Mercurial > repos > iuc > rnaspades
comparison rnaspades.xml @ 6:b66de1e9abfb draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/spades commit 8734db131db6f76697b500b30f18ee7723d61813"
author | iuc |
---|---|
date | Sun, 23 Jan 2022 21:32:25 +0000 |
parents | 1035adb112c0 |
children | 675ee1aa5952 |
comparison
equal
deleted
inserted
replaced
5:1035adb112c0 | 6:b66de1e9abfb |
---|---|
1 <tool id="rnaspades" name="rnaSPAdes" version="3.9.0.3"> | 1 <tool id="rnaspades" name="rnaSPAdes" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01"> |
2 <description>assembler for RNA-Seq data</description> | 2 <description>de novo transcriptome assembler</description> |
3 <xrefs> | 3 <macros> |
4 <xref type="bio.tools">rnaspades</xref> | 4 <import>macros.xml</import> |
5 </xrefs> | 5 </macros> |
6 <requirements> | 6 <expand macro="requirements"/> |
7 <requirement type="package" version="3.9.0">spades</requirement> | 7 <expand macro="stdio"/> |
8 </requirements> | 8 <expand macro="version_command"/> |
9 <command detect_errors="exit_code"> | 9 <command detect_errors="exit_code"><![CDATA[ |
10 <![CDATA[ | 10 |
11 | 11 #set $library = 1 |
12 if [ -n "\$GALAXY_MEMORY_MB" ]; then | 12 |
13 GALAXY_MEMORY_GB=\$(( GALAXY_MEMORY_MB / 1024 )); | 13 @PREPROCESS_INPUT_FILES_MAIN@ |
14 fi && | 14 #if $additional_reads.selector == 'true' |
15 | 15 @PREPROCESS_INPUT_FILES_ADDITIONAL@ |
16 rnaspades.py -o . | 16 #end if |
17 ## Forces unzipped output, faster | 17 @PREPROCESS_NANOPORE_PACBIO_FILES@ |
18 --disable-gzip-output | 18 @PREPROCESS_CONTIGS_FILES@ |
19 $draft $onlyassembler -t \${GALAXY_SLOTS:-4} -m \${GALAXY_MEMORY_GB:-250} $iontorrent -k $kmer | 19 @PREPROCESS_FL_RNA_FILES@ |
20 ## Sequence files, libraries | 20 |
21 #for $i, $library in enumerate( $libraries, start=1 ): | 21 |
22 #if str( $library.lib_type ) == "paired_end": | 22 ## run |
23 #set prefix = 'pe' | 23 rnaspades.py |
24 #elif str( $library.lib_type ) == "mate_paired": | 24 -o 'output' |
25 #set prefix = 'mp' | 25 @RESOURCES@ |
26 #elif str( $library.lib_type ) == "nxmate_paired": | 26 @INPUT_READS_MAIN@ |
27 #set prefix = 'nxmate' | 27 #if $additional_reads.selector == 'true' |
28 #else: | 28 @INPUT_READS_ADDITIONAL@ |
29 #set prefix = 'hqmp' | 29 #end if |
30 #end if | 30 ## additional reads |
31 --$prefix$i-$library.orientation | 31 @FL_RNA@ |
32 #for $file in $library.files | 32 @NANOPORE_PACBIO@ |
33 #if $file.file_type.type == "separate": | 33 @CONTIGS@ |
34 --$prefix$i-1 fastq:$file.file_type.fwd_reads | 34 ## parameter |
35 --$prefix$i-2 fastq:$file.file_type.rev_reads | 35 @KMER@ |
36 #elif $file.file_type.type == "interleaved": | 36 @PIPELINE_OPTIONS@ |
37 --$prefix$i-12 fastq:$file.file_type.interleaved_reads | 37 @PHREDOFFSET@ |
38 #elif $file.file_type.type == "unpaired": | 38 #if $ss != 'no' |
39 --$prefix$i-s fastq:$file.file_type.unpaired_reads | 39 --ss '$ss' |
40 #elif $file.file_type.type == "paired-collection": | 40 #end if |
41 --$prefix$i-1 fastq:$file.file_type.fastq_collection.forward | 41 ## postprocessing |
42 --$prefix$i-2 fastq:$file.file_type.fastq_collection.reverse | 42 @CORRECTED@ |
43 #end if | 43 ]]></command> |
44 #end for | |
45 #end for | |
46 #for $contig in $trusted_contigs: | |
47 #if $contig: | |
48 --trusted-contigs $contig.extension:$contig | |
49 #end if | |
50 #end for | |
51 #for $contig in $untrusted_contigs: | |
52 #if $contig: | |
53 --untrusted-contigs $contig.extension:$contig | |
54 #end if | |
55 #end for | |
56 ]]> | |
57 </command> | |
58 <inputs> | 44 <inputs> |
