Mercurial > repos > nick > duplex
changeset 4:7f513b9b1b1e draft
Change names to dunovo, use newer Github release.
| author | nick |
|---|---|
| date | Mon, 21 Dec 2015 14:47:48 -0500 |
| parents | aedbdf8ce1af |
| children | 4bc49a5769ee |
| files | align_families.xml dunovo.xml duplex.xml make_families.xml tool_dependencies.xml |
| diffstat | 5 files changed, 69 insertions(+), 67 deletions(-) [+] |
line wrap: on
line diff
--- a/align_families.xml Tue Dec 08 08:59:27 2015 -0500 +++ b/align_families.xml Mon Dec 21 14:47:48 2015 -0500 @@ -1,10 +1,11 @@ <?xml version="1.0"?> -<tool id="align_families" name="Du Novo: Align families" version="0.2"> +<tool id="align_families" name="Du Novo: Align families" version="0.3"> <description>of duplex sequencing reads</description> <requirements> <requirement type="package" version="7.221">mafft</requirement> - <requirement type="package" version="0.2">duplex</requirement> + <requirement type="package" version="0.3">duplex</requirement> <requirement type="set_environment">DUPLEX_DIR</requirement> + <!-- TODO: require Python 2.7 --> </requirements> <command detect_errors="exit_code">python \$DUPLEX_DIR/align_families.py -p \${GALAXY_SLOTS:-1} $input > $output </command>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/dunovo.xml Mon Dec 21 14:47:48 2015 -0500 @@ -0,0 +1,62 @@ +<?xml version="1.0"?> +<tool id="duplex" name="Du Novo: Make consensus reads" version="0.3"> + <description>from duplex sequencing alignments</description> + <requirements> + <requirement type="package" version="0.3">duplex</requirement> + <requirement type="set_environment">DUPLEX_DIR</requirement> + <!-- TODO: require Python 2.7 --> + </requirements> + <command detect_errors="exit_code"><![CDATA[ + python \$DUPLEX_DIR/dunovo.py -r $min_reads -q $qual_thres -F $qual_format $input + #if $keep_sscs: + --sscs-file $sscs + #end if + > duplex.fa + && awk -f \$DUPLEX_DIR/utils/outconv.awk -v target=1 duplex.fa > $output1 + && awk -f \$DUPLEX_DIR/utils/outconv.awk -v target=2 duplex.fa > $output2 + ]]> + </command> + <inputs> + <param name="input" type="data" format="tabular" label="Aligned input reads" /> + <param name="min_reads" type="integer" value="3" min="1" label="Minimum reads per family" help="Single-strand families with fewer than this many reads will be skipped."/> + <param name="qual_thres" type="integer" value="25" min="1" label="Minimum base quality" help="Bases with a PHRED score less than this will not be counted in the consensus making."/> + <param name="qual_format" type="select" label="FASTQ format" help="Solexa should also work for Illumina 1.3+ and 1.5+, and Sanger should work for Illumina 1.8+"> + <option value="sanger" selected="true">Sanger (PHRED 0 = "!")</option> + <option value="solexa">Solexa (PHRED 0 = "@")</option> + </param> + <param name="keep_sscs" type="boolean" truevalue="true" falsevalue="" label="Output single-strand consensus sequences" /> + </inputs> + <outputs> + <data name="output1" format="fasta" label="$tool.name on $on_string (mate 1)"/> + <data name="output2" format="fasta" label="$tool.name on $on_string (mate 2)"/> + <data name="sscs" format="fasta" label="$tool.name on $on_string (SSCS)"> + <filter>keep_sscs</filter> + </data> + </outputs> + <tests> + <test> + <param name="input" value="families.msa.tsv"/> + <output name="output1" file="families.cons_1.fa"/> + <output name="output2" file="families.cons_2.fa"/> + </test> + </tests> + <help> + +**What it does** + +This is for processing duplex sequencing data. It creates single-strand and duplex consensus reads from aligned read families. + +----- + +**Input** + +This expects the output format of the "Align families" tool. + +----- + +**Output** + +This will output final, duplex consensus reads in two FASTA files (first and second reads in the pairs). Optionally, you can save the single-strand reads too, in a separate FASTA file. + + </help> +</tool>
