0
|
1 <tool id="preprocess" name="preProcess" veision="1.0.0">
|
|
2 <description>Program for Raw data preprocess analysis, including 3' adapter triming, reads collaping, genome mapping and rfam non-miRNA analysis </description>
|
|
3
|
|
4 <requirements>
|
|
5 <requirement type="package" version="0.0.13">fastx_toolkit </requirement>
|
|
6 <requirement type="package" version="0.12.7">bowtie</requirement>
|
|
7 <requirement type="set_environment">SCRIPT_PATH</requirement>
|
|
8 <!--requirement type="package" version="3.0.1">R</requirement!-->
|
|
9 <requirement type="package" version="1.96">threads</requirement>
|
|
10 <requirement type="package" version="2.59">SVG</requirement>
|
|
11 <requirement type="package" version="2.1.8">ViennaRNA</requirement>
|
|
12 </requirements>
|
|
13
|
|
14 <!--command interpreter="perl">miPlant.pl -i $input -format $format -gfa $gfa -idx $index -pre $pre -mat $mat -rfam $rfam -idx2 $idx2 -D $D -a $a -M $M -min $min -max $max -mis $mis -e $e -f $f -v $v -r $r -dis $dis -flank $flank -mfe $mfe -t $t -o $output</command-->
|
|
15
|
|
16 <command interpreter="perl">preProcess.pl
|
|
17 ## Change this to accommodate the number of threads you have available.
|
|
18 -t \${GALAXY_SLOTS:-4}
|
|
19 -path \$SCRIPT_PATH
|
|
20
|
|
21 #for $j, $s in enumerate( $series )
|
|
22 ##rank_of_series=$j
|
|
23 -i ${s.input}
|
|
24 -tag ${s.tag}
|
|
25 #end for
|
|
26
|
|
27 ## Do or not annotate rfam non-miRNA RNAs
|
|
28 #if $nocoding.annotate_rfam == "yes":
|
|
29 ## prepare Rfam bowtie index
|
|
30 #set rfam_index_path = ''
|
|
31 #if str($nocoding.reference_rfam.source) == "history":
|
|
32 -rfam $nocoding.reference_rfam.own_file
|
|
33 #else:
|
|
34 #set rfam_index_path = $nocoding.reference_rfam.index.fields.path
|
|
35 -rfam ${rfam_index_path}.fa -idx2 $rfam_index_path
|
|
36 #end if
|
|
37 -v $nocoding.v
|
|
38 #end if
|
|
39
|
|
40 ## prepare bowtie index
|
|
41 #set index_path = ''
|
|
42 #if str($reference_genome.source) == "history":
|
|
43 #set index_path = 'genome'
|
|
44 -gfa $reference_genome.own_file
|
|
45 #else:
|
|
46 #set index_path = $reference_genome.index.fields.path
|
|
47 -gfa ${index_path}.fa -idx $index_path
|
|
48 #end if
|
|
49
|
|
50 -format $format -phred $phred -a $a -M $mapnt -min $min -max $max -mis $mismatch > run.log
|
|
51 </command>
|
|
52
|
|
53 <inputs>
|
|
54
|
|
55 <repeat name="series" title="Raw sequence data">
|
|
56 <param name="input" type="data" label="Raw data"/>
|
|
57 <param name="tag" type="text" data_ref="input" label="Sample name of raw data"/>
|
|
58 </repeat>
|
|
59
|
|
60 <!--param name="input" format="tabular" type="data" label="input config file" /-->
|
|
61
|
|
62 <param name="format" type="select" label="Raw data format" multiple="false">
|
|
63 <option value="fastq">Raw data is fastq. format</option>
|
|
64 <option value="fasta">Raw data is fasta. format</option>
|
|
65 </param>
|
|
66 <param name="phred" type="select" label="Input quals are Phred+64 or Phred+33" multiple="false">
|
|
67 <option value="64">Phred+64</option>
|
|
68 <option value="33" selected="true">Phred+33</option>
|
|
69 </param>
|
|
70
|
|
71 <!-- reference genome -->
|
|
72 <conditional name="reference_genome">
|
|
73 <param name="source" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
|
|
74 <option value="indexed">Use a built-in index</option>
|
|
75 <option value="history">Use one from the history</option>
|
|
76 </param>
|
|
77 <when value="indexed">
|
|
78 <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team">
|
|
79 <options from_data_table="bowtie_indexes">
|
|
80 <filter type="sort_by" column="2"/>
|
|
81 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
|
|
82 </options>
|
|
83 </param>
|
|
84 </when>
|
|
85 <when value="history">
|
|
86 <param name="own_file" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" />
