAPHLAN_COMMAND@ + #elif str($repeat.software_cond.software) == "bbduk" + @BBDUK_COMMAND@ + #elif str($repeat.software_cond.software) == "megahit" + @MEGAHIT_COMMAND@ + #elif str($repeat.software_cond.software) == "nonpareil" + @NONPAREIL_COMMAND@ + #elif str($repeat.software_cond.software) == "gtdbtk" + @GTDBTK_COMMAND@ #elif str($repeat.software_cond.software) == "sambamba" @SAMBAMBA_COMMAND@ #else if str($repeat.software_cond.software) == "custom_content": @@ -253,6 +292,19 @@ <option value="tophat">TopHat2 (TopHat2 is deprecated you should not use it)</option> <option value="trimmomatic">Trimmomatic</option> <option value="vcftools">VCFTools</option> + <option value="kraken">Kraken 1 or 2</option> + <option value="diamond">DIAMOND</option> + <option value="bakta">Bakta</option> + <option value="freyja">Freyja</option> + <option value="checkm">CheckM</option> + <option value="pairtools">pairtools</option> + <option value="porechop">Porechop</option> + <option value="snippy">Snippy</option> + <option value="metaphlan">MetaPhlAn</option> + <option value="bbduk">BBDuk</option> + <option value="megahit">MEGAHIT</option> + <option value="nonpareil">Nonpareil</option> + <option value="gtdbtk">GTDB-Tk</option> <!--<option value="verifybamid">VerifyBAMID</option>--> <!--Custom--> <option value="custom_content">Custom Content</option> @@ -353,6 +405,45 @@ <when value="vcftools"> <expand macro="vcftools_form"/> </when> + <when value="kraken"> + <expand macro="kraken_form"/> + </when> + <when value="diamond"> + <expand macro="diamond_form"/> + </when> + <when value="bakta"> + <expand macro="bakta_form"/> + </when> + <when value="freyja"> + <expand macro="freyja_form"/> + </when> + <when value="checkm"> + <expand macro="checkm_form"/> + </when> + <when value="pairtools"> + <expand macro="pairtools_form"/> + </when> + <when value="porechop"> + <expand macro="porechop_form"/> + </when> + <when value="snippy"> + <expand macro="snippy_form"/> + </when> + <when value="metaphlan"> + <expand macro="metaphlan_form"/> + </when> + <when value="bbduk"> + <expand macro="bbduk_form"/> + </when> + <when value="megahit"> + <expand macro="megahit_form"/> + </when> + <when value="nonpareil"> + <expand macro="nonpareil_form"/> + </when> + <when value="gtdbtk"> + <expand macro="gtdbtk_form"/> + </when> <when value="sambamba"> <expand macro="sambamba_form"/> </when> @@ -432,6 +523,19 @@ <expand macro="gatk_test"/> <expand macro="bamtools_test"/> <expand macro="pycoqc_test"/> + <expand macro="kraken_test"/> + <expand macro="diamond_test"/> + <expand macro="bakta_test"/> + <expand macro="freyja_test"/> + <expand macro="checkm_test"/> + <expand macro="pairtools_test"/> + <expand macro="porechop_test"/> + <expand macro="snippy_test"/> + <expand macro="metaphlan_test"/> + <expand macro="bbduk_test"/> + <expand macro="megahit_test"/> + <expand macro="nonpareil_test"/> + <expand macro="gtdbtk_test"/> <expand macro="sambamba_test"/> <!--expand macro="vcftools_test"/> Does not work, did it ever worked? -->
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/nonpareil_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,52 @@ +<macros> + <token name="@NONPAREIL_COMMAND@"><![CDATA[ + #set $pattern = "LRstar" + #for $file in $repeat.software_cond.input + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, str($identifier) + '.json') + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="nonpareil_form"> + <param name="input" type="data" format="json" multiple="true" label="JSON object output of Nonpareil" help="It should contain 'LRstar'"/> + </xml> + <xml name="nonpareil_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="nonpareil"/> + <param name="input" value="nonpareil.json"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="Estimates metagenomic coverage and sequence diversity"/> + <has_text text="Nonpareil"/> + <has_text text="Redundancy levels"/> + <has_text text="21.3"/> + <has_text text="24.3"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="nonpareil-nonpareil_R"/> + <has_text text="nonpareil-nonpareil_LR"/> + <has_text text="nonpareil-nonpareil_kappa"/> + <has_text text="nonpareil-nonpareil_C"/> + <has_text text="nonpareil-nonpareil_diversity"/> + <has_text text="11.9521"/> + <has_text text="0.0005"/> + <has_n_lines n="2"/> + <has_n_columns n="6"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="3"/> + </test> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/pairtools_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,55 @@ +<macros> + <token name="@PAIRTOOLS_COMMAND@"><![CDATA[ + #set $pattern = "total_single_sided_mapped" + #set file_paths = [] + #for $file in $repeat.software_cond.input: + @ESCAPE_IDENTIFIER@ + #set file_path = os.path.join($software_dir, str($identifier)) + #if $file_path in $file_paths + #set $file_path += '_' + str($file_paths.count($file_path)) + #end if + #set $file_paths += [$file_path] + grep -Pzq "(?s)(?=.*total_single_sided_mapped\t)(?=.*cis\t)(?=.*trans\t)(?=.*pair_types/)" $file || die "Module '${repeat.software_cond.software}: '$pattern' not found in the file '$identifier'" && + ln -s '$file' '$file_path' && + #end for + ]]></token> + <xml name="pairtools_form"> + <param name="input" type="data" format="tabular" multiple="true" label="Output of Pairtools"/> + </xml> + <xml name="pairtools_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="pairtools"/> + <param name="input" value="output_dedup_pairs.stats"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="output_dedup_pairs"/> + <has_text text="Pairs by alignment status"/> + <has_text text="Fraction of read pairs by strand orientation"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="pairtools-total"/> + <has_text text="pairtools-frac_unmapped"/> + <has_text text="0.001992"/> + <has_text text="45.88353413654618"/> + <has_text text="pairtools-frac_dups"/> + <has_text text="0.4518072289156626"/> + <has_n_lines n="2"/> + <has_n_columns n="8"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="5"/> + </test> + </xml> +</macros>
--- a/picard_plugin.xml Tue Feb 11 10:13:08 2025 +0000 +++ b/picard_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -12,7 +12,7 @@ @LN_2_FILES@ #elif str($repeat2.type) == "hsmetrics" #set $pattern = "picard.analysis.directed.HsMetrics" - @ @ + @LN_2_FILES@ #elif str($repeat2.type) == "insertsize" #set $pattern = "picard.analysis.InsertSizeMetrics" @LN_2_FILES@
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/porechop_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,44 @@ +<macros> + <token name="@PORECHOP_COMMAND@"><![CDATA[ + #set $pattern = "Looking for known adapter sets" + @LN_FILES@ + ]]></token> + <xml name="porechop_form"> + <param name="input" type="data" format="txt" multiple="true" label="Output of Porechop" help="It should contain 'Looking for known adapter sets'"/> + </xml> + <xml name="porechop_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="porechop"/> + <param name="input" value="porechop.log"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="Porechop"/> + <has_text text="Reads adapter-trimmed read end"/> + <has_text text="Middle split reads"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="porechop-Input_Reads"/> + <has_text text="porechop-Start_Trimmed"/> + <has_text text="porechop-Middle_Split_Percent"/> + <has_text text="44.44444444444444"/> + <has_text text="4e-06"/> + <has_n_lines n="2"/> + <has_n_columns n="8"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="3"/> + </test> + </xml> +</macros>
--- a/samtools_plugin.xml Tue Feb 11 10:13:08 2025 +0000 +++ b/samtools_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -6,7 +6,7 @@ #set $pattern = "This file was produced by samtools stats" @LN_3_FILES@ #elif str($repeat2.type.type) == "flagstat" - #set $pattern = "in total (QC-passed reads + QC-failed reads)" + #set $pattern = "in total \(QC-passed reads \+ QC-failed reads\)" @LN_3_FILES@ #elif str($repeat2.type.type) == "idxstats" #for $file in $repeat2.type.input @@ -15,7 +15,7 @@ ln -s '$file' '$file_path' && #end for #elif str($repeat2.type.type) == "rmdup" - #set $pattern = "[bam_rmdup" + #set $pattern = "\[bam_rmdup" @LN_3_FILES@ #end if #end for
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snippy_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,42 @@ +<macros> + <token name="@SNIPPY_COMMAND@"><![CDATA[ + #set $pattern = "snippy|ID\tLENGTH\tALIGNED\tUNALIGNED\tVARIANT\tHET\tMASKED\tLOWCOV" + @LN_FILES@ + ]]></token> + <xml name="snippy_form"> + <param name="input" type="data" format="txt" multiple="true" label="Output summary of Snippy" help="It should contain 'snippy' or 'ID\tLENGTH\tALIGNED\tUNALIGNED\tVARIANT\tHET\tMASKED\tLOWCOV'"/> + </xml> + <xml name="snippy_test"> + <test expect_num_outputs="3"> + <repeat name="results"> + <conditional name="software_cond"> + <param name="software" value="snippy"/> + <param name="input" value="snippy.txt"/> + </conditional> + </repeat> + <param name="title" value="Title of the report"/> + <param name="comment" value="Commment for the report"/> + <param name="flat" value="true"/> + <param name="export" value="true"/> + <output name="html_report"> + <assert_contents> + <has_text text="Title of the report"/> + <has_text text="Commment for the report"/> + <has_text text="Snippy-Core Alignment Statistics"/> + </assert_contents> + </output> + <output name="stats"> + <assert_contents> + <has_text text="snippy-Percent_Het"/> + <has_text text="snippy-HET"/> + <has_text text="700"/> + <has_text text="7.285714285714286"/> + <has_text text="a"/> + <has_n_lines n="5"/> + <has_n_columns n="6"/> + </assert_contents> + </output> + <output_collection name="plots" type="list" count="0"/> + </test> + </xml> +</macros>
--- a/template_plugin.xml Tue Feb 11 10:13:08 2025 +0000 +++ b/template_plugin.xml Tue Feb 18 23:18:25 2025 +0000 @@ -12,7 +12,7 @@ <token name="@TEMPLATE_COMMAND@"><![CDATA[ <!--This pattern is used to check the file content in the @CHECK_LN_FILE@ token. The pattern should be included in the file. --> #set $pattern = "Trimmomatic" - @LN_FILES@f + @LN_FILES@ ]]></token> <xml name="TEMPLATE_form"> <!-- Please add here your input forms specific to your plugin. Keep the name as `input` if you have a single input.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/bakta.txt Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,30 @@ +Sequence(s): +Length: 1330 +Count: 1 +GC: 45.2 +N50: 1330 +N ratio: 0.0 +coding density: 79.0 + +Annotation: +tRNAs: 0 +tmRNAs: 0 +rRNAs: 0 +ncRNAs: 0 +ncRNA regions: 0 +CRISPR arrays: 0 +CDSs: 2 +pseudogenes: 0 +hypotheticals: 1 +signal peptides: 0 +sORFs: 0 +gaps: 0 +oriCs: 0 +oriVs: 0 +oriTs: 1 + +Bakta: +Software: v1.9.4 +Database: v5.0, full +DOI: 10.1099/mgen.0.000685 +URL: github.com/oschwengers/bakta