59 <param argument="--draft-assembly" checked="False" falsevalue="" label="Draft assembly. Faster, but more error-prone" name="draft" truevalue="--draft-assembly" type="boolean" /> | 45 <expand macro="input_files_all" format="fastq,fastq.gz,fastqsanger.gz,fasta,fasta.gz" label="FASTQ RNA-seq file(s)"/> |
60 <param argument="--only-assembler" checked="False" falsevalue="" label="Run only assembly? (without read error correction)" name="onlyassembler" truevalue="--only-assembler" type="boolean" /> | 46 <expand macro="input_additional_files_all" format="fastq,fastq.gz,fastqsanger.gz,fasta,fasta.gz" label="FASTQ RNA-seq file(s)"/> |
61 <param argument="--iontorrent" checked="False" falsevalue="" label="Libraries are IonTorrent reads?" name="iontorrent" truevalue="--iontorrent" type="boolean" /> | 47 <section name="arf" title="Additional read files"> |
62 <param argument="-k" max="127" label="k-mer size (must be odd and less than 128)" name="kmer" type="integer" value="55" /> | 48 <expand macro="flrna"/> |
63 <repeat help="It is not possible to specify only mate-pair libraries. Scaffolds are not produced if neither a paired-end nor a mate-pair library is provided." min="1" name="libraries" title="Libraries"> | 49 <expand macro="nanopore_pacbio"/> |
64 <param label="Library type" name="lib_type" type="select"> | 50 <expand macro="contigs"/> |
65 <option value="paired_end">Paired-end / Single reads</option> | 51 </section> |
66 <option value="mate_paired">Mate pairs</option> | 52 <expand macro="kmer" help="By default rnaSPAdes uses 2 k-mer sizes, which are automatically detected using read length (approximately one third and half of the maximal read length). We recommend not to change this parameter because smaller k-mer sizes typically result in multiple chimeric (misassembled) transcripts."/> |
67 <option value="high_mate_paired">High Quality Mate pairs</option> | 53 <expand macro="phred"/> |
68 <option value="nxmate_paired">Lucigen NxMate pairs</option> | 54 <param argument="--ss" type="select" label="Set strand specificity" help="rnaSPAdes supports strand-specific RNA-Seq datasets. Use 'RF' when first read in pair corresponds to reverse gene strand (antisense data, e.g. obtained via dUTP protocol) and 'FR' otherwise. If the dataset is single-end use 'FR' option in case when reads correspond to gene strand and 'RF' otherwise. Note: strand-specificity is not related and should not be confused with FR and RF orientation of paired reads. RNA-Seq paired-end reads typically have forward-reverse orientation, which is assumed by default and no additional options are needed"> |
69 </param> | 55 <option value="no" selected="true">Disabled</option> |
70 <param label="Orientation" name="orientation" type="select"> | 56 <option value="fr">FR (normal)</option> |
71 <option selected="true" value="fr">-> <- (fr)</option> | 57 <option value="rf">RF (antisense)</option> |
72 <option value="rf"><![CDATA[<- -> (rf)]]></option> | 58 </param> |
73 <option value="ff"><![CDATA[-> -> (ff)]]></option> | 59 <expand macro="pipeline_options"> |
74 </param> | 60 <option value="--iontorrent">Iontorrent: although rnaSPAdes supports IonTorrent reads, it was not sufficiently tested on such kind of data (--iontorrent)</option> |
75 <repeat min="1" name="files" title="Files"> | 61 </expand> |
76 <conditional name="file_type"> | 62 <param name="optional_output" type="select" multiple="true" optional="false" label="Select optional output file(s)" help="Only shown in history if selected here and generated by the specific run."> |
77 <param label="Select file format" name="type" type="select"> | 63 <option value="hft">Hard filtered transcripts</option> |
