Mercurial > repos > crs4 > edena

comparison edena_ovl_wrapper.xml @ 2:b8c6a38530eb draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Support Edena v. 3.131028 (new <version_command>, official overlapping log file, covStats output file removed, -lph and -sph options instead of -peHorizon). Use $GALAXY_SLOTS instead of $EDENA _SITE_OPTIONS. Directly call edena, remove edena_ovl_wrapper.py and edena_ass_wrapper.py . Discard stderr instead of redirecting to stdout. Do not redirect stdout to logfile. Add readme.rst .
author crs4
date Fri, 31 Jan 2014 12:08:21 -0500
parents cd6cc6d76708
children
comparison
equal deleted inserted replaced
1:cd6cc6d76708 2:b8c6a38530eb
1 <tool id="edena_ovl_wrapper" name="Edena (overlapping)" version="0.2.2"> 1 <tool id="edena_ovl_wrapper" name="Edena (overlapping)" version="0.3">
2 <description></description> 2 <description></description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="3.130110">edena</requirement> 4 <requirement type="package" version="3.131028">edena</requirement>
5 </requirements> 5 </requirements>
6 <version_command>edena -v</version_command> 6 <version_command>edena | head -n 1</version_command>
7 <command interpreter="python"> 7 <command>
8 edena_ovl_wrapper.py 8 edena
9 \${EDENA_SITE_OPTIONS:---nThreads 2} 9 -nThreads \${GALAXY_SLOTS:-2}
10 #if $input_selection.input == "unpaired_file" 10 #if $input_selection.input == "unpaired_file"
11 -r
11 #for $ui in $input_selection.unpaired_input 12 #for $ui in $input_selection.unpaired_input
12 --unpaired_input=${ui.unpaired_file} 13 ${ui.unpaired_file}
13 #end for 14 #end for
14 #elif $input_selection.input == "dr_pairs" 15 #elif $input_selection.input == "dr_pairs"
16 -DRpairs
15 #for $dpi in $input_selection.dr_pairs_input 17 #for $dpi in $input_selection.dr_pairs_input
16 --dr_pair_1=${dpi.dr_pair_1} 18 ${dpi.dr_pair_1} ${dpi.dr_pair_2}
17 --dr_pair_2=${dpi.dr_pair_2}
18 #end for 19 #end for
19 #elif $input_selection.input == "rd_pairs" 20 #elif $input_selection.input == "rd_pairs"
21 -RDpairs
20 #for $rpi in $input_selection.rd_pairs_input 22 #for $rpi in $input_selection.rd_pairs_input
21 --rd_pair_1=${rpi.rd_pair_1} 23 ${rpi.rd_pair_1} ${rpi.rd_pair_2}
22 --rd_pair_2=${rpi.rd_pair_2}
23 #end for 24 #end for
24 #end if 25 #end if
25 #if str($minOlap) 26 #if str($minOlap)
26 --minOlap=$minOlap 27 -M $minOlap
27 #end if 28 #end if
28 #if str($readsTruncation) 29 #if str($readsTruncation)
29 --readsTruncation=$readsTruncation 30 -t $readsTruncation
30 #end if 31 #end if
31 --output=$output 32 2&gt;/dev/null ## need to discard stderr because edena writes some progress info there (e.g. "Computing overlaps >=30...")
32 --logfile=$logfile
33 </command> 33 </command>
34 34
35 <inputs> 35 <inputs>
36 <conditional name="input_selection"> 36 <conditional name="input_selection">
37 <param name="input" type="select" label="Select input type"> 37 <param name="input" type="select" label="Select input type">
38 <option value="unpaired_file">Unpaired files</option> 38 <option value="unpaired_file">Unpaired files</option>
39 <option value="dr_pairs">Direct-reverse paired-end files</option> 39 <option value="dr_pairs">Paired-end (forward-reverse) files</option>
40 <option value="rd_pairs">Reverse-direct paired-end files</option> 40 <option value="rd_pairs">Mate-pair (reverse-forward) files</option>
41 </param> 41 </param>
42 42
43 <when value="unpaired_file"> 43 <when value="unpaired_file">
44 <repeat name="unpaired_input" title="Unpaired inputs (-r)" min="1"> 44 <repeat name="unpaired_input" title="Unpaired input" help="(-r)" min="1">
45 <param name="unpaired_file" type="data" format="fasta,fastq" label="Unpaired file" help="FASTA or FASTQ format" /> 45 <param name="unpaired_file" type="data" format="fasta,fastq" label="Unpaired file" help="FASTA or FASTQ format" />
46 </repeat> 46 </repeat>
47 </when> 47 </when>
48 48
49 <when value="dr_pairs"> 49 <when value="dr_pairs">
50 <repeat name="dr_pairs_input" title="DR paired-end inputs (-DRpairs, -paired)" min="1"> 50 <repeat name="dr_pairs_input" title="Paired-end (forward-reverse) file" help="(-DRpairs, -paired)" min="1">
51 <param name="dr_pair_1" type="data" format="fasta,fastq" label="DR paired-end file 1" help="FASTA or FASTQ format" /> 51 <param name="dr_pair_1" type="data" format="fasta,fastq" label="Paired-end file 1" help="FASTA or FASTQ format" />
52 <param name="dr_pair_2" type="data" format="fasta,fastq" label="DR paired-end file 2" help="FASTA or FASTQ format" /> 52 <param name="dr_pair_2" type="data" format="fasta,fastq" label="Paired-end file 2" help="FASTA or FASTQ format" />
53 </repeat> 53 </repeat>
54 </when> 54 </when>
55 55
56 <when value="rd_pairs"> 56 <when value="rd_pairs">
57 <repeat name="rd_pairs_input" title="RD paired-end inputs (-RDpairs, -matePairs)" min="1"> 57 <repeat name="rd_pairs_input" title="Mate-pair (reverse-forward) file" help="(-RDpairs, -matePairs)" min="1">
58 <param name="rd_pair_1" type="data" format="fasta,fastq" label="RD paired-end file 1" help="FASTA or FASTQ format" /> 58 <param name="rd_pair_1" type="data" format="fasta,fastq" label="Mate-pair file 1" help="FASTA or FASTQ format" />
59 <param name="rd_pair_2" type="data" format="fasta,fastq" label="RD paired-end file 2" help="FASTA or FASTQ format" /> 59 <param name="rd_pair_2" type="data" format="fasta,fastq" label="Mate-pair file 2" help="FASTA or FASTQ format" />
