Mercurial > repos > pjbriggs > pal_finder
annotate pal_finder_wrapper.xml @ 3:e1a14ed7a9d6 draft
Updated to version 0.02.04.4 (new pal_filter script)
| author | pjbriggs |
|---|---|
| date | Wed, 24 Feb 2016 08:25:17 -0500 |
| parents | b6ccc7dd7b02 |
| children | a73c48890bde |
| rev | line source |
|---|---|
|
3
e1a14ed7a9d6
Updated to version 0.02.04.4 (new pal_filter script)
pjbriggs
parents:
2
diff
changeset
|
1 <tool id="microsat_pal_finder" name="pal_finder" version="0.02.04.4"> |
| 2 | 2 <description>Find microsatellite repeat elements from sequencing reads and design PCR primers to amplify them</description> |
| 3 <requirements> | |
| 4 <requirement type="package" version="5.16.3">perl</requirement> | |
| 5 <requirement type="package" version="0.02.04">pal_finder</requirement> | |
| 6 <requirement type="package" version="2.0.0">primer3_core</requirement> | |
| 7 <requirement type="package" version="1.65">biopython</requirement> | |
| 8 <requirement type="package" version="2.8.1">pandaseq</requirement> | |
| 9 </requirements> | |
| 0 | 10 <command interpreter="bash">pal_finder_wrapper.sh |
| 11 #if str( $platform.platform_type ) == "illumina" | |
| 2 | 12 #set $paired_input_type = $platform.paired_input_type_conditional.paired_input_type |
| 13 #if $paired_input_type == "pair_of_files" | |
| 14 "$platform.paired_input_type_conditional.input_fastq_r1" | |
| 15 "$platform.paired_input_type_conditional.input_fastq_r2" | |
| 16 #else | |
| 17 "$platform.paired_input_type_conditional.input_fastq_pair.forward" | |
| 18 "$platform.paired_input_type_conditional.input_fastq_pair.reverse" | |
| 19 #end if | |
| 0 | 20 #else |
| 2 | 21 --454 "$platform.input_fasta" |
| 0 | 22 #end if |
| 23 $output_microsat_summary $output_pal_summary | |
| 24 #if $keep_config_file | |
| 2 | 25 --output_config_file "$output_config_file" |
| 0 | 26 #end if |
|
1
771ebe02636f
Uploaded version 0.02.04.2: fix bug that causes tool to fail when prefix includes spaces; add explicit dependency on Perl 5.16.3.
pjbriggs
parents:
0
diff
changeset
|
27 --primer-prefix "$primer_prefix" |
| 0 | 28 --2merMinReps $min_2mer_repeats |
| 29 --3merMinReps $min_3mer_repeats | |
| 30 --4merMinReps $min_4mer_repeats | |
| 31 --5merMinReps $min_5mer_repeats | |
| 32 --6merMinReps $min_6mer_repeats | |
| 33 #if str( $primer.primer_options ) == "custom" | |
| 34 --primer-opt-size $primer.primer_opt_size | |
| 35 --primer-min-size $primer.primer_min_size | |
| 36 --primer-max-size $primer.primer_max_size | |
| 37 --primer-min-gc $primer.primer_min_gc | |
| 38 --primer-max-gc $primer.primer_max_gc | |
| 39 --primer-gc-clamp $primer.primer_gc_clamp | |
| 40 --primer-max-end-gc $primer.primer_max_end_gc | |
| 41 --primer-min-tm $primer.primer_min_tm | |
| 42 --primer-max-tm $primer.primer_max_tm | |
| 43 --primer-opt-tm $primer.primer_opt_tm | |
| 44 --primer-pair-max-diff-tm $primer.primer_pair_max_diff_tm | |
| 45 #end if | |
| 46 #if str( $mispriming.mispriming_options ) == "custom" | |
| 47 --primer-mispriming-library $mispriming.mispriming_library | |
| 48 #end if | |
| 2 | 49 #if str( $platform.platform_type ) == "illumina" |
| 50 #if $platform.filters | |
| 51 #for $filter in str($platform.filters).split(',') | |
| 52 $filter | |
| 53 --filter_microsats "$output_filtered_microsats" | |
| 54 #end for | |
| 55 #end if | |
| 56 #if str( $platform.assembly ) == '-assembly' | |
| 57 $platform.assembly "$output_assembly" | |
| 58 #end if | |
| 59 #end if | |
| 0 | 60 </command> |
| 61 <inputs> | |