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/bbduk.txt Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,26 @@ +Executing jgi.BBDuk [in=forward.fastq.gz, out=/data/jwd05e/main/079/061/79061727/outputs/dataset_1abda394-9c76-4c97-9712-e52be8f79694.dat, ref=dataset_5c3ad7b3-f75c-4f5a-a70e-15ae843bc97c.dat.fa, k=27, rcomp=t, maskmiddle=t, minkmerhits=1, minkmerfraction=0.0, mincovfraction=0.0, hammingdistance=0, qhdist=0, editdistance=0, forbidn=f, trimfailures=f, findbestmatch=f, skipr1=f, skipr2=f, t=1] +Version 39.08 + +Set threads to 1 +Changed from ASCII-33 to ASCII-64 on input quality B (Q33) for base N at lines 1 and 3, position 0 while prescanning. +Unspecified format for output /data/jwd05e/main/079/061/79061727/outputs/dataset_1abda394-9c76-4c97-9712-e52be8f79694.dat; defaulting to fastq. +0.398 seconds. +Initial: +Memory: max=3672m, total=270m, free=243m, used=27m + +Added 2970 kmers; time: 0.549 seconds. +Memory: max=3672m, total=270m, free=238m, used=32m + +Input is being processed as unpaired +Changed from ASCII-33 to ASCII-64 on input ;: 59 -> 28 +Started output streams: 0.052 seconds. +Processing time: 0.106 seconds. + +Input: 100 reads 10000 bases. +Contaminants: 0 reads (0.00%) 0 bases (0.00%) +Total Removed: 0 reads (0.00%) 0 bases (0.00%) +Result: 100 reads (100.00%) 10000 bases (100.00%) + +Time: 0.711 seconds. +Reads Processed: 100 0.14k reads/sec +Bases Processed: 10000 0.01m bases/sec
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/checkm.tabular Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,2 @@ +Bin Id Marker lineage # genomes # markers # marker sets 0 1 2 3 4 5+ Completeness Contamination Strain heterogeneity +637000110 f__Enterobacteriaceae (UID5103) 157 1005 324 1005 0 0 0 0 0 0.00 0.00 0.00
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/diamond.log Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,180 @@ +diamond blastp --quiet --threads 1 --db ./database --query /tmp/tmpxfb7idqd/files/e/4/f/dataset_e4f75201-863d-4397-8ca7-7c0b79593e9d.dat --no-self-hits --outfmt 0 --out /tmp/tmpxfb7idqd/job_working_directory/000/3/outputs/dataset_0fb25f52-9d9b-4592-a709-7e516f37daa1.dat --compress 0 --algo 0 --matrix BLOSUM62 --comp-based-stats 1 --masking 1 --max-target-seqs 25 --evalue 0.001 --id 0 --query-cover 0 --subject-cover 0 --block-size 2.0 --motif-masking 0 --log +diamond v2.0.15.153 +#CPU threads: 1 +Scoring parameters: (Matrix=BLOSUM62 Lambda=0.267 K=0.041 Penalties=11/1) +CPU features detected: ssse3 popcnt sse4.1 avx2 +Runtime dispatch: disabled +L3 cache size: 8388608 +MAX_SHAPE_LEN=19 SEQ_MASK STRICT_BAND +Temporary directory: /tmp/tmpxfb7idqd/job_working_directory/000/3/outputs +#Target sequences to report alignments for: 25 +DP fields: 1 +Opening the database... [0s] +Database: ./database.dmnd (type: Diamond database, sequences: 2, letters: 568) +Block size = 2000000000 +Opening the input file... [0s] +Opening the output file... [0s] +Loading query sequences... [0s] +Sequences = 2, letters = 566, average length = 283 +Masking queries... [0s] +Current RSS: 6.8 MB, Peak RSS: 6.8 MB +Algorithm: Double-indexed +Shape configuration: 111101110111,111011010010111 +Building query histograms... [0s] +Allocating buffers... [0s] +Current RSS: 6.9 MB, Peak RSS: 6.9 MB +Loading reference sequences... [0s] +Sequences = 2, letters = 568, average length = 284 +Current RSS: 6.9 MB, Peak RSS: 6.9 MB +Masking reference... [0s] +Masked letters: 0 +Initializing temporary storage... Async_buffer() 2,1 + [0s] +Building reference histograms... [0s] +Allocating buffers... [0s] +Current RSS: 6.9 MB, Peak RSS: 7.0 MB +Processing query block 1, reference block 1/1, shape 1/2, index chunk 1/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 97875695011120/566 (17292525620339.22%), reference seeds = 0/568 (0.00%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/57 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Processing query block 1, reference block 1/1, shape 1/2, index chunk 2/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 2560271741526742528/566 (452344830658435072.00%), reference seeds = 0/568 (0.00%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/57 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Processing query block 1, reference block 1/1, shape 1/2, index chunk 3/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 2560271741526742528/566 (452344830658435072.00%), reference seeds = 0/568 (0.00%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/65 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Processing query block 1, reference block 1/1, shape 1/2, index chunk 4/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 129/566 (22.79%), reference seeds = 107/568 (18.84%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/60 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Current RSS: 9.1 MB, Peak RSS: 9.2 MB +Processing query block 1, reference block 1/1, shape 2/2, index chunk 1/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 97875695011120/566 (17292525620339.22%), reference seeds = 107/568 (18.84%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/58 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Processing query block 1, reference block 1/1, shape 2/2, index chunk 2/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 2560271741526742528/566 (452344830658435072.00%), reference seeds = 107/568 (18.84%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/66 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Processing query block 1, reference block 1/1, shape 2/2, index chunk 3/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 2560271741526742528/566 (452344830658435072.00%), reference seeds = 107/568 (18.84%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/46 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Processing query block 1, reference block 1/1, shape 2/2, index chunk 4/4. +Building reference seed array... [0s] +Building query seed array... [0s] +Indexed query seeds = 120/566 (21.20%), reference seeds = 102/568 (17.96%) +Soft masked letters = 0/566 (0.00%), 0/568 (0.00%) +Computing hash join... [0s] +Masking low complexity seeds... [0s] +Masked seeds: 0/60 (0.00%) +Masked positions (query): 0/566 (0.00%) +Masked positions (target): 0/568 (0.00%) +Searching alignments... [0s] +Deallocating buffers... [0s] +Clearing query masking... [0s] +Computing alignments... Async_buffer.load() 17(2.37487e-07 GB, 1.4063e-07 GB on disk) +Loading trace points... [0s] +Sorting trace points... [0s] +Computing alignments... [0.01s] +Deallocating buffers... [0s] +Loading trace points... [0s] + [0.011s] +Deallocating reference... [0s] +Loading reference sequences... [0s] +Current RSS: 9.6 MB, Peak RSS: 9.6 MB +Deallocating buffers... [0s] +Current RSS: 9.6 MB, Peak RSS: 9.6 MB +Deallocating queries... [0s] +Loading query sequences... [0s] +Closing the input file... [0s] +Closing the output file... [0s] +Cleaning up... [0s] +Current RSS: 9.6 MB, Peak RSS: 9.6 MB +Total time = 0.093s +Hits (filter stage 0) = 774 +Hits (filter stage 1) = 774 (100 %) +Hits (filter stage 2) = 774 (100 %) +Hits (filter stage 3) = 17 (2.19638 %) +Target hits (stage 0) = 2 +Target hits (stage 1) = 0 +Target hits (stage 2) = 2 +Target hits (stage 3) = 2 (0 (0%) with CBS) +Target hits (stage 4) = 2 +Target hits (stage 5) = 2 +Swipe realignments = 0 +Matrix adjusts = 0 +Extensions (8 bit) = 0 +Extensions (16 bit) = 4 +Extensions (32 bit) = 0 +Hard queries = 0 +Gapped filter (targets) = 0 +Gapped filter (hits) stage 1 = 0 +Gapped filter (hits) stage 2 = 0 +Time (Load seed hit targets) = 4e-06s (CPU) +Time (Sort targets by score) = 0s (CPU) +Time (Gapped filter) = 0s (CPU) +Time (Matrix adjust) = 0s (CPU) +Time (Chaining) = 2e-05s (CPU) +Time (DP target sorting) = 0s (CPU) +Time (Smith Waterman) = 6.9e-05s (CPU) +Time (Smith Waterman TB) = 0.0001s (CPU) +Time (Traceback) = 8e-06s (CPU) +Time (Target parallel) = 0s (wall) +Time (Load seed hits) = 0.000495s (wall) +Time (Sort seed hits) = 2.4e-05s (wall) +Time (Extension) = 0.010185s (wall) +Temporary disk space used (search): 1.4063e-07 GB +Reported 2 pairwise alignments, 2 HSPs. +1 queries aligned.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/freyja.tsv Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,6 @@ + variants.tsv +summarized [('A', 0.5789470000000878), ('Delta', 0.4188134220012827)] +lineages A AY.48 B.1.617.2 A.4 A.2 +abundances 0.57475400 0.37892715 0.03988627 0.00313480 0.00105820 +resid 3.5081238846264213 +coverage 99.73246831421596
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/gtdbtk.tsv Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,2 @@ +user_genome classification closest_genome_reference closest_genome_reference_radius closest_genome_taxonomy closest_genome_ani closest_genome_af closest_placement_reference closest_placement_radius closest_placement_taxonomy closest_placement_ani closest_placement_af pplacer_taxonomy classification_method note other_related_references(genome_id,species_name,radius,ANI,AF) msa_percent translation_table red_value warnings +genome_1_fna_gz d__Archaea;p__Methanobacteriota;c__Methanobacteria;o__Methanobacteriales;f__Methanobacteriaceae;g__Methanobrevibacter;s__Methanobrevibacter ruminantium GCF_000024185.1 95.0 d__Archaea;p__Methanobacteriota;c__Methanobacteria;o__Methanobacteriales;f__Methanobacteriaceae;g__Methanobrevibacter;s__Methanobrevibacter ruminantium 100.0 1.0 GCF_000024185.1 95.0 d__Archaea;p__Methanobacteriota;c__Methanobacteria;o__Methanobacteriales;f__Methanobacteriaceae;g__Methanobrevibacter;s__Methanobrevibacter ruminantium 100.0 1.0 d__Archaea;p__Methanobacteriota;c__Methanobacteria;o__Methanobacteriales;f__Methanobacteriaceae;g__Methanobrevibacter;s__ taxonomic classification defined by topology and ANI topological placement and ANI have congruent species assignments N/A 97.56 11 N/A N/A
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/kraken_test0_report.tab Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,1 @@ +100.00 240 240 0 0 U 0 root
