# HG changeset patch # User nick # Date 1486154238 18000 # Node ID 8ef925264516a527bcfe582f3f618ff625755c98 # Parent 53cf867b305b2d52d1e5f5d95df76d8655d3c8e8 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'3eab56b30cc9d644798a290017bcc1188f028af8\n'-dirty diff -r 53cf867b305b -r 8ef925264516 align_families.xml --- a/align_families.xml Thu Feb 02 19:50:18 2017 -0500 +++ b/align_families.xml Fri Feb 03 15:37:18 2017 -0500 @@ -1,9 +1,9 @@ - + of duplex sequencing reads mafft - duplex + duplex DUPLEX_DIR diff -r 53cf867b305b -r 8ef925264516 correct_barcodes.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/correct_barcodes.xml Fri Feb 03 15:37:18 2017 -0500 @@ -0,0 +1,60 @@ + + + of duplex sequencing reads + + bowtie2 + samtools + duplex + DUPLEX_DIR + + + bash "\$DUPLEX_DIR/baralign.sh" '$input' refdir barcodes.bam + && samtools view -f 256 barcodes.bam + | python "\$DUPLEX_DIR/correct.py" -d $dist -m $mapq -p $pos '$input' refdir/barcodes.fa + | sort > '$output' + + + + + + + + + + + + @article{Stoler2016, + author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton}, + doi = {10.1186/s13059-016-1039-4}, + issn = {1474-760X}, + journal = {Genome biology}, + number = {1}, + pages = {180}, + pmid = {27566673}, + publisher = {Genome Biology}, + title = {{Streamlined analysis of duplex sequencing data with Du Novo.}}, + url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673}, + volume = {17}, + year = {2016} + } + + + +**What it does** + +This is for processing duplex sequencing data. This will correct duplex barcodes and create new, larger families. Errors in barcodes normally prevent them from being recognized as the same as the other barcodes in their family. Correcting these errors allows the original, full families to be reconstructed, saving reads which would otherwise be lost. This tool accomplishes this by doing an all vs. all alignment between the barcodes with bowtie2. This identifies ones which are identical except a few, small differences. + +----- + +**Input** + +This expects the output format of the "Make families" tool. + +----- + +**Output** + +The output format is the same as the input format, ready to be consumed by the "Align families" tool. + + + diff -r 53cf867b305b -r 8ef925264516 dunovo.xml --- a/dunovo.xml Thu Feb 02 19:50:18 2017 -0500 +++ b/dunovo.xml Fri Feb 03 15:37:18 2017 -0500 @@ -1,8 +1,8 @@ - + from duplex sequencing alignments - duplex + duplex DUPLEX_DIR diff -r 53cf867b305b -r 8ef925264516 make_families.xml --- a/make_families.xml Thu Feb 02 19:50:18 2017 -0500 +++ b/make_families.xml Fri Feb 03 15:37:18 2017 -0500 @@ -1,8 +1,8 @@ - + of duplex sequencing reads - duplex + duplex DUPLEX_DIR diff -r 53cf867b305b -r 8ef925264516 tool_dependencies.xml --- a/tool_dependencies.xml Thu Feb 02 19:50:18 2017 -0500 +++ b/tool_dependencies.xml Fri Feb 03 15:37:18 2017 -0500 @@ -3,7 +3,13 @@ - + + + + + + + https://github.com/galaxyproject/dunovo/archive/v0.5.tar.gz