78 <option value="separate">Separate input files</option> | 64 <option value="l">Log</option> |
79 <option value="interleaved">Interleaved files</option> | 65 <option value="sft">Soft filtered transcripts</option> |
80 <option value="unpaired">Unpaired/Single reads</option> | 66 <option value="tr" selected="true">Transcripts</option> |
81 <option value="paired-collection">Paired List Collection</option> | 67 <option value="tp">Transcripts paths</option> |
82 </param> | 68 </param> |
83 <when value="separate"> | |
84 <param format="fastq,fastq.gz" help="FASTQ format" label="Forward reads" name="fwd_reads" type="data" /> | |
85 <param format="fastq,fastq.gz" help="FASTQ format" label="Reverse reads" name="rev_reads" type="data" /> | |
86 </when> | |
87 <when value="interleaved"> | |
88 <param format="fastq,fastq.gz" help="FASTQ format" label="Interleaved paired reads" name="interleaved_reads" type="data" /> | |
89 </when> | |
90 <when value="unpaired"> | |
91 <param format="fastq,fastq.gz" help="FASTQ format" label="Unpaired reads" name="unpaired_reads" type="data" /> | |
92 </when> | |
93 <when value="paired-collection"> | |
94 <param name="fastq_collection" type="data_collection" collection_type="paired" format="fastq,fastq.gz" label="Paired-end reads collection" help="FASTQ format" /> | |
95 </when> | |
96 </conditional> | |
97 </repeat> | |
98 </repeat> | |
99 <param optional="true" format="fasta,fastq,fastq.gz" label="Trusted contigs" multiple="true" name="trusted_contigs" type="data" /> | |
100 <param optional="true" format="fasta,fastq,fastq.gz" label="Untrusted contigs" multiple="true" name="untrusted_contigs" type="data" /> | |
101 </inputs> | 69 </inputs> |
102 <outputs> | 70 <outputs> |
103 <data format="fasta" label="rnaSPAdes transcripts" name="output_transcripts" from_work_dir="transcripts.fasta" /> | 71 <expand macro="out_cr"/> |
72 <data name="out_hft" format="fasta" from_work_dir="output/hard_filtered_transcripts.fasta" label="${tool.name} on ${on_string}: Hard filtered transcripts"> | |
73 <filter>'hft' in optional_output</filter> | |
74 </data> | |
75 <expand macro="out_l"/> | |
76 <data name="out_sft" format="fasta" from_work_dir="output/soft_filtered_transcripts.fasta" label="${tool.name} on ${on_string}: Soft filtered transcripts"> | |
77 <filter>'sft' in optional_output</filter> | |
78 </data> | |
79 <data name="out_tr" format="fasta" from_work_dir="output/transcripts.fasta" label="${tool.name} on ${on_string}: Transcripts"> | |
80 <filter>'tr' in optional_output</filter> | |
81 </data> | |
82 <data name="out_tp" format="txt" from_work_dir="output/transcripts.paths" label="${tool.name} on ${on_string}: Transcripts paths"> | |
83 <filter>'tp' in optional_output</filter> | |
84 </data> | |
104 </outputs> | 85 </outputs> |
105 <tests> | 86 <tests> |
106 <test> | 87 <!-- |
107 <param name="lib_type" value="paired_end" /> | 88 used in a test: |
108 <param name="type" value="separate" /> | 89 single library: 12, 1, 2 |
109 <param name="fwd_reads" value="rnaspades-in1-1.fq" ftype="fastq" /> | 90 k, phred-offset, disablerr, iontorrent, only-assembler, ss |
110 <param name="rev_reads" value="rnaspades-in1-2.fq" ftype="fastq" /> | 91 |
111 <output name="output_transcripts" file="rnaspades-out1.fa" ftype="fasta" compare="re_match" lines_diff="1" /> | 92 not used in a test: |
112 </test> | 93 single library: merged, s |
113 <test> | 94 pacbio, nanopore, trusted-contigs, untrusted-contigs, fl-rna |
114 <param name="lib_type" value="paired_end" /> | 95 --> |
115 <param name="type" value="separate" /> | 96 |
116 <param name="fwd_reads" value="rnaspades-in1-1.fq.gz" ftype="fastq.gz" /> | 97 <!-- #1 --> |
