Mercurial > repos > iuc > sinto_fragments
changeset 0:b6009d0098d7 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sinto commit a836e4e010093207186d4d7839bbba702a15c18f
| author | iuc |
|---|---|
| date | Thu, 13 Apr 2023 11:03:34 +0000 |
| parents | |
| children | 02f96be6c3c9 |
| files | macros.xml sinto_fragments.xml test-data/aligned.bam test-data/barcodes.fastq.gz test-data/read1.barcoded.fastq.gz test-data/read1.fastq.gz test-data/read2.barcoded.fastq.gz test-data/read2.fastq.gz |
| diffstat | 6 files changed, 100 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Thu Apr 13 11:03:34 2023 +0000 @@ -0,0 +1,11 @@ +<?xml version="1.0"?> +<macros> + <token name="@TOOL_VERSION@">0.9.0</token> + <token name="@VERSION_SUFFIX@">0</token> + + <xml name="citations"> + <citations> + <citation type="doi">10.1038/s41592-021-01282-5</citation> + </citations> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/sinto_fragments.xml Thu Apr 13 11:03:34 2023 +0000 @@ -0,0 +1,89 @@ +<tool id="sinto_fragments" name="Sinto fragments" profile="20.01" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> + <description>Create an ATAC-seq fragment file from a BAM file</description> + <macros> + <import>macros.xml</import> + </macros> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">sinto</requirement> + </requirements> + <version_command>sinto --version</version_command> + <command><![CDATA[ + ln -s '$bam' 'input.bam' && + ln -s '$bam.metadata.bam_index' 'input.bam.bai' && + sinto fragments + --bam 'input.bam' + --min_mapq $min_mapq + --barcodetag '$barcodetag' + --barcode_regex '${ str( $barcode_regex ) }' + --max_distance $max_distance + --min_distance $min_distance + --shift_plus $shift_plus + --shift_minus $shift_minus + $collapse_within + --fragments $fragments + --nproc "\${GALAXY_SLOTS:-1}" +]]> </command> + <inputs> + <param argument="--bam" type="data" format="bam" label="Input BAM file" /> + <param argument="--min_mapq" type="integer" value="30" min="0" label="Minimum MAPQ required to retain fragment" /> + <param argument="--barcodetag" type="text" value="CB" label="Read tag storing cell barcode information" /> + <param argument="--barcode_regex" type="text" value="[^:]*" label="Read tag storing cell barcode information" + help="[^:]* matches all characters up to the first colon" > + <sanitizer> + <valid initial="string.printable"> + <remove value="'" /> + </valid> + </sanitizer> + </param> + <param argument="--max_distance" type="integer" value="5000" min="0" label="Maximum distance between integration sites for the fragment to be retained" + help="Allows filtering of implausible fragments that likely result from incorrect mapping positions. Default is 5000 bp."/> + <param argument="--min_distance" type="integer" value="10" min="0" label="Minimum distance between integration sites for the fragment to be retained" + help="Allows filtering of implausible fragments that likely result from incorrect mapping positions. Default is 5000 bp."/> + <param argument="--shift_plus" type="integer" value="4" label="Minimum MAPQ required to retain fragment" /> + <param argument="--shift_minus" type="integer" value="-5" label="Minimum MAPQ required to retain fragment" /> + <param argument="--collapse_within" type="boolean" truevalue="--collapse_within" falsevalue="" label="Take cell barcode into account + when collapsing duplicate fragments" help="Setting this flag means that fragments with the same coordinates can be identified + provided they originate from a different cell barcode." /> + </inputs> + <outputs> + <data name='fragments' format='bed' label="${tool.name} on ${on_string}: fragments" /> + </outputs> + <tests> + <test expect_num_outputs="1"> + <param name="bam" ftype="bam" value="aligned.bam" /> + <output name="fragments"> + <assert_contents> + <has_text_matching expression="chrY\t2790323\t2790683\tAACTGGTAGCTCCGGT\t2" /> + <has_text_matching expression="chrY\t3680091\t3680228\tGACCGACGTACGGTTT\t2" /> + </assert_contents> + </output> + </test> + <test expect_num_outputs="1"> + <param name="bam" ftype="bam" value="aligned.bam" /> + <param name="shift_plus" value="4" /> + <param name="shift_minus" value="5" /> + <output name="fragments"> + <assert_contents> + <has_text_matching expression="chrY\t2790323\t2790693\tAACTGGTAGCTCCGGT\t2" /> + <has_text_matching expression="chrY\t3680091\t3680238\tGACCGACGTACGGTTT\t2" /> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ + +Sinto: single-cell analysis tools +-------------------------------------------------------------------------------------------------------------- +An ATAC-seq fragment file can be created from a BAM file using the fragments command. The fragment file contains the position of each +Tn5 integration site, the cell barcode associated with the fragment, and the number of times the fragment was sequenced. PCR duplicates are collapsed. + +**Input** +A BAM file. Alignments in the input BAM file must contain cell barcodes either as a part of read names or in a tag (typically, in CB tag). + +**Output** +The fragment file. It contains the positions of Tn5 integration sites, the cell barcode that the DNA fragment originated from, and the number of times +the fragment was sequenced. + + ]]> </help> + <expand macro="citations" /> +</tool>