comparison hicstuff_pipeline.xml @ 0:1efd17d2bfdb draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hicstuff commit 021a99a3416955cd6906e95245da604fda92b255
author iuc
date Fri, 25 Nov 2022 11:32:55 +0000
parents
children 6956f0783d77
comparison
equal deleted inserted replaced
-1:000000000000 0:1efd17d2bfdb
1 <tool id="hicstuff_pipeline" name="hicstuff full pipeline" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
2 <description>generates a Hi-C contact matrix</description>
3 <macros>
4 <import>macros.xml</import>
5 <token name="@VERSION_SUFFIX@">0</token>
6 </macros>
7 <expand macro="requirements" />
8 <command detect_errors="exit_code"><![CDATA[
9 hicstuff pipeline
10 --genome '$genome'
11 --outdir results
12 --aligner $aligner
13 $circular
14 $duplicates
15 --enzyme '$enzyme'
16 $filter
17 --mapping $mapping
18 --matfmt $matfmt
19 --quality-min $quality_min
20 --size $size
21 --threads \${GALAXY_SLOTS:-1}
22 #if $paired_cond.paired_select == "paired"
23 '$paired_cond.reads.forward'
24 '$paired_cond.reads.reverse'
25 #else
26 '$forward_reads'
27 '$reverse_reads'
28 #end if
29 ]]></command>
30 <inputs>
31 <param type="data" name="genome" format="fasta,fasta.gz" label="Genome fasta file"/>
32 <conditional name="paired_cond">
33 <param name="paired_select" type="select" label="Paired reads">
34 <option value="paired">In a dataset pair</option>
35 <option value="separate">In two separate datasets</option>
36 </param>
37 <when value="paired">
38 <param name="reads" type="data_collection" collection_type="paired" format="fastqsanger,fastqsanger.gz" label="Paired reads"/>
39 </when>
40 <when value="separate">
41 <param name="forward_reads" type="data" format="fastqsanger,fastqsanger.gz" label="Forward reads"/>
42 <param name="reverse_reads" type="data" format="fastqsanger,fastqsanger.gz" label="Reverse reads"/>
43 </when>
44 </conditional>
45 <param argument="--aligner" type="select" label="Alignment software to use" help="Minimap2 should only be used for reads > 100 bp">
46 <option value="bowtie2" selected="true">bowtie2</option>
47 <option value="minimap2">minimap2</option>
48 <option value="bwa">bwa</option>
49 </param>
50 <param argument="--circular" type="boolean" truevalue="--circular" falsevalue="" label="Circular genome"/>
51 <param argument="--duplicates" type="boolean" truevalue="--duplicates" falsevalue="" label="Removes PCR duplicates" help="PCR duplicates are defined as sets of pairs having identical mapping positions for both reads."/>
52 <param argument="--enzyme" type="text" value="5000" label="Bin size or enzyme" help="Restriction enzyme or 'mnase' if a string, or chunk size (i.e. resolution) if a number. Can also be multiple comma-separated enzymes."/>
53 <param argument="--filter" type="boolean" truevalue="--filter" falsevalue="" label="Filters out spurious 3C events, such as self religations or undigested fragments" help="This is only really useful at very fine resolutions (1-2kb) and not needed most of the time. This option is only meaningful when --enzyme is given a restriction enzyme and not a bin size."/>
54 <param argument="--mapping" type="select" label="Parameter of mapping" help="'normal': Directly map reads without any process. 'iterative': Map reads iteratively using iteralign, by truncating reads to 20bp and then repeatedly extending to align them. 'cutsite': Cut reads at the religation sites of the given enzyme using cutsite, create new pairs of reads and then align them ; enzyme is required">
55 <option value="normal" selected="true">normal</option>
56 <option value="iterative">iterative</option>
57 <option value="cutsite">cutsite</option>
58 </param>
59 <param argument="--matfmt" type="select" label="Format of the output sparse matrix" help="Available formats are bg2 (bedgraph2d), graal (graal-compatible plain text COO format) and cool, a binary format that is probably the most appropriate for large genomes.">
60 <option value="bg2">bg2</option>
61 <option value="cool">cool</option>
62 <option value="graal" selected="true">graal</option>
63 </param>
64 <param argument="--quality-min" type="integer" value="30" label="Minimum mapping quality for selecting contacts"/>
65 <param argument="--size" type="integer" value="0" label="Minimum size threshold to consider contigs. Keep all contigs by default."/>
66 </inputs>
67 <outputs>
68 <data name="abs_fragments_contacts_weighted" from_work_dir="./results/abs_fragments_contacts_weighter.txt" format="tabular"/>
69 <data name="fragments_list" from_work_dir="./results/fragments_list.txt" format="tabular"/>
70 <data name="info_contigs" from_work_dir="./results/info_contigs.txt" format="tabular"/>
71 </outputs>
72 <tests>
73 <test>
74 <param name="genome" value="seq.fa.gz" />
75 <param name="paired_cond|paired_select" value="separate"/>
76 <param name="paired_cond|forward_reads" value="sample.reads_for.fastq.gz" />
77 <param name="paired_cond|reverse_reads" value="sample.reads_rev.fastq.gz" />
78 <output name="info_contigs" file="info_contigs.txt"/>
79 <assert_stderr>
80 <has_text text="Contact map generated" />
81 </assert_stderr>
82 </test>
83 </tests>
84 <help><![CDATA[
85
86 hicstuff is a toolkit to generate and manipulate Hi-C matrices.
87
88 The "hicstuff full pipeline" tool generates a Hi-C contact matrix.
89 Output files can be used with instaGRAAL downstream.
90
91 -----------
92 Input files
93 -----------
94 * the fasta genome file
95 * forward reads
96 * reverse reads
97
98 ------------
99 Output files
100 ------------
101 * abs_fragments_contacts_weighter.txt: Sparse matrix file with 3 columns the rows, column and values of nonzero pixels. The first row contains the shape and total number of nonzero pixels in the matrix.
102 * fragments_list.txt: Contains genomic coordinates of the matrix bins (row/columns).
103 * info_contigs.txt: Contains chromosome names, theirs length and number of bins.
104
105 ]]></help>
106 <expand macro="citations" />
107 </tool>