# HG changeset patch
# User nick
# Date 1487413629 18000
# Node ID 548c63893c70ec89e421660ea9e2bac9d3207f0c
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'fcd6f371638bc29da6dbe22f939f7a5a7f360481\n'-dirty
diff -r 000000000000 -r 548c63893c70 align_families.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/align_families.xml Sat Feb 18 05:27:09 2017 -0500
@@ -0,0 +1,80 @@
+
+
+ of duplex sequencing reads
+
+ mafft
+ dunovo
+
+
+ align_families.py -p \${GALAXY_SLOTS:-1} '$input' > '$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. It does a multiple sequence alignment on each (single-stranded) family of reads.
+
+-----
+
+**Input**
+
+This expects the output format of the "Make families" tool.
+
+-----
+
+**Output**
+
+The output is a tabular file where each line corresponds to a (single) read.
+
+The columns are::
+
+ 1: barcode (both tags)
+ 2: tag order in barcode ("ab" or "ba")
+ 3: read mate ("1" or "2")
+ 4: read name
+ 5: read sequence, aligned ("-" for gaps)
+ 6: read quality scores, aligned (" " for gaps)
+
+-----
+
+**Alignments**
+
+The alignments are done using MAFFT, specifically the command
+::
+
+ $ mafft --nuc --quiet family.fa > family.aligned.fa
+
+
+
diff -r 000000000000 -r 548c63893c70 correct_barcodes.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/correct_barcodes.xml Sat Feb 18 05:27:09 2017 -0500
@@ -0,0 +1,57 @@
+
+
+ of duplex sequencing reads
+
+ bowtie2
+ samtools
+ networkx
+ dunovo
+
+
+ correct-barcodes.sh -d $dist -m $mapq -p $pos '$input' > '$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 000000000000 -r 548c63893c70 dunovo.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/dunovo.xml Sat Feb 18 05:27:09 2017 -0500
@@ -0,0 +1,75 @@
+
+
+ from duplex sequencing alignments
+
+ dunovo
+
+
+ dunovo.sh -r $min_reads -q $qual_thres -F $qual_format '$input' '$dcs1' '$dcs2'
+ #if $keep_sscs:
+ '$sscs1' '$sscs2'
+ #end if
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ keep_sscs
+
+
+ keep_sscs
+
+
+
+
+
+
+
+
+
+
+ @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. 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.
+
+
+
diff -r 000000000000 -r 548c63893c70 make_families.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/make_families.xml Sat Feb 18 05:27:09 2017 -0500
@@ -0,0 +1,95 @@
+
+
+ of duplex sequencing reads
+
+ dunovo
+
+
+ make-families.sh -t $taglen -i $invariant '$fastq1' '$fastq2' > '$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 tool is for processing raw duplex sequencing data, removing the barcodes and grouping by them into families of reads from the same fragment.
+
+-----
+
+**Output**
+
+The output will be a tabular file where each line corresponds to a pair of input reads.
+
+The columns are::
+
+ 1: barcode (both tags joined and ordered)
+ 2: tag order in barcode ("ab" or "ba")
+ 3: read1 name
+ 4: read1 sequence (minus the tag and invariant sequences)
+ 5: read1 quality scores (minus the same tag and invariant)
+ 6: read2 name
+ 7: read2 sequence (minus the tag and invariant sequences)
+ 8: read2 quality scores (minus the same tag and invariant)
+
+-----
+
+**Barcode creation**
+
+For each pair, the tool will remove the tag at the beginning of each read and create a barcode by concatenating the two tags. The order of the tags is determined by a string comparison so that it will make an identical barcode from pairs of either order. The original tag order will be noted in the second column.
+
+Since pairs from opposite strands will have the same tags, but in the reverse order, this produces the same barcode for reads from the same fragment, regardless of strand. Then a simple sort will group all reads from the same strand together, separated into strands by the different "order" values.
+
+Examples::
+
+ +---------------+-----------------+
+ | input tags | output |
+ +-------+-------+-------+---------+
+ | read1 | read2 | order | barcode |
+ +-------+-------+-------+---------+
+ | ATG | CCT | ab | ATGCCT |
+ +-------+-------+-------+---------+
+ | CCT | ATG | ba | ATGCCT |
+ +-------+-------+-------+---------+
+
+
+
diff -r 000000000000 -r 548c63893c70 tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Sat Feb 18 05:27:09 2017 -0500
@@ -0,0 +1,30 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ https://github.com/galaxyproject/dunovo/archive/v0.7.tar.gz
+ make
+
+ .
+ $INSTALL_DIR
+
+
+ $INSTALL_DIR
+
+
+
+
+