| 62 <param name="primer_prefix" type="text" value="test" size="25" label="Primer prefix" help="This prefix will be added to the beginning of all primer names" /> | |
| 63 <conditional name="platform"> | |
| 64 <param name="platform_type" type="select" label="Sequencing platform used to generate data" help="Currently pal_finder only handles Illumina paired-end reads and 454 single-end reads" > | |
| 65 <option value="illumina" selected="true">Illumina</option> | |
| 66 <option value="454">454</option> | |
| 67 </param> | |
| 68 <when value="illumina"> | |
| 2 | 69 <conditional name="paired_input_type_conditional"> |
| 70 <param name="paired_input_type" type="select" label="Input Type"> | |
| 71 <option value="pair_of_files" selected="true">Pair of datasets</option> | |
| 72 <option value="collection">Dataset collection pair</option> | |
| 73 </param> | |
| 74 <when value="pair_of_files"> | |
| 75 <param name="input_fastq_r1" type="data" format="fastqsanger" | |
| 76 label="Illumina fastq file (read 1)" /> | |
| 77 <param name="input_fastq_r2" type="data" format="fastqsanger" | |
| 78 label="Illumina fastq file (read 2)" /> | |
| 79 </when> | |
| 80 <when value="collection"> | |
| 81 <param name="input_fastq_pair" format="fastqsanger" | |
| 82 type="data_collection" collection_type="paired" | |
| 83 label="Select FASTQ dataset collection with R1/R2 pair" /> | |
| 84 </when> | |
| 85 </conditional> | |
| 86 <param name="filters" type="select" display="checkboxes" | |
| 87 multiple="True" label="Filters to apply to the pal_finder results" | |
| 88 help="Apply none, one or more filters to refine results"> | |
| 89 <option value="-primers" selected="True">Only include loci with designed primers</option> | |
| 90 <option value="-occurrences" selected="True">Exclude loci where the primer sequences occur more than once in the reads</option> | |
| 91 <option value="-rankmotifs" selected="True">Only include loci with 'perfect' motifs, and rank by motif size</option> | |
| 92 </param> | |
| 93 <param name="assembly" type="boolean" | |
| 94 checked="True" truevalue="-assembly" falsevalue="" | |
| 95 label="Use PANDAseq to assemble paired-end reads and confirm primer sequences are present in high-quality assembly" /> | |
| 0 | 96 </when> |
| 97 <when value="454"> | |
| 98 <param name="input_fasta" type="data" format="fasta" label="454 fasta file with raw reads" /> | |
| 99 </when> | |
| 100 </conditional> | |
| 101 <param name="min_2mer_repeats" type="integer" value="6" label="Minimum number of 2-mer repeat units to detect" help="Set to zero to ignore repeats of this n-mer unit" /> | |
| 102 <param name="min_3mer_repeats" type="integer" value="0" label="Minimum number of 3-mer repeat units" help="Set to zero to ignore repeats of this n-mer unit" /> | |
| 103 <param name="min_4mer_repeats" type="integer" value="0" label="Minimum number of 4-mer repeat units" help="Set to zero to ignore repeats of this n-mer unit" /> | |
| 104 <param name="min_5mer_repeats" type="integer" value="0" label="Minimum number of 5-mer repeat units" help="Set to zero to ignore repeats of this n-mer unit" /> | |
| 105 <param name="min_6mer_repeats" type="integer" value="0" label="Minimum number of 6-mer repeat units" help="Set to zero to ignore repeats of this n-mer unit" /> | |
| 106 <conditional name="mispriming"> | |
| 107 <param name="mispriming_options" type="select" label="Mispriming library to use" help="Specify file of nucleotide sequences to avoid amplifying (PRIMER_MISPRIMING_LIBRARY)"> | |
