Mercurial > repos > rnateam > mirdeep2_mapper

comparison mapper.xml @ 2:ab8cd78709e1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/mirdeep2/mirdeep2_mapper commit b9d202134c3c6d0e5c398c3ae75e410067fcfc52
author rnateam
date Wed, 23 Nov 2016 16:32:13 -0500
parents 12fc62b7dc09
children a8d24f4b6d95
comparison
equal deleted inserted replaced
1:12fc62b7dc09 2:ab8cd78709e1
38 <command> 38 <command>
39 <![CDATA[ 39 <![CDATA[
40 40
41 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map" 41 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
42 #if $operation.refGenomeSource.genomeSource == "history" 42 #if $operation.refGenomeSource.genomeSource == "history"
43 bowtie-build $operation.refGenomeSource.ownFile custom_bowtie_indices && 43 bowtie-build '$operation.refGenomeSource.ownFile' custom_bowtie_indices &&
44 #end if 44 #end if
45 #end if 45 #end if
46
46 mapper.pl 47 mapper.pl
47 48
48 $reads 49 '$reads'
49 50
50 #if $reads.extension.startswith("fasta") 51 #if $reads.extension.startswith("fasta")
51 -c 52 -c
52 #else if $reads.extension.startswith("fastq") 53 #else if $reads.extension.startswith("fastq")
53 -e -h 54 -e
55 -h
54 #end if 56 #end if
55 57
56 $remove_non_canon 58 $remove_non_canon
57 59
58 $convert_rna_dna 60 $convert_rna_dna
62 #end if 64 #end if
63 65
64 -l $discard_short_reads 66 -l $discard_short_reads
65 67
66 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse" 68 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_collapse"
67 -m -s $output_reads_collapsed 69 -m -s '$output_reads_collapsed'
68 #end if 70 #end if
69 71
70 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map" 72 #if $operation.collapse_map == "collapse_and_map" or $operation.collapse_map == "only_map"
71 -p 73 -p
72 74
73 #if $operation.refGenomeSource.genomeSource == "history" 75 #if $operation.refGenomeSource.genomeSource == "history"
74 custom_bowtie_indices 76 custom_bowtie_indices
75 #else 77 #else
76 $operation.refGenomeSource.index 78 '$operation.refGenomeSource.index.fields.path'
77 #end if 79 #end if
78
79 $operation.map_mismatch 80 $operation.map_mismatch
80
81 -r $operation.map_threshold 81 -r $operation.map_threshold
82 82
83 -t $output_mapping 83 -t '$output_mapping'
84 #end if 84 #end if
85 85
86 -v -n 86 -v -n
87 ]]> 87 ]]>
88 </command> 88 </command>
93 <!-- In case the return code has not been set propery check stderr too --> 93 <!-- In case the return code has not been set propery check stderr too -->
94 <regex match="Error:" /> 94 <regex match="Error:" />
95 <regex match="Exception:" /> 95 <regex match="Exception:" />
96 </stdio> 96 </stdio>
97 <inputs> 97 <inputs>
98 <param format="fastq, fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or fasta format"/> 98 <param format="fastq, fasta" name="reads" type="data" optional="false" label="Deep sequencing reads" help="Reads in fastq or FASTA format"/>
99 <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/> 99 <param name="remove_non_canon" type="boolean" truevalue="-j" falsevalue="" checked="false" label="Remove reads with non-standard nucleotides" help="Remove all entries that have a sequence that contains letters other than a,c,g,t,u,n,A,C,G,T,U,N. (-j)"/>
100 <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/> 100 <param name="convert_rna_dna" type="boolean" truevalue="-i" falsevalue="" checked="false" label="Convert RNA to DNA alphabet (to map against genome)" help="(-i)"/>
101 101
102 <conditional name="clip_adapter"> 102 <conditional name="clip_adapter">
103 <param name="clip" type="select" label="Clip 3' Adapter Sequence" help="(-k)"> 103 <param name="clip" type="select" label="Clip 3' Adapter Sequence" help="(-k)">
179 </output> 179 </output>
180 </test> 180 </test>
181 </tests> 181 </tests>
182 <help> 182 <help>
183 <![CDATA[ 183 <![CDATA[
184 **What MiRDeep2 Mapper does** 184 **What it does**
185 185
186 The mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome. 186 The MiRDeep2 Mapper module is designed as a tool to process deep sequencing reads and/or map them to the reference genome.
187 The module works in sequence space, and can process or map data that is in sequence fasta format. 187 The module works in sequence space, and can process or map data that is in sequence FASTA format.
188 A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind. 188 A number of the functions of the mapper module are implemented specifically with Solexa/Illumina data in mind.
189 189
190 **Example** 190 **Input**
191 191
192 Processing reads and mapping them to a genome. 192 Default input is a file in FASTA format, seq.txt or qseq.txt format. More input can be given depending on the options used.
193 193
194 The -c option designates that the input file is a fasta file. The -j options removes entries with 194 **Output**
195 non-canonical letters (letters other than a,c,g,t,u,n,A,C,G,T,U,N). The -k option clips adapters. The -l option discards reads shorter than 18 nts. 195
196 The -m option collapses the reads. The -p option maps the processed reads against the previously indexed genome (cel_cluster). The -s option 196 The output depends on the options used. Either a FASTA file with processed reads or an arf file with with mapped reads, or both, are output.
197 designates the name of the output file of processed reads and the -t option designates the name of the output file of the genome mappings. Last, 197
198 -v gives verbose output to the screen. 198 Arf format:
199 199 Is a proprietary file format generated and processed by miRDeep2. It contains information of reads mapped to a reference genome. Each line in such a file contains 13 columns:
200 ``mapper.pl reads.fa -c -j -k TCGTATGCCGTCTTCTGCTTGT -l 18 -m -p cel_cluster -s reads_collapsed.fa -t reads_collapsed_vs_genome.arf -v`` 200
201 1. read identifier
202 2. length of read sequence
203 3. start position in read sequence that is mapped
204 4. end position in read sequence that is mapped
205 5. read sequence
206 6. identifier of the genome-part to which a read is mapped to. This is either a scaffold id or a chromosome name
207 7. length of the genome sequence a read is mapped to
208 8. start position in the genome where a read is mapped to
209 9. end position in the genome where a read is mapped to
210 10. genome sequence to which a read is mapped
211 11. genome strand information. Plus means the read is aligned to the sense-strand of the genome. Minus means it is aligned to the antisense-strand of the genome.
212 12. Number of mismatches in the read mapping
213 13. Edit string that indicates matches by lowercase 'm' and mismatches by uppercase 'M'
201 214
202 ]]> 215 ]]>
203 </help> 216 </help>
204 <citations> 217 <citations>
205 <citation type="doi">10.1093/nar/gkr688</citation> 218 <citation type="doi">10.1093/nar/gkr688</citation>