Mercurial > repos > iuc > sra_tools

comparison fastq_dump.xml @ 1:069a879beef7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit 8550e0c7389533bebc75d7a93b89a3e59fe77bcd
author iuc
date Tue, 17 May 2016 13:55:57 -0400
parents 20da3b075bbf
children 6aa2efbe5920
comparison
equal deleted inserted replaced
0:20da3b075bbf 1:069a879beef7
1 <tool id="fastq_dump" name="Extract reads" version="1.2.5"> 1 <tool id="fastq_dump" name="Extract reads" version="1.3.0">
2 <description>in FASTQ/A format from NCBI SRA.</description> 2 <description>in FASTQ/A format from NCBI SRA.</description>
3 <macros> 3 <macros>
4 <import>sra_macros.xml</import> 4 <import>sra_macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="requirements"/> 6 <expand macro="requirements"/>
8 <exit_code range="127" level="fatal" description="Could not locate fastq-dump binary"/> 8 <exit_code range="127" level="fatal" description="Could not locate fastq-dump binary"/>
9 </stdio> 9 </stdio>
10 <version_command>fastq-dump --version</version_command> 10 <version_command>fastq-dump --version</version_command>
11 <command> 11 <command>
12 <![CDATA[ 12 <![CDATA[
13
14 #if $input.input_select=="file_list":
15 for acc in `cat $input.file_list` ;
16 do
17 #elif $input.input_select=="accession_number":
18 acc="$input.accession" &&
19 #end if
20
21 #if $input.input_select=="file_list" or $input.input_select=="accession_number":
22 [ ""\$acc" =~ ^[E|S|D]RR[0-9]{1,}$" ] && (
23 #end if
24
13 ## Need to set the home directory to the current working directory, 25 ## Need to set the home directory to the current working directory,
14 ## else the tool tries to write to home/.ncbi and fails when used 26 ## else the tool tries to write to home/.ncbi and fails when used
15 ## with a cluster manager. 27 ## with a cluster manager.
16 export HOME=\$PWD && 28 export HOME=\$PWD &&
17 vdb-config --restore-defaults && 29 vdb-config --restore-defaults &&
22 ## Do not use prefetch if region is specified, to avoid downloading 34 ## Do not use prefetch if region is specified, to avoid downloading
23 ## the complete sra file. 35 ## the complete sra file.
24 #if ( str( $adv.region ) == "" ) and ( str( $adv.minID ) == "" ) and ( str( $adv.maxID ) == "" ): 36 #if ( str( $adv.region ) == "" ) and ( str( $adv.minID ) == "" ) and ( str( $adv.maxID ) == "" ):
25 ASCP_PATH=`command -v ascp` && 37 ASCP_PATH=`command -v ascp` &&
26 ASCP_KEY=`dirname \$ASCP_PATH`/asperaweb_id_dsa.openssh || true && 38 ASCP_KEY=`dirname \$ASCP_PATH`/asperaweb_id_dsa.openssh || true &&
27 prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" $input.accession && 39 prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" "\$acc" &&
28 ## Duplicate vdb-config, in case settings changed between prefetch and 40 ## Duplicate vdb-config, in case settings changed between prefetch and
29 ## dump command. 41 ## dump command.
30 vdb-config -s "/repository/user/main/public/root=\$PWD" && 42 vdb-config -s "/repository/user/main/public/root=\$PWD" &&
31 #end if 43 #end if
32 fastq-dump --accession "$input.accession" 44 fastq-dump --accession "\$acc"
45 --split-files
33 #end if 46 #end if
34 --defline-seq '@\$sn[_\$rn]/\$ri' 47 --defline-seq '@\$sn[_\$rn]/\$ri'
35 --stdout 48
36 $adv.split 49 $adv.split
37 #if str( $adv.alignments ) == "aligned": 50 #if str( $adv.alignments ) == "aligned":
38 --aligned 51 --aligned
39 #end if 52 #end if
40 #if str( $adv.alignments ) == "unaligned": 53 #if str( $adv.alignments ) == "unaligned":
61 #if str( $adv.matepairDist ) != "": 74 #if str( $adv.matepairDist ) != "":
62 --matepair-distance "$adv.matepairDist" 75 --matepair-distance "$adv.matepairDist"
63 #end if 76 #end if
64 $adv.clip 77 $adv.clip
65 $adv.skip_technical 78 $adv.skip_technical
79
66 #if str( $outputformat ) == "fasta": 80 #if str( $outputformat ) == "fasta":
67 --fasta 81 --fasta
68 #end if 82 #end if
69 #if $input.input_select=="file": 83 #if $input.input_select=="file":
84 --stdout
70 "$input.file" > "$output_file" 85 "$input.file" > "$output_file"
86 #elif $input.input_select=="file_list":
87 "\$acc"
71 #else: 88 #else:
72 "$input.accession" > "$output_accession" 89 --stdout
73 #end if 90 "\$acc" > "$output_accession" )
91 #end if
92
93 #if $input.input_select=="file_list":
94 ) ; done
95
96 ;
97
98
99 #if str( $outputformat ) == "fasta":
100
101 for f in *_2.fasta ; do mv "\$f" "`basename \$f _2.fasta`_reverse.fasta" ; mv "`basename \$f _2.fasta`_1.fasta" "`basename \$f _2.fasta`_forward.fasta" ; done &&
102 for f in *_1.fasta; do mv "\$f" "`basename \$f _1.fasta`__single.fasta"; done
103
104 #else:
105
106 for f in *_2.fastq ; do mv "\$f" "`basename \$f _2.fastq`_reverse.fastq" ; mv "`basename \$f _2.fastq`_1.fastq" "`basename \$f _2.fastq`_forward.fastq" ; done &&
107 for f in *_1.fastq; do mv "\$f" "`basename \$f _1.fastq`__single.fastq"; done
108
109 #end if
110
111
112
113
114
115 #end if
116
117
74 ]]> 118 ]]>