| 108 <option value="default">Default from pal_finder</option> | |
| 109 <option value="custom">Custom sequences from history</option> | |
| 110 </param> | |
| 111 <when value="default"> | |
| 112 </when> | |
| 113 <when value="custom"> | |
| 114 <param name="mispriming_library" type="data" format="fasta" label="Select mispriming library from history" help="Fasta file containing sequences to avoid amplifying" /> | |
| 115 </when> | |
| 116 </conditional> | |
| 117 <conditional name="primer"> | |
| 118 <param name="primer_options" type="select" label="Primer settings to use" help="Advanced users can customise the settings for primer3 for more control"> | |
| 119 <option value="default">Defaults for pal_finder</option> | |
| 120 <option value="custom">Custom</option> | |
| 121 </param> | |
| 122 <when value="custom"> | |
| 123 <param name="primer_opt_size" type="integer" value="20" | |
| 124 label="Optimum length (in bases) of a primer (PRIMER_OPT_SIZE)" | |
| 125 help="Primer3 will attempt to pick primers close to this length" /> | |
| 126 <param name="primer_min_size" type="integer" value="18" | |
| 127 label="Minimum acceptable length (in bases) of a primer (PRIMER_MIN_SIZE)" | |
| 128 help="Must be greater than 0 and less than or equal to PRIMER_MAX_SIZE" /> | |
| 129 <param name="primer_max_size" type="integer" value="30" | |
| 130 label="Maximum acceptable length (in bases) of a primer (PRIMER_MAX_SIZE)" | |
| 131 help="Currently this parameter cannot be larger than 35. This limit is governed by maximum oligo size for which primer3's melting-temperature is valid" /> | |
| 132 <param name="primer_min_gc" type="float" value="30.0" | |
| 133 label="Minimum allowable percentage of Gs and Cs in any primer (PRIMER_MIN_GC)" /> | |
| 134 <param name="primer_max_gc" type="float" value="80.0" | |
| 135 label="Maximum allowable percentage of Gs and Cs in any primer (PRIMER_MAX_GC)" /> | |
| 136 <param name="primer_gc_clamp" type="integer" value="2" | |
| 137 label="Specify number of consecutive Gs and Cs at 3' end of both the left and right primer (PRIMER_GC_CLAMP)" /> | |
| 138 <param name="primer_max_end_gc" type="integer" value="5" | |
| 139 label="Maximum number of Gs or Cs allowed in last five 3' bases of a left or right primer (PRIMER_MAX_END_GC)" /> | |
| 140 <param name="primer_min_tm" type="float" value="58.0" | |
| 141 label="Minimum acceptable melting temperature for a primer oligo (PRIMER_MIN_TM)" | |
| 142 help="Temperature should be in degrees Celsius" /> | |
| 143 <param name="primer_max_tm" type="float" value="65.0" | |
| 144 label="Maximum acceptable melting temperature for a primer oligo (PRIMER_MAX_TM)" | |
| 145 help="Temperature should be in degrees Celsius" /> | |
| 146 <param name="primer_opt_tm" type="float" value="62.0" | |
| 147 label="Optimum melting temperature for a primer (PRIMER_OPT_TM)" | |
| 148 help="Temperature should be in degrees Celsius" /> | |
| 149 <param name="primer_pair_max_diff_tm" type="float" value="2.0" | |
| 150 label="Maximum acceptable difference between melting temperatures of left and right primers (PRIMER_PAIR_MAX_DIFF_TM)" | |
| 151 help="Temperature should be in degrees Celsius" /> | |
| 152 </when> | |
| 153 </conditional> | |
| 154 <param name="keep_config_file" type="boolean" truevalue="True" falsevalue="False" | |
| 155 label="Output the config file to the history" | |
| 156 help="Can be used to run pal_finder outside of Galaxy" /> | |
| 157 </inputs> | |
| 158 <outputs> | |