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/megahit.txt Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,143 @@ +2025-02-13 13:23:44 - MEGAHIT v1.2.9 +2025-02-13 13:23:44 - Using megahit_core with POPCNT and BMI2 support +2025-02-13 13:23:44 - Convert reads to binary library +2025-02-13 13:23:44 - command /usr/local/tools/_conda/envs/__megahit@1.2.9/bin/megahit_core buildlib /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/reads.lib /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/reads.lib +2025-02-13 13:23:44 - b'INFO sequence/io/sequence_lib.cpp : 75 - Lib 0 (/data/dnb10/galaxy_db/files/c/5/2/dataset_c52c6559-228d-4131-9eec-f5b8d04f08c8.dat): se, 1 reads, 1232 max length' +2025-02-13 13:23:44 - b'INFO utils/utils.h : 152 - Real: 0.2031\tuser: 0.0028\tsys: 0.0074\tmaxrss: 14696' +2025-02-13 13:23:44 - Start assembly. Number of CPU threads 10 +2025-02-13 13:23:44 - k list: 21,29,39,59,79,99,119,141 +2025-02-13 13:23:44 - Memory used: 83886080 +2025-02-13 13:23:44 - Extract solid (k+1)-mers for k = 21 +2025-02-13 13:23:44 - command /usr/local/tools/_conda/envs/__megahit@1.2.9/bin/megahit_core count -k 21 -m 2 --host_mem 83886080 --mem_flag 1 --output_prefix /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/k21/21 --num_cpu_threads 10 --read_lib_file /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/reads.lib +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 148 - Preparing data...' +2025-02-13 13:23:44 - b'INFO sequence/io/sequence_lib.cpp : 115 - Before reading, sizeof seq_package: 324' +2025-02-13 13:23:44 - b'INFO sequence/io/sequence_lib.cpp : 117 - After reading, sizeof seq_package: 324' +2025-02-13 13:23:44 - b'INFO sorting/kmer_counter.cpp : 76 - 1 reads, 1232 max read length' +2025-02-13 13:23:44 - b'INFO sorting/kmer_counter.cpp : 82 - 2 words per substring, 2 words per edge' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 153 - Preparing data... Done. Time elapsed: 0.0209' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 156 - Preparing partitions and calculating bucket sizes...' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 80 - Minimum memory required: 5243336 bytes' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 138 - Lv1 items: 161, Lv2 items: 30' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 139 - Memory of derived class: 5243252, Memory for Lv1+Lv2: 1124' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 165 - Preparing partitions and calculating bucket sizes... Done. Time elapsed: 0.0257' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 172 - Start main loop...' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 0 to 120' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0003' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0022' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 120 to 361' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0001' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0001' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 361 to 602' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0001' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0001' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 602 to 843' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0001' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0002' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 843 to 1084' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0001' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0002' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 1084 to 65536' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0027' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0031' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 204 - Main loop done. Time elapsed: 0.0096' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 207 - Postprocessing...' +2025-02-13 13:23:44 - b'INFO sorting/kmer_counter.cpp : 405 - Total number of candidate reads: 1 (1)' +2025-02-13 13:23:44 - b'INFO sorting/kmer_counter.cpp : 407 - Total number of solid edges: 26' +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 210 - Postprocess done. Time elapsed: 0.0595' +2025-02-13 13:23:44 - b'INFO utils/utils.h : 152 - Real: 0.1204\tuser: 0.3707\tsys: 0.0656\tmaxrss: 30296' +2025-02-13 13:23:44 - Build graph for k = 21 +2025-02-13 13:23:44 - command /usr/local/tools/_conda/envs/__megahit@1.2.9/bin/megahit_core seq2sdbg --host_mem 83886080 --mem_flag 1 --output_prefix /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/k21/21 --num_cpu_threads 10 -k 21 --kmer_from 0 --input_prefix /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/k21/21 --need_mercy +2025-02-13 13:23:44 - b'INFO sorting/base_engine.cpp : 148 - Preparing data...' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 369 - Number edges: 26' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 413 - Bases to reserve: 704, number contigs: 0, number multiplicity: 32' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 421 - Before reading, sizeof seq_package: 184, multiplicity vector: 32' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 428 - Read 26 edges.' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 429 - After reading, sizeof seq_package: 184/26/572, multiplicity vector: 26/32' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 440 - Adding mercy edges...' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 191 - Read 1 reads to search for mercy k-mers' +2025-02-13 13:23:44 - b'INFO sorting/seq_to_sdbg.cpp : 355 - Number of reads: 1, Number of mercy edges: 529' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 444 - Done. Time elapsed: 0.2585' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 445 - After adding mercy, sizeof seq_package: 5640/555/12210, multiplicity vector: 555/555' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 506 - Finally, sizeof seq_package: 5640/555/12210, multiplicity vector: 555/555' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 153 - Preparing data... Done. Time elapsed: 0.3852' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 156 - Preparing partitions and calculating bucket sizes...' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 80 - Minimum memory required: 7022 bytes' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 138 - Lv1 items: 444, Lv2 items: 90' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 139 - Memory of derived class: 6870, Memory for Lv1+Lv2: 2496' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 165 - Preparing partitions and calculating bucket sizes... Done. Time elapsed: 0.0129' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 172 - Start main loop...' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 0 to 167' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0001' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0005' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 167 to 355' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0001' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0001' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 355 to 543' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0001' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 543 to 731' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0001' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 731 to 919' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0002' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 185 - Lv1 scanning from bucket 919 to 65536' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 192 - Lv1 scanning done. Large diff: 0. Time elapsed: 0.0026' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 198 - Lv1 fetching & sorting done. Time elapsed: 0.0024' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 204 - Main loop done. Time elapsed: 0.0066' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 207 - Postprocessing...' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 793 - Number of $ A C G T A- C- G- T-:' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 794 - 0 253 302 302 253 0 0 0 0' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 800 - Total number of edges: 1110' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 801 - Total number of ONEs: 1110' +2025-02-13 13:23:45 - b'INFO sorting/seq_to_sdbg.cpp : 802 - Total number of $v edges: 0' +2025-02-13 13:23:45 - b'INFO sorting/base_engine.cpp : 210 - Postprocess done. Time elapsed: 0.1141' +2025-02-13 13:23:45 - b'INFO utils/utils.h : 152 - Real: 0.5262\tuser: 0.5163\tsys: 0.3042\tmaxrss: 269456' +2025-02-13 13:23:45 - Assemble contigs from SdBG for k = 21 +2025-02-13 13:23:45 - command /usr/local/tools/_conda/envs/__megahit@1.2.9/bin/megahit_core assemble -s /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/k21/21 -o /data/jwd02f/main/079/102/79102477/working/megahit_out/intermediate_contigs/k21 -t 10 --min_standalone 300 --prune_level 2 --merge_len 20 --merge_similar 0.95 --cleaning_rounds 5 --disconnect_ratio 0.1 --low_local_ratio 0.2 --cleaning_rounds 5 --min_depth 2.0 --bubble_level 2 --max_tip_len -1 --careful_bubble +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 129 - Loading succinct de Bruijn graph: /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/k21/21Done. Time elapsed: 0.148410' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 133 - Number of Edges: 1110; K value: 21' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 140 - Number of CPU threads: 10' +2025-02-13 13:23:45 - b'INFO assembly/sdbg_pruning.cpp : 160 - Removing tips with length less than 2; Accumulated tips removed: 0; time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO assembly/sdbg_pruning.cpp : 160 - Removing tips with length less than 4; Accumulated tips removed: 0; time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO assembly/sdbg_pruning.cpp : 160 - Removing tips with length less than 8; Accumulated tips removed: 0; time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO assembly/sdbg_pruning.cpp : 160 - Removing tips with length less than 16; Accumulated tips removed: 0; time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO assembly/sdbg_pruning.cpp : 160 - Removing tips with length less than 32; Accumulated tips removed: 0; time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO assembly/sdbg_pruning.cpp : 169 - Removing tips with length less than 42; Accumulated tips removed: 0; time elapsed: 0.0000' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 158 - Tips removal done! Time elapsed(sec): 