60 </repeat> 60 </repeat>
61 </when> 61 </when>
62 </conditional> 62 </conditional>
63 63
64 <param name="minOlap" type="integer" value="" optional="true" label="Minimum overlap size to compute (-M)" help="If not specified, this value is set to half of the reads length. When the sequencing coverage is sufficient, you can increase this value which will reduce the computational time. Edena will compute the overlaps whose sizes range from this value to the reads length." /> 64 <param name="minOlap" type="integer" value="" optional="true" label="Minimum overlap size to compute (-M)" help="If not specified, this value is set to half of the reads length. When the sequencing coverage is sufficient, you can increase this value which will reduce the computational time. Edena will compute the overlaps whose sizes range from this value to the reads length." />
65 65
66 <param name="readsTruncation" type="integer" value="" optional="true" label="3' end reads truncation (-t)" help="Use this option to truncate the 3’end of the reads such that the resulting length is the inserted value. You may consider reads truncation since it can significantly improve the assembly. Since Edena computes exact overlaps, only error free reads can take part to the assembly. Since errors are likely to occur at the 3’ ends, shortening the reads by some nucleotides may increase the number of errors-free reads in the dataset, and thus increase the assembly performance." /> 66 <param name="readsTruncation" type="integer" value="" optional="true" label="3' end reads truncation (-t)" help="Use this option to truncate the 3’end of the reads to the specified length. You may consider reads truncation since it can significantly improve the assembly. Since Edena computes exact overlaps, only error free reads can take part to the assembly. Since errors are likely to occur at the 3’ ends, shortening the reads by some nucleotides may increase the number of errors-free reads in the dataset, and thus increase the assembly performance." />
67 67
68 </inputs> 68 </inputs>
69 69
70 <outputs> 70 <outputs>
71 <data name="logfile" format="txt" label="${tool.name} on ${on_string}: log" /> 71 <data name="logfile" format="txt" label="${tool.name} on ${on_string}: log" from_work_dir="out_overlapping.log" />
72 <data name="output" format="ovl" label="${tool.name} on ${on_string}: overlapping" /> 72 <data name="output" format="ovl" label="${tool.name} on ${on_string}: overlapping" from_work_dir="out.ovl" />
73 </outputs> 73 </outputs>
74 74
75 <tests> 75 <tests>
76 76
77 </tests> 77 </tests>
78 <help> 78 <help>
79 **What it does** 79 **What it does**
80 80
81 Edena is an overlaps graph based short reads assembler and is suited to Illumina GA reads. An assembly with Edena is a two step process: overlapping and assembling. 81 Edena is an overlaps graph based short reads assembler and is suited to Illumina GA reads. This program requires the reads to be all the same length, as Illumina GA reads are. This is due to historical reasons and because it greatly simplifies several computational steps. 454 or Sanger reads are therefore not suited to Edena. If you provide multiple files with different read lengths, Edena will trim the 3’ end of the reads so that the reads are all the same length as the shortest reads in the file.
82
83 An assembly with Edena is a two step process: overlapping and assembling.
82 84
83 In the overlapping step, the reads files are provided to the program which computes the transitively reduced overlaps graph. This structure is then stored together with the sequence reads in the overlapping file. 85 In the overlapping step, the reads files are provided to the program which computes the transitively reduced overlaps graph. This structure is then stored together with the sequence reads in the overlapping file.
84 86
85 Edena can accept both unpaired and paired files, FASTQ and FASTA format. Note that for technical reasons, all reads are required to be of the same length. You can however provide the program with different files containing different reads length. In such case, Edena will trim the 3’ ends of the longer reads so that they fit the shorter length. It is however required that reads within each individual file are of the same length (as Illumina GA reads are). By default all overlaps with a minimum size corresponding to half of the reads length are computed. This is quite conservative. Provided enough coverage, this value can be increased (option -M) to reduce the memory requirements. 87 Edena can accept both unpaired and paired files, FASTQ and FASTA format. Note that for technical reasons, all reads are required to be of the same length. You can however provide the program with different files containing different reads length. In such case, Edena will trim the 3’ ends of the longer reads so that they fit the shorter length. It is however required that reads within each individual file are of the same length (as Illumina GA reads are). By default all overlaps with a minimum size corresponding to half of the reads length are computed. This is quite conservative. Provided enough coverage, this value can be increased (option -M) to reduce the memory requirements.
86 88