| 2 | 159 <data name="output_pal_summary" format="tabular" label="${tool.name} on ${on_string} for ${primer_prefix}: all microsatellites (full details)" /> |
| 160 <data name="output_filtered_microsats" format="tabular" label="${tool.name} on ${on_string} for ${primer_prefix}: filtered microsatellites (full details)"> | |
| 161 <filter>platform['platform_type'] == 'illumina' and platform['filters'] is not None</filter> | |
| 0 | 162 </data> |
| 2 | 163 <data name="output_microsat_summary" format="txt" label="${tool.name} on ${on_string} for ${primer_prefix}: summary of microsatellite types" /> |
| 164 <data name="output_assembly" format="tabular" label="${tool.name} on ${on_string} for ${primer_prefix}: assembly"> | |
| 165 <filter>platform['assembly'] is True</filter> | |
| 166 </data> | |
| 167 <data name="output_config_file" format="txt" label="${tool.name} on ${on_string} for ${primer_prefix}: config file"> | |
| 0 | 168 <filter>keep_config_file is True</filter> |
| 169 </data> | |
| 170 </outputs> | |
| 171 <tests> | |
| 172 <test> | |
| 173 <!-- Test with Illumina input --> | |
| 174 <param name="platform_type" value="illumina" /> | |
| 175 <param name="input_fastq_r1" value="illuminaPE_r1.fq" ftype="fastqsanger" /> | |
| 176 <param name="input_fastq_r2" value="illuminaPE_r2.fq" ftype="fastqsanger" /> | |
| 2 | 177 <output name="output_microsat_summary" file="illuminaPE_microsat_types.out" /> |
| 178 <output name="output_pal_summary" file="illuminaPE_microsats.out" /> | |
| 179 <output name="output_filtered_microsats" file="illuminaPE_filtered_microsats.out" /> | |
| 180 <output name="output_assembly" file="illuminaPE_assembly_after_filters.out" /> | |
| 181 </test> | |
| 182 <test> | |
| 183 <!-- Test with Illumina input as dataset pair --> | |
| 184 <param name="platform_type" value="illumina" /> | |
| 185 <param name="paired_input_type" value="collection" /> | |
| 186 <param name="input_fastq_pair"> | |
| 187 <collection type="paired"> | |
| 188 <element name="forward" value="illuminaPE_r1.fq" ftype="fastqsanger" /> | |
| 189 <element name="reverse" value="illuminaPE_r2.fq" ftype="fastqsanger" /> | |
| 190 </collection> | |
| 191 </param> | |
| 0 | 192 <output name="output_microsat_summary" file="illuminaPE_microsat_types.out" /> |
| 193 <output name="output_pal_summary" file="illuminaPE_microsats.out" /> | |
| 194 <output name="output_filtered_microsats" file="illuminaPE_filtered_microsats.out" /> | |
| 2 | 195 <output name="output_assembly" file="illuminaPE_assembly_after_filters.out" /> |
| 196 </test> | |
| 197 <test> | |
| 198 <!-- Test with Illumina input filter to loci with PandaSEQ assembly | |
| 199 ('-assembly' option) --> | |
| 200 <param name="platform_type" value="illumina" /> | |
| 201 <param name="filters" value="" /> | |
| 202 <param name="input_fastq_r1" value="illuminaPE_r1.fq" ftype="fastqsanger" /> | |
| 203 <param name="input_fastq_r2" value="illuminaPE_r2.fq" ftype="fastqsanger" /> | |
| 204 <output name="output_microsat_summary" file="illuminaPE_microsat_types.out" /> | |
| 205 <output name="output_pal_summary" file="illuminaPE_microsats.out" /> | |
| 206 <output name="output_assembly" file="illuminaPE_assembly.out" /> | |
| 207 </test> | |
| 208 <test> | |
| 209 <!-- Test with Illumina input filter to loci with primers | |
| 210 ('-primers' option) --> | |
| 211 <param name="platform_type" value="illumina" /> | |
| 212 <param name="filters" value="-primers" /> | |
| 213 <param name="assembly" value="false" /> | |
| 214 <param name="input_fastq_r1" value="illuminaPE_r1.fq" ftype="fastqsanger" /> | |