0.002' +2025-02-13 13:23:45 - b'INFO assembly/unitig_graph.cpp : 83 - Graph size without loops: 0, palindrome: 0' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 166 - unitig graph size: 1, time for building: 0.002' +2025-02-13 13:23:45 - b'INFO assembly/contig_stat.h : 40 - Max: 576, Min: 576, N50: 576, number contigs: 1, number isolated: 1, number looped: 1, total size: 576,' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 184 - Graph cleaning round 1' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 200 - Number of bubbles removed: 0, Time elapsed(sec): 0.000' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 210 - Number of complex bubbles removed: 0, Time elapsed(sec): 0.000024' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 221 - Number unitigs disconnected: 0, time: 0.000' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 245 - Unitigs removed in excessive pruning: 0, time: 0.000' +2025-02-13 13:23:45 - b'INFO assembly/contig_stat.h : 40 - Max: 576, Min: 576, N50: 576, number contigs: 1, number isolated: 1, number looped: 1, total size: 576,' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 267 - Time to output: 0.000192' +2025-02-13 13:23:45 - b'INFO main_assemble.cpp : 286 - Number of local low depth unitigs removed: 0, complex bubbles removed: 0, time: 0.000034' +2025-02-13 13:23:45 - b'INFO assembly/contig_stat.h : 40 - Max: 576, Min: 576, N50: 576, number contigs: 1, number isolated: 1, number looped: 1, total size: 576,' +2025-02-13 13:23:45 - b'INFO utils/utils.h : 152 - Real: 0.1675\tuser: 0.2808\tsys: 0.0330\tmaxrss: 22464' +2025-02-13 13:23:45 - Local assembly for k = 21 +2025-02-13 13:23:45 - command /usr/local/tools/_conda/envs/__megahit@1.2.9/bin/megahit_core local -c /data/jwd02f/main/079/102/79102477/working/megahit_out/intermediate_contigs/k21.contigs.fa -l /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/reads.lib -t 10 -o /data/jwd02f/main/079/102/79102477/working/megahit_out/intermediate_contigs/k21.local.fa --kmax 29 +2025-02-13 13:23:45 - b'INFO localasm/hash_mapper.cpp : 99 - Number of contigs: 0, index size: 0' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 315 - Hash mapper construction time elapsed: 0.003884' +2025-02-13 13:23:45 - b'INFO sequence/io/sequence_lib.cpp : 115 - Before reading, sizeof seq_package: 324' +2025-02-13 13:23:45 - b'INFO sequence/io/sequence_lib.cpp : 117 - After reading, sizeof seq_package: 324' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 324 - Read lib time elapsed: 0.001268' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 330 - Insert size estimation time elapsed: 0.000001' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 218 - Lib 0: total 1 reads, aligned 0, added 0 reads to local assembly' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 338 - Mapping time elapsed: 0.000047' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 232 - Minimum number of reads to do local assembly: 0' +2025-02-13 13:23:45 - b'INFO localasm/local_assemble.cpp : 346 - Local assembly time elapsed: 0.004100' +2025-02-13 13:23:45 - b'INFO utils/utils.h : 152 - Real: 0.0094\tuser: 0.0553\tsys: 0.0074\tmaxrss: 14696' +2025-02-13 13:23:45 - Extract iterative edges from k = 21 to 29 +2025-02-13 13:23:45 - command /usr/local/tools/_conda/envs/__megahit@1.2.9/bin/megahit_core iterate -c /data/jwd02f/main/079/102/79102477/working/megahit_out/intermediate_contigs/k21.contigs.fa -b /data/jwd02f/main/079/102/79102477/working/megahit_out/intermediate_contigs/k21.bubble_seq.fa -t 10 -k 21 -s 8 -o /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/k29/29 -r /data/jwd02f/main/079/102/79102477/working/megahit_out/tmp/reads.lib.bin +2025-02-13 13:23:45 - b'INFO main_iterate.cpp : 190 - Selected kmer type size for k: 8' +2025-02-13 13:23:45 - b'INFO main_iterate.cpp : 123 - Selected kmer type size for next k: 8' +2025-02-13 13:23:45 - b'INFO main_iterate.cpp : 138 - Processed: 1, aligned: 0. Iterative edges: 0' +2025-02-13 13:23:45 - b'INFO main_iterate.cpp : 142 - Total: 1, aligned: 0. Iterative edges: 0' +2025-02-13 13:23:45 - b'INFO utils/utils.h : 152 - Real: 0.0136\tuser: 0.0433\tsys: 0.0101\tmaxrss: 14696' +2025-02-13 13:23:45 - Merging to output final contigs +2025-02-13 13:23:45 - 1 contigs, total 576 bp, min 576 bp, max 576 bp, avg 576 bp, N50 576 bp +2025-02-13 13:23:45 - ALL DONE. Time elapsed: 1.490756 seconds
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/metaphlan.txt Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,31 @@ +#custom_db +#mpa_v21_CHOCOPhlAnxxx_2 +#/home/bebatut/miniconda3/envs/mulled-v1-b4915a464cf72db4053ec566c65e3f5f431691323f08f9b6b1c9ecfc4f8b9c88/bin/metaphlan in --input_type fasta --read_min_len 70 --bowtie2db ref_db/ --index custom_db --bt2_ps very-sensitive --min_mapq_val 5 -t rel_ab --tax_lev a --min_cu_len 2000 --add_viruses --stat_q 0.2 --perc_nonzero 0.33 --avoid_disqm --sample_id_key SampleID --sample_id Metaphlan_Analysis -o /tmp/tmptu3575j7/files/000/dataset_19.dat --bowtie2out bowtie2out -s /tmp/tmptu3575j7/files/000/dataset_21.dat --biom /tmp/tmptu3575j7/files/000/dataset_22.dat --nproc 1 +#SampleID Metaphlan_Analysis +#clade_name NCBI_tax_id relative_abundance additional_species +k__Bacteria 2 100.0 +k__Bacteria|p__Proteobacteria 2|1224 52.20019 +k__Bacteria|p__Actinobacteria 2|201174 34.37371 +k__Bacteria|p__Firmicutes 2|1239 13.4261 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria 2|1224|1236 52.20019 +k__Bacteria|p__Actinobacteria|c__Actinobacteria 2|201174|1760 34.37371 +k__Bacteria|p__Firmicutes|c__Bacilli 2|1239|91061 13.4261 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales 2|1224|1236|72274 52.20019 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales 2|201174|1760|85007 24.7409 +k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales 2|1239|91061|186826 13.4261 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Propionibacteriales 2|201174|1760|85009 9.63281 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae 2|1224|1236|72274|468 52.20019 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae 2|201174|1760|85007|1653 24.7409 +k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Carnobacteriaceae 2|1239|91061|186826|186828 13.4261 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Propionibacteriales|f__Propionibacteriaceae 2|201174|1760|85009|31957 9.63281 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella 2|1224|1236|72274|468|475 52.20019 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium 2|201174|1760|85007|1653|1716 24.7409 +k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Carnobacteriaceae|g__Dolosigranulum 2|1239|91061|186826|186828|29393 13.4261 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Propionibacteriales|f__Propionibacteriaceae|g__Cutibacterium 2|201174|1760|85009|31957|1912216 9.63281 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_lacunata 2|1224|1236|72274|468|475|477 22.57968 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_pseudodiphtheriticum 2|201174|1760|85007|1653|1716|37637 18.75365 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_nonliquefaciens 2|1224|1236|72274|468|475|478 15.88652 +k__Bacteria|p__Proteobacteria|c__Gammaproteobacteria|o__Pseudomonadales|f__Moraxellaceae|g__Moraxella|s__Moraxella_equi 2|1224|1236|72274|468|475|60442 13.73399 +k__Bacteria|p__Firmicutes|c__Bacilli|o__Lactobacillales|f__Carnobacteriaceae|g__Dolosigranulum|s__Dolosigranulum_pigrum 2|1239|91061|186826|186828|29393|29394 13.4261 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Propionibacteriales|f__Propionibacteriaceae|g__Cutibacterium|s__Cutibacterium_acnes 2|201174|1760|85009|31957|1912216|1747 9.63281 +k__Bacteria|p__Actinobacteria|c__Actinobacteria|o__Corynebacteriales|f__Corynebacteriaceae|g__Corynebacterium|s__Corynebacterium_accolens 2|201174|1760|85007|1653|1716|38284 5.98726
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/nonpareil.json Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,2194 @@ +{ + "test.fasta": { + "file": "test.fasta", + "label": "test.fasta", + "col": "#79756B", + "L": 88.496, + "AL": 88.496, + "R": 500, + "LR": 44248, + "overlap": 50, + "ksize": [ + + ], + "log.sample": 0.7, + "kernel": "alignment", + "version": "3.5.5", + "kappa": 0.2128, + "C": 0.2431, + "consistent": true, + "star": 95, + "has.model": true, + "warning": [ + + ], + "LRstar": 24276420.6735, + "modelR": 0.9977, + "diversity": 11.9521, + "x.obs": [ + 0, + 2, + 2, + 3, + 5, + 7, + 10, + 14, + 20, + 29, + 41, + 59, + 84, + 120, + 171, + 245, + 350, + 500 + ], + "x.adj": [ + 0, + 1021.2669, + 1021.2669, + 1346.8936, + 1908.7977, + 2401.6077, + 3063.6067, + 3854.5631, + 4917.0668, + 6336.5164, + 8025.9965, + 10289.4237, + 13095.2993, + 16704.9959, + 21273.3215, + 27191.4116, + 34686.6773, + 44248 + ], + "y.red": [ + 0, + 0, + 0.0012, + 0.0046, + 0.006, + 0.0075, + 0.0146, + 0.0231, + 0.0329, + 0.0439, + 0.0585, + 0.0786, + 0.0989, + 0.1216, + 0.1432, + 0.1679, + 0.1914, + 0.2128 + ], + "y.cov": [ + 0, + 0, + 0.0022, + 0.0073, + 0.0093, + 0.0114, + 0.021, + 0.032, + 0.0441, + 0.0575, + 0.0747, + 0.0978, + 0.1206, + 0.1457, + 0.1692, + 0.1957, + 0.2206, + 0.2431 + ], + "y.sd": [ + 0, + 0, + 0.0432, + 0.0518, + 0.062, + 0.0512, + 0.0584, + 0.0619, + 0.0609, + 0.0567, + 0.0556, + 0.0513, + 0.0476, + 0.0437, + 0.0365, + 0.0306, + 0.0237, + 0.0135 + ], + "y.p25": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0.0409, + 0.0657, + 0.0933, + 0.1208, + 0.1494, + 0.1802, + 0.209, + 0.2368 + ], + "y.p50": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0.0547, + 0.0527, + 0.0937, + 0.1173, + 0.1241, + 0.1667, + 0.1944, + 0.2204, + 0.2423 + ], + "y.p75": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0, + 0.0793, + 0.0868, + 0.1058, + 0.1241, + 0.147, + 0.1702, + 0.1889, + 0.2115, + 0.232, + 0.2504 + ], + "x.model": [ + 1000, + 1006.0155, + 1012.0672, + 1018.1552, + 1024.2799, + 1030.4415, + 1036.6401, + 1042.876, + 1049.1494, + 1055.4605, + 1061.8096, + 1068.1969, + 1074.6226, + 1081.087, + 1087.5902, + 1094.1326, + 1100.7144, + 1107.3357, + 1113.9969, + 1120.6981, + 1127.4396, + 1134.2217, + 1141.0446, + 1147.9085, + 1154.8138, + 1161.7605, + 1168.7491, + 1175.7797, + 1182.8525, + 1189.968, + 1197.1262, + 1204.3275, + 1211.5721, + 1218.8603, + 1226.1923, + 1233.5685, + 1240.989, + 1248.4541, + 1255.9642, + 1263.5194, + 1271.1201, + 1278.7665, + 1286.4589, + 1294.1976, + 1301.9828, + 1309.8148, + 1317.694, + 1325.6206, + 