75 </command> 119 </command>
76 <inputs> 120 <inputs>
77 <expand macro="input_conditional"/> 121 <expand macro="input_conditional"/>
78 <param name="outputformat" type="select" label="select output format"> 122 <param name="outputformat" type="select" label="select output format">
103 </param> 147 </param>
104 <param name="skip_technical" type="boolean" truevalue="--skip-technical" falsevalue="" checked="False" label="Dump only biological reads"/> 148 <param name="skip_technical" type="boolean" truevalue="--skip-technical" falsevalue="" checked="False" label="Dump only biological reads"/>
105 </section> 149 </section>
106 </inputs> 150 </inputs>
107 <outputs> 151 <outputs>
108 <data format="fastq" name="output_accession" label="${input.accession}.${outputformat}"> 152 <collection name="list_paired" type="list:paired" label="Pair-end Fast(q|a)">
109 <filter>input['input_select'] == "accession_number"</filter> 153 <filter>input['input_select'] == "file_list"</filter>
110 <change_format> 154 <!-- Use named regex group to grab pattern
111 <when input="outputformat" value="fasta" format="fasta"/> 155 <identifier_0>_<identifier_1>.fq. Here identifier_0 is the list
112 </change_format> 156 identifier in the nested collection and identifier_1 is either
113 </data> 157 forward or reverse (for instance samp1_forward.fq).
114 <data format="fastq" name="output_file" label="${input.file.name}.${outputformat}"> 158 -->
115 <filter>input['input_select'] == "file"</filter> 159 <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.fastq" ext="fastqsanger" visible="false" />
116 <change_format> 160 <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.fasta" ext="fasta" visible="false" />
117 <when input="outputformat" value="fasta" format="fasta"/> 161 </collection>
118 </change_format> 162 <collection name="output_collection" type='list' label="Single-end Fast(q|a)">
119 </data> 163 <filter>input['input_select'] == "file_list"</filter>
164 <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fastq" directory="." ext='fastqsanger'/>
165 <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fasta" directory="." ext='fasta'/>
166 </collection>
167 <data format="fastqsanger" name="output_accession" >
168 <filter>input['input_select'] == "accession_number"</filter>
169 <change_format>
170 <when input="outputformat" value="fasta" format="fasta"/>
171 </change_format>
172 </data>
173 <data format="fastqsanger" name="output_file" label="${input.file.name}.${outputformat}">
174 <filter>input['input_select'] == "file"</filter>
175 <change_format>
176 <when input="outputformat" value="fasta" format="fasta"/>
177 </change_format>
178 </data>
120 </outputs> 179 </outputs>
121 <tests> 180 <tests>
122 <test> 181 <test>
123 <param name="input_select" value="accession_number"/> 182 <param name="input_select" value="accession_number"/>
124 <param name="outputformat" value="fastqsanger"/> 183 <param name="outputformat" value="fastqsanger"/>
125 <param name="accession" value="SRR044777"/> 184 <param name="accession" value="SRR044777"/>
126 <param name="skip_technical" value="True"/> 185 <param name="skip_technical" value="True"/>
127 <output name="output_accession"> 186 <output name="output_accession">
128 <assert_contents> 187 <assert_contents>
129 <not_has_text text="rRNA_primer"/> 188 <not_has_text text="rRNA_primer"/>
130 <has_text text="F47USSH02GNP1D" /> 189 <has_text text="F47USSH02GNP1D" />
131 </assert_contents> 190 </assert_contents>
132 </output> 191 </output>
133 </test> 192 </test>
134 <test> 193 <test>
135 <param name="input_select" value="accession_number"/> 194 <param name="input_select" value="accession_number"/>
136 <param name="outputformat" value="fastqsanger"/> 195 <param name="outputformat" value="fastqsanger"/>
137 <param name="accession" value="SRR925743"/> 196 <param name="accession" value="SRR925743"/>
138 <param name="maxID" value="5"/> 197 <param name="maxID" value="5"/>
139 <output name="output_accession" file="fastq_dump_result.fastq" ftype="fastq"/> 198 <output name="output_accession" file="fastq_dump_result.fastq" ftype="fastqsanger"/>
140 </test> 199 </test>
141 </tests> 200 </tests>
142 <help> 201 <help>
143 This tool extracts reads from SRA archives using fastq-dump. 202 This tool extracts reads from SRA archives using fastq-dump.
144 The fastq-dump program is developed at NCBI, and is available at 203 The fastq-dump program is developed at NCBI, and is available at
145 http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software. 204 http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software.
205
206 NB: Single-end or pair-end collections may be empty if given SRRs LibraryLayout contains only either SINGLE or PAIRED respectively
146 @SRATOOLS_ATTRRIBUTION@ 207 @SRATOOLS_ATTRRIBUTION@
147 </help> 208 </help>
148 <expand macro="citation"/> 209 <expand macro="citation"/>
149 </tool> 210 </tool>