117 <param name="rev_reads" value="rnaspades-in1-2.fq.gz" ftype="fastq.gz" /> | 98 <test expect_num_outputs="1"> |
118 <output name="output_transcripts" file="rnaspades-out1.fa" ftype="fasta" compare="re_match" lines_diff="1" /> | 99 <conditional name="singlePaired"> |
100 <param name="sPaired" value="paired_interlaced"/> | |
101 <param name="input1" value="ecoli_1K.fastq.gz"/> | |
102 </conditional> | |
103 <output name="out_tr"> | |
104 <assert_contents> | |
105 <has_n_lines n="18"/> | |
106 <has_text_matching expression=">NODE\_1\_length\_1000.+"/> | |
107 </assert_contents> | |
108 </output> | |
109 </test> | |
110 <!-- #2 single, separate, fastq, all outputs custom parameters--> | |
111 <test expect_num_outputs="5"> | |
112 <conditional name="singlePaired"> | |
113 <param name="sPaired" value="paired"/> | |
114 <param name="input1" value="ecoli_1K_1.fastq.gz"/> | |
115 <param name="input2" value="ecoli_1K_2.fastq.gz"/> | |
116 </conditional> | |
117 <param name="phred_offset" value="33"/> | |
118 <param name="ss" value="fr"/> | |
119 <param name="optional_output" value="hft,l,sft,tr,tp"/> | |
120 <output name="out_hft"> | |
121 <assert_contents> | |
122 <has_n_lines n="18"/> | |
123 </assert_contents> | |
124 </output> | |
125 <output name="out_sft"> | |
126 <assert_contents> | |
127 <has_n_lines n="18"/> | |
128 </assert_contents> | |
129 </output> | |
130 <output name="out_tr"> | |
131 <assert_contents> | |
132 <has_n_lines n="18"/> | |
133 </assert_contents> | |
134 </output> | |
135 <output name="out_tp"> | |
136 <assert_contents> | |
137 <has_n_lines n="4"/> | |
138 </assert_contents> | |
139 </output> | |
140 <output name="out_l"> | |
141 <assert_contents> | |
142 <has_text_matching expression="Thank you for using SPAdes!"/> | |
143 </assert_contents> | |
144 </output> | |
145 </test> | |
146 <!-- #3 single, separate, fasta, default parameters --> | |
147 <test expect_num_outputs="1"> | |
148 <conditional name="singlePaired"> | |
149 <param name="sPaired" value="paired"/> | |
150 <param name="input1" value="ecoli_1K_1.fasta.gz"/> | |
151 <param name="input2" value="ecoli_1K_2.fasta.gz"/> | |
152 </conditional> | |
153 <output name="out_tr"> | |
154 <assert_contents> | |
155 <has_n_lines n="18"/> | |
156 <has_text_matching expression=">NODE\_1\_length\_1000.+"/> | |
157 </assert_contents> | |
158 </output> | |
159 </test> | |
160 <!-- #3 Collection, default parameters --> | |
161 <test expect_num_outputs="1"> | |
162 <conditional name="singlePaired"> | |
163 <param name="sPaired" value="paired_collection"/> | |
164 <param name="input"> | |
165 <collection type="list:paired"> | |
166 <element name="ecoli.fastq"> | |
167 <collection type="paired"> | |
168 <element name="forward" value="ecoli_1K_1.fastq.gz" ftype="fastqsanger.gz"/> | |
169 <element name="reverse" value="ecoli_1K_2.fastq.gz" ftype="fastqsanger.gz"/> | |
170 </collection> | |
171 </element> | |
172 </collection> | |
173 </param> | |
174 </conditional> | |
175 <output name="out_tr"> | |
176 <assert_contents> | |
177 <has_n_lines n="18"/> | |
178 <has_text_matching expression=">NODE\_1\_length\_1000.+"/> | |
179 </assert_contents> | |
180 </output> | |
181 </test> | |
182 <!-- #3 Hibryd assembly --> | |
183 <test expect_num_outputs="1"> | |
184 <conditional name="singlePaired"> | |
185 <param name="sPaired" value="paired"/> | |
186 <param name="input1" value="ecoli_1K_1.fasta.gz"/> | |
187 <param name="input2" value="ecoli_1K_2.fasta.gz"/> | |
188 </conditional> | |
189 <section name="arf"> | |
190 <param name="nanopore" value="ecoli_1K.fastq.gz"/> | |