1333.5948, + 1341.617, + 1349.6875, + 1357.8065, + 1365.9744, + 1374.1914, + 1382.4578, + 1390.774, + 1399.1402, + 1407.5567, + 1416.0238, + 1424.5419, + 1433.1112, + 1441.732, + 1450.4047, + 1459.1296, + 1467.907, + 1476.7372, + 1485.6204, + 1494.5572, + 1503.5477, + 1512.5922, + 1521.6912, + 1530.8449, + 1540.0537, + 1549.3178, + 1558.6377, + 1568.0137, + 1577.446, + 1586.9351, + 1596.4813, + 1606.0849, + 1615.7463, + 1625.4658, + 1635.2438, + 1645.0805, + 1654.9765, + 1664.932, + 1674.9474, + 1685.023, + 1695.1592, + 1705.3564, + 1715.6149, + 1725.9352, + 1736.3175, + 1746.7623, + 1757.2699, + 1767.8408, + 1778.4752, + 1789.1736, + 1799.9363, + 1810.7638, + 1821.6564, + 1832.6145, + 1843.6386, + 1854.729, + 1865.8861, + 1877.1103, + 1888.402, + 1899.7617, + 1911.1896, + 1922.6864, + 1934.2523, + 1945.8877, + 1957.5932, + 1969.369, + 1981.2157, + 1993.1337, + 2005.1234, + 2017.1852, + 2029.3195, + 2041.5268, + 2053.8076, + 2066.1623, + 2078.5912, + 2091.0949, + 2103.6739, + 2116.3285, + 2129.0592, + 2141.8666, + 2154.7509, + 2167.7128, + 2180.7526, + 2193.8709, + 2207.0681, + 2220.3447, + 2233.7011, + 2247.1379, + 2260.6555, + 2274.2545, + 2287.9352, + 2301.6982, + 2315.5441, + 2329.4732, + 2343.4861, + 2357.5833, + 2371.7653, + 2386.0326, + 2400.3857, + 2414.8252, + 2429.3516, + 2443.9653, + 2458.6669, + 2473.457, + 2488.336, + 2503.3046, + 2518.3632, + 2533.5123, + 2548.7526, + 2564.0846, + 2579.5088, + 2595.0258, + 2610.6361, + 2626.3404, + 2642.1391, + 2658.0328, + 2674.0222, + 2690.1077, + 2706.29, + 2722.5696, + 2738.9472, + 2755.4233, + 2771.9985, + 2788.6734, + 2805.4486, + 2822.3248, + 2839.3024, + 2856.3822, + 2873.5647, + 2890.8506, + 2908.2404, + 2925.7349, + 2943.3346, + 2961.0402, + 2978.8523, + 2996.7715, + 3014.7985, + 3032.934, + 3051.1786, + 3069.5329, + 3087.9976, + 3106.5734, + 3125.2609, + 3144.0609, + 3162.9739, + 3182.0008, + 3201.142, + 3220.3984, + 3239.7707, + 3259.2595, + 3278.8655, + 3298.5895, + 3318.4321, + 3338.394, + 3358.4761, + 3378.6789, + 3399.0033, + 3419.45, + 3440.0196, + 3460.713, + 3481.5309, + 3502.4739, + 3523.543, + 3544.7388, + 3566.0621, + 3587.5137, + 3609.0944, + 3630.8048, + 3652.6458, + 3674.6183, + 3696.7229, + 3718.9604, + 3741.3318, + 3763.8377, + 3786.479, + 3809.2565, + 3832.171, + 3855.2234, + 3878.4144, + 3901.7449, + 3925.2158, + 3948.8279, + 3972.582, + 3996.479, + 4020.5198, + 4044.7051, + 4069.036, + 4093.5132, + 4118.1376, + 4142.9102, + 4167.8318, + 4192.9034, + 4218.1257, + 4243.4998, + 4269.0265, + 4294.7067, + 4320.5415, + 4346.5316, + 4372.6781, + 4398.9818, + 4425.4438, + 4452.065, + 4478.8464, + 4505.7888, + 4532.8933, + 4560.1608, + 4587.5924, + 4615.189, + 4642.9516, + 4670.8811, + 4698.9788, + 4727.2454, + 4755.682, + 4784.2898, + 4813.0696, + 4842.0225, + 4871.1496, + 4900.4519, + 4929.9305, + 4959.5864, + 4989.4207, + 5019.4345, + 5049.6288, + 5080.0048, + 5110.5635, + 5141.306, + 5172.2334, + 5203.3469, + 5234.6475, + 5266.1365, + 5297.8148, + 5329.6837, + 5361.7444, + 5393.9978, + 5426.4453, + 5459.088, + 5491.9271, + 5524.9637, + 5558.199, + 5591.6342, + 5625.2706, + 5659.1093, + 5693.1516, + 5727.3987, + 5761.8517, + 5796.5121, + 5831.3809, + 5866.4595, + 5901.749, + 5937.2509, + 5972.9663, + 6008.8966, + 6045.043, + 6081.4069, + 6117.9895, + 6154.7921, + 6191.8162, + 6229.063, + 6266.5338, + 6304.23, + 6342.153, + 6380.3041, + 6418.6847, + 6457.2962, + 6496.14, + 6535.2174, + 6574.5299, + 6614.0788, + 6653.8657, + 6693.8919, + 6734.1589, + 6774.6681, + 6815.421, + 6856.4191, + 6897.6637, + 6939.1565, + 6980.8989, + 7022.8924, + 7065.1385, + 7107.6387, + 7150.3946, + 7193.4076, + 7236.6795, + 7280.2116, + 7324.0056, + 7368.063, + 7412.3855, + 7456.9745, + 7501.8318, + 7546.959, + 7592.3576, + 7638.0293, + 7683.9757, + 7730.1985, + 7776.6994, + 7823.48, + 7870.542, + 7917.8871, + 7965.517, + 8013.4335, + 8061.6381, + 8110.1328, + 8158.9192, + 8207.999, + 8257.3741, + 8307.0462, + 8357.0171, + 8407.2885, + 8457.8624, + 8508.7406, + 8559.9248, + 8611.4168, + 8663.2187, + 8715.3321, + 8767.759, + 8820.5013, + 8873.5609, + 8926.9397, + 8980.6395, + 9034.6624, + 9089.0103, + 9143.685, + 9198.6887, + 9254.0233, + 9309.6907, + 9365.693, + 9422.0321, + 9478.7102, + 9535.7292, + 9593.0912, + 9650.7983, + 9708.8525, + 9767.256, + 9826.0107, + 9885.1189, + 9944.5827, + 10004.4042, + 10064.5855, + 10125.1288, + 10186.0364, + 10247.3103, + 10308.9528, + 10370.9661, + 10433.3525, + 10496.1141, + 10559.2533, + 10622.7723, + 10686.6735, + 10750.959, + 10815.6312, + 10880.6924, + 10946.145, + 11011.9914, + 11078.2338, + 11144.8747, + 11211.9165, + 11279.3616, + 11347.2124, + 11415.4714, + 11484.141, + 11553.2236, + 11622.7218, + 11692.6381, + 11762.975, + 11833.735, + 11904.9206, + 11976.5344, + 12048.5791, + 12121.0571, + 12193.9711, + 12267.3237, + 12341.1176, + 12415.3554, + 12490.0397, + 12565.1734, + 12640.7589, + 12716.7992, + 12793.2969, + 12870.2548, + 12947.6756, + 13025.5621, + 13103.9171, + 13182.7435, + 13262.0441, + 13341.8217, + 13422.0792, + 13502.8195, + 13584.0454, + 13665.76, + 13747.9662, + 13830.6668, + 13913.865, + 13997.5636, + 14081.7657, + 14166.4743, + 14251.6925, + 14337.4233, + 14423.6698, + 14510.4351, + 14597.7224, + 14685.5348, + 14773.8754, + 14862.7473, + 14952.1539, + 15042.0984, + 15132.5839, + 15223.6137, + 15315.191, + 15407.3193, + 15500.0018, + 15593.2418, + 15687.0426, + 15781.4078, + 15876.3406, + 15971.8444, + 16067.9228, + 16164.5791, + 16261.8168, + 16359.6395, + 16458.0506, + 16557.0538, + 16656.6524, + 16756.8502, + 16857.6508, + 16959.0577, + 17061.0746, + 17163.7052, + 17266.9532, + 17370.8222, + 17475.3161, + 17580.4386, + 17686.1934, + 17792.5844, + 17899.6154, + 18007.2902, + 18115.6128, + 18224.5869, + 18334.2166, + 18444.5058, + 18555.4584, + 18667.0784, + 18779.3699, + 18892.3369, + 19005.9834, + 19120.3136, + 19235.3315, + 19351.0413, + 19467.4472, + 19584.5533, + 19702.3638, + 19820.883, + 19940.1152, + 20060.0646, + 20180.7356, + 20302.1325, + 20424.2596, + 20547.1214, + 20670.7222, + 20795.0666, + 20920.159, + 21046.0038, + 21172.6057, + 21299.9692, + 21428.0988, + 21556.9991, + 21686.6749, + 21817.1307, + 21948.3713, + 22080.4013, + 22213.2256, + 22346.8489, + 22481.2759, + 22616.5117, + 22752.5609, + 22889.4286, + 23027.1195, + 23165.6388, + 23304.9913, + 23445.182, + 23586.2161, + 23728.0986, + 23870.8346, + 24014.4292, + 24158.8875, + 24304.2149, + 24450.4165, + 24597.4976, + 24745.4634, + 24894.3193, + 25044.0706, + 25194.7228, + 25346.2812, + 25498.7514, + 25652.1387, + 25806.4487, + 25961.6869, + 26117.859, + 26274.9705, + 26433.0272, + 26592.0346, + 26751.9985, + 26912.9247, + 27074.8189, + 27237.687, + 27401.5349, + 27566.3683, + 27732.1933, + 27899.0159, + 28066.8419, + 28235.6775, + 28405.5288, + 28576.4017, + 28748.3026, + 28921.2375, + 29095.2127, + 29270.2345, + 29446.3091, + 29623.4428, + 29801.6421, + 29980.9134, + 30161.2631, + 30342.6976, + 30525.2236, + 30708.8476, + 30893.5761, + 31079.4159, + 31266.3736, + 31454.4559, + 31643.6696, + 31834.0216, + 32025.5186, + 32218.1676, + 32411.9754, + 32606.9491, + 32803.0956, + 33000.4221, + 33198.9355, + 33398.6432, + 33599.5521, + 33801.6697, + 34005.003, + 34209.5595, + 34415.3465, + 34622.3715, + 34830.6417, + 35040.1649, + 35250.9484, + 35462.9999, + 35676.3269, + 35890.9373, + 36106.8386, + 36324.0386, + 36542.5453, + 36762.3663, + 36983.5097, + 37205.9834, + 37429.7953, + 37654.9536, + 37881.4663, + 38109.3416, + 38338.5877, + 38569.2128, + 38801.2253, + 39034.6334, + 39269.4456, + 39505.6702, + 39743.3159, + 39982.3911, + 40222.9045, + 40464.8647, + 40708.2804, + 40953.1604, + 41199.5134, + 41447.3484, + 41696.6742, + 41947.4998, + 42199.8343, + 42453.6866, + 42709.0661, + 42965.9817, + 43224.4428, + 43484.4587, + 43746.0387, + 44009.1923, + 44273.9288, + 44540.2579, + 44808.189, + 45077.7319, + 45348.8963, + 45621.6918, + 45896.1283, + 46172.2156, + 46449.9638, + 46729.3828, + 47010.4826, + 47293.2733, + 47577.7652, + 47863.9684, + 48151.8933, + 48441.5502, + 48732.9495, + 49026.1017, + 49321.0174, + 49617.7071, + 49916.1816, + 50216.4515, + 50518.5277, + 50822.421, + 51128.1424, + 51435.7029, + 51745.1135, + 52056.3853, + 52369.5296, + 52684.5576, + 53001.4807, + 53320.3101, + 53641.0576, + 53963.7344, + 54288.3523, + 54614.923, + 54943.4581, + 55273.9695, + 55606.4692, + 55940.9689, + 56277.4808, + 56616.0171, + 56956.5897, + 57299.2111, + 57643.8935, + 57990.6494, + 58339.4911, + 58690.4314, + 59043.4826, + 59398.6577, + 59755.9693, + 60115.4303, + 60477.0536, + 60840.8523, + 61206.8394, + 61575.0281, + 61945.4316, + 62318.0633, + 62692.9365, + 63070.0648, + 63449.4617, + 63831.1408, + 64215.116, + 64601.4009, + 64990.0095, + 65380.9558, + 65774.2538, + 66169.9177, + 66567.9617, + 66968.4001, + 67371.2474, + 67776.518, + 68184.2265, + 68594.3875, + 69007.0159, + 69422.1264, + 69839.734, + 70259.8537, + 70682.5006, + 71107.69, + 71535.4371, + 71965.7573, + 72398.6661, + 72834.179, + 73272.3117, + 73713.0801, + 74156.4998, + 74602.587, + 75051.3576, + 75502.8277, + 75957.0137, + 76413.9318, + 76873.5985, + 77336.0303, + 77801.2438, + 78269.2559, + 78740.0832, + 79213.7429, + 79690.2518, + 80169.6271, + 80651.8861, + 81137.0461, + 81625.1246, + 82116.1392, + 82610.1074, + 83107.0471, + 83606.9761, + 84109.9124, + 84615.8742, + 85124.8795, + 85636.9467, + 86152.0943, + 86670.3408, + 87191.7047, + 87716.2049, + 88243.8602, + 88774.6896, + 89308.7123, + 89845.9473, + 90386.414, + 90930.132, + 91477.1206, + 92027.3996, + 92580.9889, + 93137.9082, + 93698.1777, + 94261.8175, + 94828.8478, + 95399.2891, + 95973.1619, + 96550.4868, + 97131.2846, + 97715.5762, + 98303.3825, + 98894.7248, + 99489.6244, + 100088.1025, + 100690.1807, + 101295.8808, + 101905.2244, + 102518.2335, + 103134.9302, + 103755.3366, + 104379.4751, + 105007.368, + 105639.038, + 106274.5078, + 106913.8003, + 107556.9384, + 108203.9453, + 108854.8443, + 109509.6588, + 110168.4122, + 110831.1284, + 111497.8312, + 112168.5444, + 112843.2924, + 113522.0993, + 114204.9895, + 114891.9877, + 115583.1184, + 116278.4067, + 116977.8774, + 117681.5559, + 118389.4672, + 119101.637, + 119818.0909, + 120538.8545, + 121263.9539, + 121993.4152, + 122727.2645, + 123465.5282, + 124208.233, + 124955.4055, + 125707.0726, + 126463.2613, + 127223.9989, + 127989.3126, + 128759.2301, + 129533.7791, + 130312.9873, + 131096.8828, + 131885.4939, + 132678.8488, + 133476.9761, + 134279.9046, + 135087.663, + 135900.2805, + 136717.7863, + 