|
|
87 </when>
|
|
88 </conditional>
|
|
89
|
|
90 <!--param name="gfa" type="data" label="genome sequence fasta file"/-->
|
|
91 <!--param type="data" name="index" label="genome sequence bowtie index"/-->
|
|
92 <param name="a" type="text" value="TGGAATTCTCGGGTGCCAAGG" label="3' adapter sequence" />
|
|
93 <param name="mapnt" type="integer" value="8" label="minimum adapter map nts" />
|
|
94 <param name="min" type="integer" value="19" label="Minimum microRNA length" />
|
|
95 <param name="max" type="integer" value="28" label="Maximum microRNA length" />
|
|
96 <param name="mismatch" type="integer" value="0" label="Number of allowed mismatches when mapping reads to genome" />
|
|
97
|
|
98 <conditional name="nocoding">
|
|
99 <param name="annotate_rfam" type="select" label="Annotate nocoding RNAs(excluding miRNA)">
|
|
100 <option value="yes" selected="true">yes</option>
|
|
101 <option value="no">no</option>
|
|
102 </param>
|
|
103 <when value="yes">
|
|
104 <!--param name="rfam" type="data" label="rfam sequence file" /-->
|
|
105 <conditional name="reference_rfam">
|
|
106 <param name="source" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
|
|
107 <option value="indexed">Use a built-in index</option>
|
|
108 <option value="history">Use one from the history</option>
|
|
109 </param>
|
|
110 <when value="indexed">
|
|
111 <param name="index" type="select" label="Select a reference" help="If your reference of interest is not listed, contact the Galaxy team">
|
|
112 <options from_data_table="rfam_bowtie_indexes">
|
|
113 <filter type="sort_by" column="2"/>
|
|
114 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
|
|
115 </options>
|
|
116 </param>
|
|
117 </when>
|
|
118 <when value="history">
|
|
119 <param name="own_file" type="data" format="fasta" metadata_name="dbkey" label="Select the reference" />
|
|
120 </when>
|
|
121 </conditional>
|
|
122
|
|
123 <param name="v" type="integer" value="0" label="Report end-to-end hits less than v mismatches for non-coding RNA annotation"/>
|
|
124 </when>
|
|
125 </conditional>
|
|
126
|
|
127
|
|
128
|
|
129 </inputs>
|
|
130
|
|
131 <outputs>
|
|
132 <data format="html" name="preprocess result" from_work_dir="preProcess/preprocessResult.html" label="${tool.name} on ${on_string}: preprocess result"/>
|
|
133
|
|
134 <data format="txt" name="clean FASTA data" from_work_dir="preProcess/preProcess_clean/clean_data.fa" label="${tool.name} on ${on_string}: clean FASTA data"/>
|
|
135
|
|
136 <data format="txt" name="genome mapping result" from_work_dir="preProcess/genome_match/genome_mapped.bwt" label="${tool.name} on ${on_string}: genome mapping result"/>
|
|
137 <data format="txt" name="genome mapped FASTA reads" from_work_dir="preProcess/genome_match/genome_mapped.fa" label="${tool.name} on ${on_string}: genome mapped FASTA reads"/>
|
|
138
|
|
139 <data format="txt" name="Rfam mapping result" from_work_dir="preProcess/rfam_match/rfam_mapped.bwt" label="${tool.name} on ${on_string}: Rfam mapping result">
|
|
140 <filter>(nocoding['annotate_rfam'] == 'yes')</filter>
|
|
141 </data>
|
|
142 <data format="txt" name="Rfam mapped FASTA file" from_work_dir="preProcess/rfam_match/rfam_mapped.fa" label="${tool.name} on ${on_string}: Rfam mapped FASTA file">
|
|
143 <filter>(nocoding['annotate_rfam'] == 'yes')</filter>
|
|
144 </data>
|
|
145 <data format="txt" name="Rfam not mapped FASTA file" from_work_dir="preProcess/rfam_match/rfam_not_mapped.fa" label="${tool.name} on ${on_string}: Rfam not mapped FASTA file">
|
|
146 <filter>(nocoding['annotate_rfam'] == 'yes')</filter>
|
|
147 </data>
|
|
148 <data format="txt" name="input config" from_work_dir="preProcess/input_config" label="${tool.name} on ${on_string}: input config"/>
|
|
149
|
|
150 </outputs>
|
|
151
|
|
152 <help>
|
|
153
|
|
154 </help>
|
|
155 </tool>
|