--- a/duplex.xml Tue Dec 08 08:59:27 2015 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,61 +0,0 @@ -<?xml version="1.0"?> -<tool id="duplex" name="Du Novo: Make consensus reads" version="0.2"> - <description>from duplex sequencing alignments</description> - <requirements> - <requirement type="package" version="0.2">duplex</requirement> - <requirement type="set_environment">DUPLEX_DIR</requirement> - </requirements> - <command detect_errors="exit_code"><![CDATA[ - python \$DUPLEX_DIR/duplex.py -r $min_reads -q $qual_thres -F $qual_format $input - #if $keep_sscs: - --sscs-file $sscs - #end if - > duplex.fa - && awk -f \$DUPLEX_DIR/utils/outconv.awk -v target=1 duplex.fa > $output1 - && awk -f \$DUPLEX_DIR/utils/outconv.awk -v target=2 duplex.fa > $output2 - ]]> - </command> - <inputs> - <param name="input" type="data" format="tabular" label="Aligned input reads" /> - <param name="min_reads" type="integer" value="3" min="1" label="Minimum reads per family" help="Single-strand families with fewer than this many reads will be skipped."/> - <param name="qual_thres" type="integer" value="25" min="1" label="Minimum base quality" help="Bases with a PHRED score less than this will not be counted in the consensus making."/> - <param name="qual_format" type="select" label="FASTQ format" help="Solexa should also work for Illumina 1.3+ and 1.5+, and Sanger should work for Illumina 1.8+"> - <option value="sanger" selected="true">Sanger (PHRED 0 = "!")</option> - <option value="solexa">Solexa (PHRED 0 = "@")</option> - </param> - <param name="keep_sscs" type="boolean" truevalue="true" falsevalue="" label="Output single-strand consensus sequences" /> - </inputs> - <outputs> - <data name="output1" format="fasta" label="$tool.name on $on_string (mate 1)"/> - <data name="output2" format="fasta" label="$tool.name on $on_string (mate 2)"/> - <data name="sscs" format="fasta" label="$tool.name on $on_string (SSCS)"> - <filter>keep_sscs</filter> - </data> - </outputs> - <tests> - <test> - <param name="input" value="families.msa.tsv"/> - <output name="output1" file="families.cons_1.fa"/> - <output name="output2" file="families.cons_2.fa"/> - </test> - </tests> - <help> - -**What it does** - -This is for processing duplex sequencing data. It creates single-strand and duplex consensus reads from aligned read families. - ------ - -**Input** - -This expects the output format of the "Align families" tool. - ------ - -**Output** - -This will output final, duplex consensus reads in two FASTA files (first and second reads in the pairs). Optionally, you can save the single-strand reads too, in a separate FASTA file. - - </help> -</tool>
--- a/make_families.xml Tue Dec 08 08:59:27 2015 -0500 +++ b/make_families.xml Mon Dec 21 14:47:48 2015 -0500 @@ -1,8 +1,8 @@ <?xml version="1.0"?> -<tool id="make_families" name="Du Novo: Make families" version="0.2"> +<tool id="make_families" name="Du Novo: Make families" version="0.3"> <description>of duplex sequencing reads</description> <requirements> - <requirement type="package" version="0.2">duplex</requirement> + <requirement type="package" version="0.3">duplex</requirement> <requirement type="set_environment">DUPLEX_DIR</requirement> </requirements> <!-- TODO: Add dependency on coreutils to get paste? -->
--- a/tool_dependencies.xml Tue Dec 08 08:59:27 2015 -0500 +++ b/tool_dependencies.xml Mon Dec 21 14:47:48 2015 -0500 @@ -3,10 +3,10 @@ <package name="mafft" version="7.221"> <repository changeset_revision="d71e007323d4" name="mafft" owner="rnateam" toolshed="https://toolshed.g2.bx.psu.edu" /> </package> - <package name="duplex" version="0.2"> + <package name="duplex" version="0.3"> <install version="1.0"> <actions> - <action type="download_by_url">https://github.com/makrutenko/duplex/archive/v0.2.tar.gz</action> + <action type="download_by_url">https://github.com/makrutenko/dunovo/archive/v0.3.tar.gz</action> <action type="shell_command">make</action> <action type="move_directory_files"> <source_directory>.</source_directory>