137540.2098, + 138367.5806, + 139199.9284, + 140037.2832, + 140879.675, + 141727.1343, + 142579.6914, + 143437.3771, + 144300.2222, + 145168.2577, + 146041.5148, + 146920.0251, + 147803.82, + 148692.9313, + 149587.3911, + 150487.2314, + 151392.4848, + 152303.1837, + 153219.3609, + 154141.0493, + 155068.2821, + 156001.0927, + 156939.5146, + 157883.5815, + 158833.3275, + 159788.7866, + 160749.9933, + 161716.9822, + 162689.7879, + 163668.4455, + 164652.9902, + 165643.4575, + 166639.8828, + 167642.3022, + 168650.7516, + 169665.2672, + 170685.8857, + 171712.6438, + 172745.5782, + 173784.7263, + 174830.1253, + 175881.8129, + 176939.8269, + 178004.2054, + 179074.9866, + 180152.2091, + 181235.9117, + 182326.1332, + 183422.9129, + 184526.2903, + 185636.305, + 186752.997, + 187876.4064, + 189006.5737, + 190143.5395, + 191287.3447, + 192438.0304, + 193595.6381, + 194760.2093, + 195931.786, + 197110.4103, + 198296.1246, + 199488.9715, + 200688.994, + 201896.2352, + 203110.7385, + 204332.5476, + 205561.7066, + 206798.2595, + 208042.2508, + 209293.7254, + 210552.7282, + 211819.3045, + 213093.4999, + 214375.3602, + 215664.9315, + 216962.2602, + 218267.3929, + 219580.3767, + 220901.2586, + 222230.0864, + 223566.9076, + 224911.7705, + 226264.7234, + 227625.8149, + 228995.0941, + 230372.6102, + 231758.4126, + 233152.5514, + 234555.0765, + 235966.0386, + 237385.4882, + 238813.4765, + 240250.0549, + 241695.275, + 243149.1887, + 244611.8485, + 246083.3069, + 247563.6168, + 249052.8314, + 250551.0045, + 252058.1897, + 253574.4414, + 255099.8141, + 256634.3626, + 258178.1422, + 259731.2084, + 261293.617, + 262865.4243, + 264446.6867, + 266037.4612, + 267637.805, + 269247.7756, + 270867.431, + 272496.8293, + 274136.0293, + 275785.0899, + 277444.0703, + 279113.0304, + 280792.03, + 282481.1296, + 284180.39, + 285889.8722, + 287609.6379, + 289339.7487, + 291080.267, + 292831.2553, + 294592.7767, + 296364.8945, + 298147.6724, + 299941.1746, + 301745.4655, + 303560.6102, + 305386.6738, + 307223.7221, + 309071.8211, + 310931.0373, + 312801.4377, + 314683.0893, + 316576.06, + 318480.4179, + 320396.2313, + 322323.5694, + 324262.5012, + 326213.0967, + 328175.426, + 330149.5596, + 332135.5686, + 334133.5244, + 336143.4989, + 338165.5643, + 340199.7935, + 342246.2595, + 344305.036, + 346376.197, + 348459.817, + 350555.9711, + 352664.7345, + 354786.1831, + 356920.3933, + 359067.4418, + 361227.4058, + 363400.363, + 365586.3917, + 367785.5703, + 369997.9781, + 372223.6946, + 374462.7998, + 376715.3743, + 378981.4992, + 381261.2559, + 383554.7264, + 385861.9932, + 388183.1394, + 390518.2484, + 392867.4042, + 395230.6913, + 397608.1947, + 400000 + ], + "y.model": [ + 0.0056, + 0.0056, + 0.0057, + 0.0058, + 0.0058, + 0.0059, + 0.0059, + 0.006, + 0.0061, + 0.0061, + 0.0062, + 0.0062, + 0.0063, + 0.0064, + 0.0064, + 0.0065, + 0.0065, + 0.0066, + 0.0067, + 0.0067, + 0.0068, + 0.0069, + 0.0069, + 0.007, + 0.0071, + 0.0071, + 0.0072, + 0.0073, + 0.0073, + 0.0074, + 0.0075, + 0.0076, + 0.0076, + 0.0077, + 0.0078, + 0.0078, + 0.0079, + 0.008, + 0.0081, + 0.0081, + 0.0082, + 0.0083, + 0.0084, + 0.0084, + 0.0085, + 0.0086, + 0.0087, + 0.0088, + 0.0088, + 0.0089, + 0.009, + 0.0091, + 0.0092, + 0.0093, + 0.0093, + 0.0094, + 0.0095, + 0.0096, + 0.0097, + 0.0098, + 0.0099, + 0.0099, + 0.01, + 0.0101, + 0.0102, + 0.0103, + 0.0104, + 0.0105, + 0.0106, + 0.0107, + 0.0108, + 0.0109, + 0.011, + 0.0111, + 0.0112, + 0.0113, + 0.0114, + 0.0115, + 0.0116, + 0.0117, + 0.0118, + 0.0119, + 0.012, + 0.0121, + 0.0122, + 0.0123, + 0.0124, + 0.0125, + 0.0126, + 0.0127, + 0.0128, + 0.0129, + 0.013, + 0.0131, + 0.0133, + 0.0134, + 0.0135, + 0.0136, + 0.0137, + 0.0138, + 0.0139, + 0.0141, + 0.0142, + 0.0143, + 0.0144, + 0.0145, + 0.0147, + 0.0148, + 0.0149, + 0.015, + 0.0151, + 0.0153, + 0.0154, + 0.0155, + 0.0157, + 0.0158, + 0.0159, + 0.016, + 0.0162, + 0.0163, + 0.0164, + 0.0166, + 0.0167, + 0.0168, + 0.017, + 0.0171, + 0.0173, + 0.0174, + 0.0175, + 0.0177, + 0.0178, + 0.018, + 0.0181, + 0.0182, + 0.0184, + 0.0185, + 0.0187, + 0.0188, + 0.019, + 0.0191, + 0.0193, + 0.0194, + 0.0196, + 0.0197, + 0.0199, + 0.02, + 0.0202, + 0.0204, + 0.0205, + 0.0207, + 0.0208, + 0.021, + 0.0211, + 0.0213, + 0.0215, + 0.0216, + 0.0218, + 0.022, + 0.0221, + 0.0223, + 0.0225, + 0.0226, + 0.0228, + 0.023, + 0.0232, + 0.0233, + 0.0235, + 0.0237, + 0.0239, + 0.024, + 0.0242, + 0.0244, + 0.0246, + 0.0248, + 0.025, + 0.0251, + 0.0253, + 0.0255, + 0.0257, + 0.0259, + 0.0261, + 0.0263, + 0.0265, + 0.0267, + 0.0268, + 0.027, + 0.0272, + 0.0274, + 0.0276, + 0.0278, + 0.028, + 0.0282, + 0.0284, + 0.0286, + 0.0289, + 0.0291, + 0.0293, + 0.0295, + 0.0297, + 0.0299, + 0.0301, + 0.0303, + 0.0305, + 0.0307, + 0.031, + 0.0312, + 0.0314, + 0.0316, + 0.0318, + 0.0321, + 0.0323, + 0.0325, + 0.0327, + 0.033, + 0.0332, + 0.0334, + 0.0337, + 0.0339, + 0.0341, + 0.0344, + 0.0346, + 0.0348, + 0.0351, + 0.0353, + 0.0355, + 0.0358, + 0.036, + 0.0363, + 0.0365, + 0.0368, + 0.037, + 0.0373, + 0.0375, + 0.0378, + 0.038, + 0.0383, + 0.0385, + 0.0388, + 0.039, + 0.0393, + 0.0396, + 0.0398, + 0.0401, + 0.0403, + 0.0406, + 0.0409, + 0.0411, + 0.0414, + 0.0417, + 0.0419, + 0.0422, + 0.0425, + 0.0428, + 0.043, + 0.0433, + 0.0436, + 0.0439, + 0.0442, + 0.0444, + 0.0447, + 0.045, + 0.0453, + 0.0456, + 0.0459, + 0.0462, + 0.0465, + 0.0468, + 0.0471, + 0.0474, + 0.0477, + 0.048, + 0.0483, + 0.0486, + 0.0489, + 0.0492, + 0.0495, + 0.0498, + 0.0501, + 0.0504, + 0.0507, + 0.051, + 0.0513, + 0.0517, + 0.052, + 0.0523, + 0.0526, + 0.0529, + 0.0533, + 0.0536, + 0.0539, + 0.0542, + 0.0546, + 0.0549, + 0.0552, + 0.0556, + 0.0559, + 0.0562, + 0.0566, + 0.0569, + 0.0572, + 0.0576, + 0.0579, + 0.0583, + 0.0586, + 0.059, + 0.0593, + 0.0597, + 0.06, + 0.0604, + 0.0607, + 0.0611, + 0.0614, + 0.0618, + 0.0621, + 0.0625, + 0.0629, + 0.0632, + 0.0636, + 0.064, + 0.0643, + 0.0647, + 0.0651, + 0.0655, + 0.0658, + 0.0662, + 0.0666, + 0.067, + 0.0673, + 0.0677, + 0.0681, + 0.0685, + 0.0689, + 0.0693, + 0.0697, + 0.07, + 0.0704, + 0.0708, + 0.0712, + 0.0716, + 0.072, + 0.0724, + 0.0728, + 0.0732, + 0.0736, + 0.074, + 0.0745, + 0.0749, + 0.0753, + 0.0757, + 0.0761, + 0.0765, + 0.0769, + 0.0774, + 0.0778, + 0.0782, + 0.0786, + 0.079, + 0.0795, + 0.0799, + 0.0803, + 0.0808, + 0.0812, + 0.0816, + 0.0821, + 0.0825, + 0.0829, + 0.0834, + 0.0838, + 0.0843, + 0.0847, + 0.0852, + 0.0856, + 0.0861, + 0.0865, + 0.087, + 0.0874, + 0.0879, + 0.0883, + 0.0888, + 0.0892, + 0.0897, + 0.0902, + 0.0906, + 0.0911, + 0.0916, + 0.092, + 0.0925, + 0.093, + 0.0935, + 0.0939, + 0.0944, + 0.0949, + 0.0954, + 0.0959, + 0.0963, + 0.0968, + 0.0973, + 0.0978, + 0.0983, + 0.0988, + 0.0993, + 0.0998, + 0.1003, + 0.1008, + 0.1013, + 0.1018, + 0.1023, + 0.1028, + 0.1033, + 0.1038, + 0.1043, + 0.1048, + 0.1053, + 0.1058, + 0.1064, + 0.1069, + 0.1074, + 0.1079, + 0.1084, + 0.109, + 0.1095, + 0.11, + 0.1105, + 0.1111, + 0.1116, + 0.1121, + 0.1127, + 0.1132, + 0.1138, + 0.1143, + 0.1148, + 0.1154, + 0.1159, + 0.1165, + 0.117, + 0.1176, + 0.1181, + 0.1187, + 0.1192, + 0.1198, + 0.1203, + 0.1209, + 0.1215, + 0.122, + 0.1226, + 0.1231, + 0.1237, + 0.1243, + 0.1248, + 0.1254, + 0.126, + 0.1266, + 0.1271, + 0.1277, + 0.1283, + 0.1289, + 0.1295, + 0.13, + 0.1306, + 0.1312, + 0.1318, + 0.1324, + 0.133, + 0.1336, + 0.1342, + 0.1348, + 0.1354, + 0.136, + 0.1366, + 0.1372, + 0.1378, + 0.1384, + 0.139, + 0.1396, + 0.1402, + 0.1408, + 0.1414, + 0.1421, + 0.1427, + 0.1433, + 0.1439, + 0.1445, + 0.1452, + 0.1458, + 0.1464, + 0.147, + 0.1477, + 0.1483, + 0.1489, + 0.1496, + 0.1502, + 0.1508, + 0.1515, + 0.1521, + 0.1528, + 0.1534, + 0.154, + 0.1547, + 0.1553, + 0.156, + 0.1566, + 0.1573, + 0.1579, + 0.1586, + 0.1593, + 0.1599, + 0.1606, + 0.1612, + 0.1619, + 0.1626, + 0.1632, + 0.1639, + 0.1646, + 0.1652, + 0.1659, + 0.1666, + 0.1673, + 0.1679, + 0.1686, + 0.1693, + 0.17, + 0.1707, + 0.1713, + 0.172, + 0.1727, + 0.1734, + 0.1741, + 0.1748, + 0.1755, + 0.1762, + 0.1769, + 0.1776, + 0.1783, + 0.179, + 0.1797, + 0.1804, + 0.1811, + 0.1818, + 0.1825, + 0.1832, + 0.1839, + 0.1846, + 0.1853, + 0.186, + 0.1867, + 0.1875, + 0.1882, + 0.1889, + 0.1896, + 0.1903, + 0.1911, + 0.1918, + 0.1925, + 0.1932, + 0.194, + 0.1947, + 0.1954, + 0.1962, + 0.1969, + 0.1976, + 0.1984, + 0.1991, + 0.1999, + 0.2006, + 0.2013, + 0.2021, + 0.2028, + 0.2036, + 0.2043, + 0.2051, + 0.2058, + 0.2066, + 0.2073, + 0.2081, + 0.2089, + 0.2096, + 0.2104, + 0.2111, + 0.2119, + 0.2127, + 0.2134, + 0.2142, + 0.2149, + 0.2157, + 0.2165, + 0.2173, + 0.218, + 0.2188, + 0.2196, + 0.2204, + 0.2211, + 0.2219, + 0.2227, + 0.2235, + 0.2243, + 0.225, + 0.2258, + 0.2266, + 0.2274, + 0.2282, + 0.229, + 0.2298, + 0.2306, + 0.2313, + 0.2321, + 0.2329, + 0.2337, + 0.2345, + 0.2353, + 0.2361, + 0.2369, + 0.2377, + 0.2385, + 0.2393, + 0.2402, + 0.241, + 0.2418, + 0.2426, + 0.2434, + 0.2442, + 0.245, + 0.2458, + 0.2466, + 0.2475, + 0.2483, + 0.2491, + 0.2499, + 0.2507, + 0.2516, + 0.2524, + 0.2532, + 0.254, + 0.2549, + 0.2557, + 0.2565, + 0.2574, + 0.2582, + 0.259, + 0.2599, + 0.2607, + 0.2615, + 0.2624, + 0.2632, + 0.264, + 0.2649, + 0.2657, + 0.2666, + 0.2674, + 0.2682, + 0.2691, + 0.2699, + 0.2708, + 0.2716, + 0.2725, + 0.2733, + 0.2742, + 0.275, + 0.2759, + 0.2767, + 0.2776, + 0.2784, + 0.2793, + 0.2802, + 0.281, + 0.2819, + 0.2827, + 0.2836, + 0.2845, + 0.2853, + 0.2862, + 0.2871, + 0.2879, + 0.2888, + 0.2897, + 0.2905, + 0.2914, + 0.2923, + 0.2931, + 0.294, + 0.2949, + 0.2958, + 0.2966, + 0.2975, + 0.2984, + 0.2993, + 0.3001, + 0.301, + 0.3019, + 0.3028, + 0.3037, + 0.3045, + 0.3054, + 0.3063, + 0.3072, + 0.3081, + 0.309, + 0.3099, + 0.3107, + 0.3116, + 0.3125, + 0.3134, + 0.3143, + 0.3152, + 0.3161, + 0.317, + 0.3179, + 0.3188, + 0.3197, + 0.3206, + 0.3215, + 0.3224, + 0.3233, + 0.3242, + 0.3251, + 0.326, + 0.3269, + 0.3278, + 0.3287, + 0.3296, + 0.3305, + 0.3314, + 0.3323, + 0.3332, + 0.3341, + 0.335, + 0.3359, + 0.3368, + 0.3377, + 0.3386, + 0.3395, + 0.3405, + 0.3414, + 0.3423, + 0.3432, + 0.3441, + 0.345, + 0.3459, + 0.3469, + 0.3478, + 0.3487, + 0.3496, + 0.3505, + 0.3514, + 0.3524, + 0.3533, + 0.3542, + 0.3551, + 0.356, + 0.357, + 0.3579, + 0.3588, + 0.3597, + 0.3606, + 0.3616, + 0.3625, + 0.3634, + 0.3643, + 0.3653, + 0.3662, + 0.3671, + 0.3681, + 0.369, + 0.3699, + 0.3708, + 0.3718, + 0.3727, + 0.3736, + 0.3746, + 0.3755, + 0.3764, + 0.3773, + 0.3783, + 0.3792, + 0.3801, + 0.3811, + 0.382, + 0.3829, + 0.3839, + 0.3848, + 0.3857, + 0.3867, + 0.3876, + 0.3885, + 0.3895, + 0.3904, + 