191 <param name="pacbio" value="ecoli_1K.fastq.gz"/> | |
192 <param name="trusted_contigs" value="ecoli_1K.fasta.gz"/> | |
193 <param name="flrna" value="ecoli_1K.fasta.gz"/> | |
194 </section> | |
195 <assert_command> | |
196 <has_text text="--nanopore"/> | |
197 <has_text text="--pacbio"/> | |
198 <has_text text="--trusted-contigs"/> | |
199 <has_text text="--fl-rna"/> | |
200 </assert_command> | |
201 <output name="out_tr"> | |
202 <assert_contents> | |
203 <has_n_lines n="18"/> | |
204 <has_text_matching expression=">NODE\_1\_length\_1000.+"/> | |
205 </assert_contents> | |
206 </output> | |
119 </test> | 207 </test> |
120 </tests> | 208 </tests> |
121 <help> | 209 <help><![CDATA[ |
210 .. class:: infomark | |
211 | |
122 **What it does** | 212 **What it does** |
123 | 213 |
124 SPAdes – St. Petersburg genome assembler – is intended for both standard isolates and single-cell MDA bacteria assemblies. See http://bioinf.spbau.ru/en/spades for more details on SPAdes. | 214 @HELP_WID@ |
125 | 215 |
126 This wrapper runs SPAdes 3.9.0, collects the output, and throws away all the temporary files. | 216 rnaSPAdes is a subtool for de novo transcriptome assembly from RNA-Seq data and is suitable for all kinds of organisms. |
127 | 217 |
128 **License** | 218 **Input** |
129 | 219 |
130 SPAdes is developed by and copyrighted to Saint-Petersburg Academic University, and is released under GPLv2. | 220 rnaSPAdes take as an input at least one paired-end or single-end library. For hybrid assembly you can use PacBio or Oxford Nanopore reads. |
131 | 221 |
132 The original wrapper was written by Lionel Guy, Philip Mabon and was released under the GNU General Public License as published by the Free Software Foundation. The rnaSPAdes extension was developed by the Galaxy team. | 222 In case you have sequenced several RNA-Seq libraries using the same protocol from different tissues / conditions, and the goal as to assemble a total transcriptome, |
133 | 223 we suggest to provide all files as a single library. Note, that sequencing using the same protocol implies that the resulting reads have the same length, insert size |
134 This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. | 224 and strand-specificity. Transcript quantification for each sample can be done afterwards by separately mapping reads from each library to the assembled transcripts. |
135 | 225 |
136 You should have received a copy of the GNU General Public License along with this program. If not, see http://www.gnu.org/licenses/. | 226 **Output** |
137 | 227 |
138 ** Acknowledgments ** | 228 @HELP_OUT_AG@ |
139 | 229 @HELP_OUT_AGS@ |
140 Anton Korobeynikov greatlty helped understanding how SPAdes work, and integrated handy features into SPAdes. | 230 @HELP_OUT_CR@ |
141 | 231 - Hard filtered transcripts includes only long and reliable transcripts with rather high expression |
142 Nicola Soranzo fixed various bugs. | 232 @HELP_OUT_L@ |
143 </help> | 233 - Soft filtered transcripts includes short and low-expressed transcipts, likely to contain junk sequences |
144 <citations> | 234 - Transcripts |
145 <citation type="doi">10.1089/cmb.2012.0021</citation> | 235 - Transcripts paths |
146 </citations> | 236 |
237 .. class:: infomark | |
238 | |
239 **References** | |
240 | |
241 More information can be found on on `github <https://github.com/ablab/spades>`_ and on the `project website <http://cab.spbu.ru/software/rnaspades>`_. | |
242 ]]></help> | |
243 <expand macro="citations"> | |
244 <citation type="doi">10.1101/420208</citation> | |
245 </expand> | |
147 </tool> | 246 </tool> |