0.3914, + 0.3923, + 0.3932, + 0.3942, + 0.3951, + 0.396, + 0.397, + 0.3979, + 0.3989, + 0.3998, + 0.4007, + 0.4017, + 0.4026, + 0.4036, + 0.4045, + 0.4054, + 0.4064, + 0.4073, + 0.4083, + 0.4092, + 0.4101, + 0.4111, + 0.412, + 0.413, + 0.4139, + 0.4148, + 0.4158, + 0.4167, + 0.4177, + 0.4186, + 0.4196, + 0.4205, + 0.4215, + 0.4224, + 0.4233, + 0.4243, + 0.4252, + 0.4262, + 0.4271, + 0.4281, + 0.429, + 0.4299, + 0.4309, + 0.4318, + 0.4328, + 0.4337, + 0.4347, + 0.4356, + 0.4366, + 0.4375, + 0.4384, + 0.4394, + 0.4403, + 0.4413, + 0.4422, + 0.4432, + 0.4441, + 0.4451, + 0.446, + 0.447, + 0.4479, + 0.4488, + 0.4498, + 0.4507, + 0.4517, + 0.4526, + 0.4536, + 0.4545, + 0.4555, + 0.4564, + 0.4573, + 0.4583, + 0.4592, + 0.4602, + 0.4611, + 0.4621, + 0.463, + 0.464, + 0.4649, + 0.4658, + 0.4668, + 0.4677, + 0.4687, + 0.4696, + 0.4706, + 0.4715, + 0.4724, + 0.4734, + 0.4743, + 0.4753, + 0.4762, + 0.4772, + 0.4781, + 0.479, + 0.48, + 0.4809, + 0.4819, + 0.4828, + 0.4837, + 0.4847, + 0.4856, + 0.4866, + 0.4875, + 0.4884, + 0.4894, + 0.4903, + 0.4913, + 0.4922, + 0.4931, + 0.4941, + 0.495, + 0.496, + 0.4969, + 0.4978, + 0.4988, + 0.4997, + 0.5006, + 0.5016, + 0.5025, + 0.5034, + 0.5044, + 0.5053, + 0.5062, + 0.5072, + 0.5081, + 0.509, + 0.51, + 0.5109, + 0.5118, + 0.5128, + 0.5137, + 0.5146, + 0.5156, + 0.5165, + 0.5174, + 0.5184, + 0.5193, + 0.5202, + 0.5211, + 0.5221, + 0.523, + 0.5239, + 0.5248, + 0.5258, + 0.5267, + 0.5276, + 0.5285, + 0.5295, + 0.5304, + 0.5313, + 0.5322, + 0.5332, + 0.5341, + 0.535, + 0.5359, + 0.5368, + 0.5378, + 0.5387, + 0.5396, + 0.5405, + 0.5414, + 0.5424, + 0.5433, + 0.5442, + 0.5451, + 0.546, + 0.5469, + 0.5479, + 0.5488, + 0.5497, + 0.5506, + 0.5515, + 0.5524, + 0.5533, + 0.5542, + 0.5551, + 0.5561, + 0.557, + 0.5579, + 0.5588, + 0.5597, + 0.5606, + 0.5615, + 0.5624, + 0.5633, + 0.5642, + 0.5651, + 0.566, + 0.5669, + 0.5678, + 0.5687, + 0.5696, + 0.5705, + 0.5714, + 0.5723, + 0.5732, + 0.5741, + 0.575, + 0.5759, + 0.5768, + 0.5777, + 0.5786, + 0.5795, + 0.5804, + 0.5813, + 0.5821, + 0.583, + 0.5839, + 0.5848, + 0.5857, + 0.5866, + 0.5875, + 0.5884, + 0.5892, + 0.5901 + ] + } +} +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/output_dedup_pairs.stats Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,438 @@ +total 1992 +total_unmapped 914 +total_single_sided_mapped 287 +total_mapped 791 +total_dups 9 +total_nodups 782 +cis 597 +trans 185 +pair_types/NN 853 +pair_types/UU 782 +pair_types/NU 234 +pair_types/MU 53 +pair_types/MM 40 +pair_types/NM 21 +pair_types/DD 9 +cis_1kb+ 185 +cis_2kb+ 171 +cis_4kb+ 151 +cis_10kb+ 114 +cis_20kb+ 80 +cis_40kb+ 46 +summary/frac_cis 0.7634271099744245 +summary/frac_cis_1kb+ 0.23657289002557544 +summary/frac_cis_2kb+ 0.2186700767263427 +summary/frac_cis_4kb+ 0.19309462915601022 +summary/frac_cis_10kb+ 0.14578005115089515 +summary/frac_cis_20kb+ 0.10230179028132992 +summary/frac_cis_40kb+ 0.058823529411764705 +summary/frac_dups 0.011378002528445006 +summary/complexity_naive 34495.88583157276 +summary/dist_freq_convergence/convergence_dist 1333521 +summary/dist_freq_convergence/strands_w_max_convergence_dist ++ +summary/dist_freq_convergence/convergence_rel_diff_threshold 0.05 +summary/dist_freq_convergence/n_cis_pairs_below_convergence_dist/++ 49 +summary/dist_freq_convergence/n_cis_pairs_below_convergence_dist/-- 58 +summary/dist_freq_convergence/n_cis_pairs_below_convergence_dist/-+ 65 +summary/dist_freq_convergence/n_cis_pairs_below_convergence_dist/+- 425 +summary/dist_freq_convergence/n_cis_pairs_below_convergence_dist_all_strands 597 +summary/dist_freq_convergence/n_cis_pairs_above_convergence_dist_all_strands 0 +summary/dist_freq_convergence/frac_cis_in_cis_below_convergence_dist/++ 0.08207705192629816 +summary/dist_freq_convergence/frac_cis_in_cis_below_convergence_dist/-- 0.09715242881072027 +summary/dist_freq_convergence/frac_cis_in_cis_below_convergence_dist/-+ 0.10887772194304858 +summary/dist_freq_convergence/frac_cis_in_cis_below_convergence_dist/+- 0.711892797319933 +summary/dist_freq_convergence/frac_cis_in_cis_below_convergence_dist_all_strands 1.0 +summary/dist_freq_convergence/frac_cis_in_cis_above_convergence_dist_all_strands 0.0 +summary/dist_freq_convergence/frac_total_mapped_in_cis_below_convergence_dist/++ 0.061946902654867256 +summary/dist_freq_convergence/frac_total_mapped_in_cis_below_convergence_dist/-- 0.07332490518331226 +summary/dist_freq_convergence/frac_total_mapped_in_cis_below_convergence_dist/-+ 0.08217446270543616 +summary/dist_freq_convergence/frac_total_mapped_in_cis_below_convergence_dist/+- 0.5372945638432364 +summary/dist_freq_convergence/frac_total_mapped_in_cis_below_convergence_dist_all_strands 0.754740834386852 +summary/dist_freq_convergence/frac_total_mapped_in_cis_above_convergence_dist_all_strands 0.0 +summary/dist_freq_convergence/frac_total_nodups_in_cis_below_convergence_dist/++ 0.06265984654731457 +summary/dist_freq_convergence/frac_total_nodups_in_cis_below_convergence_dist/-- 0.0741687979539642 +summary/dist_freq_convergence/frac_total_nodups_in_cis_below_convergence_dist/-+ 0.08312020460358056 +summary/dist_freq_convergence/frac_total_nodups_in_cis_below_convergence_dist/+- 0.5434782608695652 +summary/dist_freq_convergence/frac_total_nodups_in_cis_below_convergence_dist_all_strands 0.7634271099744245 +summary/dist_freq_convergence/frac_total_nodups_in_cis_above_convergence_dist_all_strands 0.0 +chrom_freq/chrIV/chrIV 83 +chrom_freq/chrVII/chrVII 55 +chrom_freq/chrXV/chrXV 53 +chrom_freq/chrXIII/chrXIII 46 +chrom_freq/chrII/chrII 41 +chrom_freq/chrXVI/chrXVI 40 +chrom_freq/chrXIV/chrXIV 37 +chrom_freq/chrX/chrX 37 +chrom_freq/chrXII/chrXII 36 +chrom_freq/chrXI/chrXI 36 +chrom_freq/chrM/chrM 33 +chrom_freq/chrVIII/chrVIII 30 +chrom_freq/chrIX/chrIX 22 +chrom_freq/chrV/chrV 21 +chrom_freq/chrIII/chrIII 12 +chrom_freq/chrVI/chrVI 8 +chrom_freq/chrI/chrI 7 +chrom_freq/chrVII/chrXV 6 +chrom_freq/chrIV/chrXII 6 +chrom_freq/chrIV/chrXIII 6 +chrom_freq/chrVII/chrXII 6 +chrom_freq/chrII/chrVII 5 +chrom_freq/chrXII/chrXIII 5 +chrom_freq/chrIV/chrX 5 +chrom_freq/chrX/chrXIV 4 +chrom_freq/chrII/chrIV 4 +chrom_freq/chrII/chrXVI 4 +chrom_freq/chrXIV/chrXVI 4 +chrom_freq/chrII/chrXIV 4 +chrom_freq/chrVII/chrXIV 4 +chrom_freq/chrXI/chrXV 4 +chrom_freq/chrXI/chrXII 4 +chrom_freq/chrIV/chrVII 4 +chrom_freq/chrXIII/chrXV 3 +chrom_freq/chrXI/chrXVI 3 +chrom_freq/chrII/chrXIII 3 +chrom_freq/chrXI/chrXIII 3 +chrom_freq/chrVII/chrIX 3 +chrom_freq/chrVIII/chrXIII 3 +chrom_freq/chrX/chrXII 3 +chrom_freq/chrX/chrXIII 3 +chrom_freq/chrXIII/chrXIV 3 +chrom_freq/chrV/chrXVI 3 +chrom_freq/chrIV/chrV 3 +chrom_freq/chrIV/chrVIII 3 +chrom_freq/chrIV/chrXI 3 +chrom_freq/chrIV/chrXV 3 +chrom_freq/chrIV/chrXVI 3 +chrom_freq/chrXV/chrXVI 3 +chrom_freq/chrIX/chrXII 3 +chrom_freq/chrXIII/chrXVI 2 +chrom_freq/chrX/chrXVI 2 +chrom_freq/chrIV/chrVI 2 +chrom_freq/chrIV/chrXIV 2 +chrom_freq/chrXI/chrXIV 2 +chrom_freq/chrVII/chrXVI 2 +chrom_freq/chrIX/chrX 2 +chrom_freq/chrVII/chrVIII 2 +chrom_freq/chrIII/chrX 2 +chrom_freq/chrIX/chrXV 2 +chrom_freq/chrIII/chrV 2 +chrom_freq/chrXIV/chrXV 2 +chrom_freq/chrXII/chrXV 2 +chrom_freq/chrV/chrX 2 +chrom_freq/chrI/chrX 2 +chrom_freq/chrII/chrXV 2 +chrom_freq/chrII/chrVIII 1 +chrom_freq/chrXII/chrXIV 1 +chrom_freq/chrXII/chrXVI 1 +chrom_freq/chrII/chrX 1 +chrom_freq/chrI/chrXV 1 +chrom_freq/chrIII/chrXIII 1 +chrom_freq/chrII/chrXI 1 +chrom_freq/chrVI/chrX 1 +chrom_freq/chrIII/chrVIII 1 +chrom_freq/chrIX/chrXI 1 +chrom_freq/chrV/chrM 1 +chrom_freq/chrV/chrVI 1 +chrom_freq/chrV/chrXI 1 +chrom_freq/chrV/chrXIII 1 +chrom_freq/chrV/chrXIV 1 +chrom_freq/chrV/chrXV 1 +chrom_freq/chrVI/chrXI 1 +chrom_freq/chrVIII/chrXV 1 +chrom_freq/chrVI/chrXII 1 +chrom_freq/chrVI/chrXIII 1 +chrom_freq/chrVI/chrXIV 1 +chrom_freq/chrVI/chrXVI 1 +chrom_freq/chrVII/chrXIII 1 +chrom_freq/chrVIII/chrIX 1 +chrom_freq/chrVIII/chrXI 1 +chrom_freq/chrVIII/chrXII 1 +chrom_freq/chrVI/chrVII 1 +dist_freq/0-1/+- 0 +dist_freq/0-1/-+ 0 +dist_freq/0-1/-- 0 +dist_freq/0-1/++ 0 +dist_freq/1-2/+- 0 +dist_freq/1-2/-+ 0 +dist_freq/1-2/-- 0 +dist_freq/1-2/++ 0 +dist_freq/2-3/+- 0 +dist_freq/2-3/-+ 0 +dist_freq/2-3/-- 0 +dist_freq/2-3/++ 0 +dist_freq/3-4/+- 0 +dist_freq/3-4/-+ 0 +dist_freq/3-4/-- 0 +dist_freq/3-4/++ 0 +dist_freq/4-6/+- 0 +dist_freq/4-6/-+ 1 +dist_freq/4-6/-- 0 +dist_freq/4-6/++ 1 +dist_freq/6-7/+- 0 +dist_freq/6-7/-+ 0 +dist_freq/6-7/-- 0 +dist_freq/6-7/++ 0 +dist_freq/7-10/+- 0 +dist_freq/7-10/-+ 0 +dist_freq/7-10/-- 0 +dist_freq/7-10/++ 0 +dist_freq/10-13/+- 0 +dist_freq/10-13/-+ 0 +dist_freq/10-13/-- 0 +dist_freq/10-13/++ 0 +dist_freq/13-18/+- 0 +dist_freq/13-18/-+ 0 +dist_freq/13-18/-- 0 +dist_freq/13-18/++ 0 +dist_freq/18-24/+- 0 +dist_freq/18-24/-+ 0 +dist_freq/18-24/-- 0 +dist_freq/18-24/++ 0 +dist_freq/24-32/+- 0 +dist_freq/24-32/-+ 0 +dist_freq/24-32/-- 0 +dist_freq/24-32/++ 0 +dist_freq/32-42/+- 0 +dist_freq/32-42/-+ 0 +dist_freq/32-42/-- 0 +dist_freq/32-42/++ 0 +dist_freq/42-56/+- 0 +dist_freq/42-56/-+ 0 +dist_freq/42-56/-- 0 +dist_freq/42-56/++ 0 +dist_freq/56-75/+- 0 +dist_freq/56-75/-+ 0 +dist_freq/56-75/-- 0 +dist_freq/56-75/++ 0 +dist_freq/75-100/+- 0 +dist_freq/75-100/-+ 1 +dist_freq/75-100/-- 0 +dist_freq/75-100/++ 0 +dist_freq/100-133/+- 1 +dist_freq/100-133/-+ 0 +dist_freq/100-133/-- 1 +dist_freq/100-133/++ 0 +dist_freq/133-178/+- 6 +dist_freq/133-178/-+ 2 +dist_freq/133-178/-- 1 +dist_freq/133-178/++ 0 +dist_freq/178-237/+- 116 +dist_freq/178-237/-+ 3 +dist_freq/178-237/-- 0 +dist_freq/178-237/++ 0 +dist_freq/237-316/+- 218 +dist_freq/237-316/-+ 6 +dist_freq/237-316/-- 1 +dist_freq/237-316/++ 0 +dist_freq/316-422/+- 32 +dist_freq/316-422/-+ 3 +dist_freq/316-422/-- 0 +dist_freq/316-422/++ 0 +dist_freq/422-562/+- 2 +dist_freq/422-562/-+ 4 +dist_freq/422-562/-- 0 +dist_freq/422-562/++ 0 +dist_freq/562-750/+- 1 +dist_freq/562-750/-+ 3 +dist_freq/562-750/-- 0 +dist_freq/562-750/++ 0 +dist_freq/750-1000/+- 0 +dist_freq/750-1000/-+ 8 +dist_freq/750-1000/-- 0 +dist_freq/750-1000/++ 1 +dist_freq/1000-1334/+- 0 +dist_freq/1000-1334/-+ 1 +dist_freq/1000-1334/-- 2 +dist_freq/1000-1334/++ 0 +dist_freq/1334-1778/+- 0 +dist_freq/1334-1778/-+ 4 +dist_freq/1334-1778/-- 4 +dist_freq/1334-1778/++ 1 +dist_freq/1778-2371/+- 1 +dist_freq/1778-2371/-+ 4 +dist_freq/1778-2371/-- 1 +dist_freq/1778-2371/++ 0 +dist_freq/2371-3162/+- 4 +dist_freq/2371-3162/-+ 3 +dist_freq/2371-3162/-- 1 +dist_freq/2371-3162/++ 0 +dist_freq/3162-4217/+- 1 +dist_freq/3162-4217/-+ 2 +dist_freq/3162-4217/-- 3 +dist_freq/3162-4217/++ 3 +dist_freq/4217-5623/+- 3 +dist_freq/4217-5623/-+ 2 +dist_freq/4217-5623/-- 3 +dist_freq/4217-5623/++ 1 +dist_freq/5623-7499/+- 6 +dist_freq/5623-7499/-+ 2 +dist_freq/5623-7499/-- 6 +dist_freq/5623-7499/++ 2 +dist_freq/7499-10000/+- 3 +dist_freq/7499-10000/-+ 2 +dist_freq/7499-10000/-- 3 +dist_freq/7499-10000/++ 3 +dist_freq/10000-13335/+- 5 +dist_freq/10000-13335/-+ 1 +dist_freq/10000-13335/-- 3 +dist_freq/10000-13335/++ 6 +dist_freq/13335-17783/+- 2 +dist_freq/13335-17783/-+ 3 +dist_freq/13335-17783/-- 5 +dist_freq/13335-17783/++ 4 +dist_freq/17783-23714/+- 5 +dist_freq/17783-23714/-+ 0 +dist_freq/17783-23714/-- 4 +dist_freq/17783-23714/++ 4 +dist_freq/23714-31623/+- 4 +dist_freq/23714-31623/-+ 4 +dist_freq/23714-31623/-- 4 +dist_freq/23714-31623/++ 1 +dist_freq/31623-42170/+- 4 +dist_freq/31623-42170/-+ 2 +dist_freq/31623-42170/-- 3 +dist_freq/31623-42170/++ 6 +dist_freq/42170-56234/+- 2 +dist_freq/42170-56234/-+ 2 +dist_freq/42170-56234/-- 4 +dist_freq/42170-56234/++ 4 +dist_freq/56234-74989/+- 2 +dist_freq/56234-74989/-+ 0 +dist_freq/56234-74989/-- 4 +dist_freq/56234-74989/++ 2 +dist_freq/74989-100000/+- 0 +dist_freq/74989-100000/-+ 1 +dist_freq/74989-100000/-- 1 +dist_freq/74989-100000/++ 3 +dist_freq/100000-133352/+- 1 +dist_freq/100000-133352/-+ 0 +dist_freq/100000-133352/-- 0 +dist_freq/100000-133352/++ 2 +dist_freq/133352-177828/+- 2 +dist_freq/133352-177828/-+ 1 +dist_freq/133352-177828/-- 1 +dist_freq/133352-177828/++ 0 +dist_freq/177828-237137/+- 2 +dist_freq/177828-237137/-+ 0 +dist_freq/177828-237137/-- 2 +dist_freq/177828-237137/++ 2 +dist_freq/237137-316228/+- 1 +dist_freq/237137-316228/-+ 0 +dist_freq/237137-316228/-- 0 +dist_freq/237137-316228/++ 1 +dist_freq/316228-421697/+- 0 +dist_freq/316228-421697/-+ 0 +dist_freq/316228-421697/-- 0 +dist_freq/316228-421697/++ 0 +dist_freq/421697-562341/+- 0 +dist_freq/421697-562341/-+ 0 +dist_freq/421697-562341/-- 0 +dist_freq/421697-562341/++ 1 +dist_freq/562341-749894/+- 1 +dist_freq/562341-749894/-+ 0 +dist_freq/562341-749894/-- 0 +dist_freq/562341-749894/++ 1 +dist_freq/749894-1000000/+- 0 +dist_freq/749894-1000000/-+ 0 +dist_freq/749894-1000000/-- 0 +dist_freq/749894-1000000/++ 0 +dist_freq/1000000-1333521/+- 0 +dist_freq/1000000-1333521/-+ 0 +dist_freq/1000000-1333521/-- 1 +dist_freq/1000000-1333521/++ 0 +dist_freq/1333521-1778279/+- 0 +dist_freq/1333521-1778279/-+ 0 +dist_freq/1333521-1778279/-- 0 +dist_freq/1333521-1778279/++ 0 +dist_freq/1778279-2371374/+- 0 +dist_freq/1778279-2371374/-+ 0 +dist_freq/1778279-2371374/-- 0 +dist_freq/1778279-2371374/++ 0 +dist_freq/2371374-3162278/+- 0 +dist_freq/2371374-3162278/-+ 0 +dist_freq/2371374-3162278/-- 0 +dist_freq/2371374-3162278/++ 0 +dist_freq/3162278-4216965/+- 0 +dist_freq/3162278-4216965/-+ 0 +dist_freq/3162278-4216965/-- 0 +dist_freq/3162278-4216965/++ 0 +dist_freq/4216965-5623413/+- 0 +dist_freq/4216965-5623413/-+ 0 +dist_freq/4216965-5623413/-- 0 +dist_freq/4216965-5623413/++ 0 +dist_freq/5623413-7498942/+- 0 +dist_freq/5623413-7498942/-+ 0 +dist_freq/5623413-7498942/-- 0 +dist_freq/5623413-7498942/++ 0 +dist_freq/7498942-10000000/+- 0 +dist_freq/7498942-10000000/-+ 0 +dist_freq/7498942-10000000/-- 0 +dist_freq/7498942-10000000/++ 0 +dist_freq/10000000-13335214/+- 0 +dist_freq/10000000-13335214/-+ 0 +dist_freq/10000000-13335214/-- 0 +dist_freq/10000000-13335214/++ 0 +dist_freq/13335214-17782794/+- 0 +dist_freq/13335214-17782794/-+ 0 +dist_freq/13335214-17782794/-- 0 +dist_freq/13335214-17782794/++ 0 +dist_freq/17782794-23713737/+- 0 +dist_freq/17782794-23713737/-+ 0 +dist_freq/17782794-23713737/-- 0 +dist_freq/17782794-23713737/++ 0 +dist_freq/23713737-31622777/+- 0 +dist_freq/23713737-31622777/-+ 0 +dist_freq/23713737-31622777/-- 0 +dist_freq/23713737-31622777/++ 0 +dist_freq/31622777-42169650/+- 0 +dist_freq/31622777-42169650/-+ 0 +dist_freq/31622777-42169650/-- 0 +dist_freq/31622777-42169650/++ 0 +dist_freq/42169650-56234133/+- 0 +dist_freq/42169650-56234133/-+ 0 +dist_freq/42169650-56234133/-- 0 +dist_freq/42169650-56234133/++ 0 +dist_freq/56234133-74989421/+- 0 +dist_freq/56234133-74989421/-+ 0 +dist_freq/56234133-74989421/-- 0 +dist_freq/56234133-74989421/++ 0 +dist_freq/74989421-100000000/+- 0 +dist_freq/74989421-100000000/-+ 0 +dist_freq/74989421-100000000/-- 0 +dist_freq/74989421-100000000/++ 0 +dist_freq/100000000-133352143/+- 0 +dist_freq/100000000-133352143/-+ 0 +dist_freq/100000000-133352143/-- 0 +dist_freq/100000000-133352143/++ 0 +dist_freq/133352143-177827941/+- 0 +dist_freq/133352143-177827941/-+ 0 +dist_freq/133352143-177827941/-- 0 +dist_freq/133352143-177827941/++ 0 +dist_freq/177827941-237137371/+- 0 +dist_freq/177827941-237137371/-+ 0 +dist_freq/177827941-237137371/-- 0 +dist_freq/177827941-237137371/++ 0 +dist_freq/237137371-316227766/+- 0 +dist_freq/237137371-316227766/-+ 0 +dist_freq/237137371-316227766/-- 0 +dist_freq/237137371-316227766/++ 0 +dist_freq/316227766-421696503/+- 0 +dist_freq/316227766-421696503/-+ 0 +dist_freq/316227766-421696503/-- 0 +dist_freq/316227766-421696503/++ 0 +dist_freq/421696503-562341325/+- 0 +dist_freq/421696503-562341325/-+ 0 +dist_freq/421696503-562341325/-- 0 +dist_freq/421696503-562341325/++ 0 +dist_freq/562341325-749894209/+- 0 +dist_freq/562341325-749894209/-+ 0 +dist_freq/562341325-749894209/-- 0 +dist_freq/562341325-749894209/++ 0 +dist_freq/749894209-1000000000/+- 0 +dist_freq/749894209-1000000000/-+ 0 +dist_freq/749894209-1000000000/-- 0 +dist_freq/749894209-1000000000/++ 0 +dist_freq/1000000000+/+- 0 +dist_freq/1000000000+/-+ 0 +dist_freq/1000000000+/-- 0 +dist_freq/1000000000+/++ 0
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/porechop.log Tue Feb 18 23:18:25 2025 +0000 @@ -0,0 +1,153 @@ + +[1m[4mLoading reads[0m +/tmp/tmp4zxnky4h/files/5/c/1/dataset_5c125cad-e633-41bc-8f37-36d6af3f5f0f.dat +9 reads loaded + + +[1m[4mLooking for known adapter sets[0m + 0 / 9 (0.0%) 9 / 9 (100.0%) 9 / 9 (100.0%) + Best [0m + read Best [0m + start read end[0m + [4mSet %ID %ID [0m + [32mSQK-NSK007 96.4 95.5[0m + Rapid 62.5 0.0 + RBK004_upstream 72.7 0.0 + SQK-MAP006 62.2 63.6 + SQK-MAP006 short 60.7 60.0 + PCR adapters 1 66.7 73.9 + PCR adapters 2 66.7 63.6 + PCR adapters 3 68.0 72.0 + 1D^2 part 1 62.1 58.8 + 1D^2 part 2 79.4 68.8 + cDNA SSP 57.1 61.4 + Barcode 1 (reverse) 59.4 66.7 + Barcode 2 (reverse) 66.7 63.0 + Barcode 3 (reverse) 69.2 72.0 + Barcode 4 (reverse) 66.7 63.3 + Barcode 5 (reverse) 62.5 66.7 + Barcode 6 (reverse) 73.1 62.5 + Barcode 7 (reverse) 65.4 65.5 + Barcode 8 (reverse) 69.2 58.3 + Barcode 9 (reverse) 75.0 66.7 + Barcode 10 (reverse) 62.5 60.0 + Barcode 11 (reverse) 69.2 60.5 + Barcode 12 (reverse) 65.6 64.0 + Barcode 1 (forward) 65.4 61.5 + Barcode 2 (forward) 69.2 70.4 + Barcode 3 (forward) 73.1 68.0 + Barcode 4 (forward) 73.1 64.3 + Barcode 5 (forward) 62.5 66.7 + Barcode 6 (forward) 65.5 65.6 + Barcode 7 (forward) 73.1 66.7 + Barcode 8 (forward) 62.1 60.7 + Barcode 9 (forward) 68.0 70.8 + Barcode 10 (forward) 69.2 66.7 + Barcode 11 (forward) 65.4 60.7 + Barcode 12 (forward) 64.3 66.7 + Barcode 13 (forward) 64.3 69.2 + Barcode 14 (forward) 63.3 66.7 + Barcode 15 (forward) 66.7 66.7 + Barcode 16 (forward) 70.8 65.5 + Barcode 17 (forward) 69.2 66.7 + Barcode 18 (forward) 70.4 70.4 + Barcode 19 (forward) 65.5 64.0 + Barcode 20 (forward) 65.5 64.0 + Barcode 21 (forward) 64.3 66.7 + Barcode 22 (forward) 69.2 68.0 + Barcode 23 (forward) 61.5 66.7 + Barcode 24 (forward) 66.7 65.4 + Barcode 25 (forward) 64.0 65.5 + Barcode 26 (forward) 72.0 72.0 + Barcode 27 (forward) 77.8 60.7 + Barcode 28 (forward) 65.5 66.7 + Barcode 29 (forward) 62.5 66.7 + Barcode 30 (forward) 68.0 65.4 + Barcode 31 (forward) 62.5 69.2 + Barcode 32 (forward) 68.0 70.8 + Barcode 33 (forward) 62.5 70.4 + Barcode 34 (forward) 64.0 62.5 + Barcode 35 (forward) 65.5 65.4 + Barcode 36 (forward) 63.0 63.0 + Barcode 37 (forward) 67.9 64.3 + Barcode 38 (forward) 64.0 62.1 + Barcode 39 (forward) 64.0 69.2 + Barcode 40 (forward) 62.5 64.0 + Barcode 41 (forward) 68.0 65.5 + Barcode 42 (forward) 70.4 69.2 + Barcode 43 (forward) 63.3 63.3 + Barcode 44 (forward) 60.0 66.7 + Barcode 45 (forward) 73.1 65.4 + Barcode 46 (forward) 65.4 60.7 + Barcode 47 (forward) 65.5 64.0 + Barcode 48 (forward) 71.4 62.1 + Barcode 49 (forward) 69.2 62.1 + Barcode 50 (forward) 66.7 63.0 + Barcode 51 (forward) 69.2 64.3 + Barcode 52 (forward) 66.7 64.0 + Barcode 53 (forward) 67.9 69.0 + Barcode 54 (forward) 69.2 64.0 + Barcode 55 (forward) 66.7 73.1 + Barcode 56 (forward) 66.7 72.0 + Barcode 57 (forward) 69.0 60.0 + Barcode 58 (forward) 70.4 72.0 + Barcode 59 (forward) 56.7 66.7 + Barcode 60 (forward) 66.7 66.7 + Barcode 61 (forward) 70.8 65.5 + Barcode 62 (forward) 66.7 68.0 + Barcode 63 (forward) 66.7 60.7 + Barcode 64 (forward) 69.2 66.7 + Barcode 65 (forward) 61.5 69.0 + Barcode 66 (forward) 64.3 63.0 + Barcode 67 (forward) 66.7 67.9 + Barcode 68 (forward) 67.9 69.2 + Barcode 69 (forward) 69.2 75.0 + Barcode 70 (forward) 64.3 73.1 + Barcode 71 (forward) 64.0 71.4 + Barcode 72 (forward) 66.7 62.1 + Barcode 73 (forward) 67.7 64.0 + Barcode 74 (forward) 64.5 68.0 + Barcode 75 (forward) 65.4 65.5 + Barcode 76 (forward) 70.4 70.8 + Barcode 77 (forward) 65.4 64.3 + Barcode 78 (forward) 67.7 63.0 + Barcode 79 (forward) 70.8 69.2 + Barcode 80 (forward) 71.4 72.0 + Barcode 81 (forward) 68.0 66.7 + Barcode 82 (forward) 64.7 66.7 + Barcode 83 (forward) 69.2 68.0 + Barcode 84 (forward) 70.8 67.9 + Barcode 85 (forward) 61.5 60.0 + Barcode 86 (forward) 64.3 65.4 + Barcode 87 (forward) 66.7 65.4 + Barcode 88 (forward) 63.3 60.7 + Barcode 89 (forward) 69.2 66.7 + Barcode 90 (forward) 66.7 64.0 + Barcode 91 (forward) 68.0 64.3 + Barcode 92 (forward) 65.5 68.0 + Barcode 93 (forward) 69.2 73.1 + Barcode 94 (forward) 63.0 68.0 + Barcode 95 (forward) 64.0 63.3 + Barcode 96 (forward) 69.0 68.0 + + +[1m[4mTrimming adapters from read ends[0m + SQK-NSK007_Y_Top: [31mAATGTACTTCGTTCAGTTACGTATTGCT[0m + SQK-NSK007_Y_Bottom: [31mGCAATACGTAACTGAACGAAGT[0m + + 0 / 9 (0.0%) 9 / 9 (100.0%) 9 / 9 (100.0%) + +4 / 9 reads had adapters trimmed from their start (74 bp removed) +3 / 9 reads had adapters trimmed from their end (49 bp removed) + + +[1m[4mSplitting reads containing middle adapters[0m + 0 / 9 (0.0%) 9 / 9 (100.0%) 10 / 9 (111.1%) 9 / 9 (100.0%) + +4 / 9 reads were split based on middle adapters + + +[1m[4mSaving trimmed reads to file[0m + +Saved result to /tmp/tmp4zxnky4h/job_working_directory/000/2/working/out.fasta +