| 215 <param name="input_fastq_r2" value="illuminaPE_r2.fq" ftype="fastqsanger" /> | |
| 216 <output name="output_microsat_summary" file="illuminaPE_microsat_types.out" /> | |
| 217 <output name="output_pal_summary" file="illuminaPE_microsats.out" /> | |
| 218 <output name="output_filtered_microsats" file="illuminaPE_filtered_microsats_primers.out" /> | |
| 219 </test> | |
| 220 <test> | |
| 221 <!-- Test with Illumina input filter to loci which appear only once | |
| 222 ('-occurrences' option) --> | |
| 223 <param name="platform_type" value="illumina" /> | |
| 224 <param name="filters" value="-occurrences" /> | |
| 225 <param name="assembly" value="false" /> | |
| 226 <param name="input_fastq_r1" value="illuminaPE_r1.fq" ftype="fastqsanger" /> | |
| 227 <param name="input_fastq_r2" value="illuminaPE_r2.fq" ftype="fastqsanger" /> | |
| 228 <output name="output_microsat_summary" file="illuminaPE_microsat_types.out" /> | |
| 229 <output name="output_pal_summary" file="illuminaPE_microsats.out" /> | |
| 230 <output name="output_filtered_microsats" file="illuminaPE_filtered_microsats_occurrences.out" /> | |
| 231 </test> | |
| 232 <test> | |
| 233 <!-- Test with Illumina input filter and rank loci with perfect motifs | |
| 234 ('-rankmotifs' option) --> | |
| 235 <param name="platform_type" value="illumina" /> | |
| 236 <param name="filters" value="-rankmotifs" /> | |
| 237 <param name="assembly" value="false" /> | |
| 238 <param name="input_fastq_r1" value="illuminaPE_r1.fq" ftype="fastqsanger" /> | |
| 239 <param name="input_fastq_r2" value="illuminaPE_r2.fq" ftype="fastqsanger" /> | |
| 240 <output name="output_microsat_summary" file="illuminaPE_microsat_types.out" /> | |
| 241 <output name="output_pal_summary" file="illuminaPE_microsats.out" /> | |
| 242 <output name="output_filtered_microsats" file="illuminaPE_filtered_microsats_rankmotifs.out" /> | |
| 0 | 243 </test> |
| 244 <test> | |
| 245 <!-- Test with 454 input --> | |
| 246 <param name="platform_type" value="454" /> | |
| 247 <param name="input_fasta" value="454_in.fa" ftype="fasta" /> | |
| 248 <output name="output_microsat_summary" file="454_microsat_types.out" /> | |
| 249 <output name="output_pal_summary" file="454_microsats.out" /> | |
| 250 </test> | |
| 251 </tests> | |
| 252 <help> | |
| 253 .. class:: infomark | |
| 254 | |
| 255 **What it does** | |
| 256 | |
| 257 This tool runs the pal_finder program, which finds microsatellite repeat elements | |
| 258 directly from raw 454 or Illumina paired-end sequencing reads. It then designs PCR | |
| 259 primers to amplify these repeat loci (Potentially Amplifiable Loci: PAL). | |
| 260 | |
| 2 | 261 Optionally for Illumina data, one or more filters can be applied to the output from |
| 262 pal_finder to: | |
| 263 | |
| 264 * Only include loci with designed primers | |
| 265 * Exclude loci where the primer sequences occur more than once in the reads | |
| 266 * Only include loci with 'perfect' motifs (and rank by motif size,largest to | |
| 267 smallest) | |
| 268 * Use PANDAseq to assemble paired-end reads and confirm primer sequences are | |
| 269 present in high-quality assembly | |
| 0 | 270 |
| 271 Pal_finder runs the primer3_core program; information on the settings used in | |
| 272 primer3_core can be found in the Primer3 manual at | |
| 273 http://primer3.sourceforge.net/primer3_manual.htm | |
| 274 | |
| 275 ------------- | |
| 276 | |
| 277 .. class:: infomark | |
| 278 | |
| 279 **Credits** | |
| 280 | |
| 281 This Galaxy tool has been developed by Peter Briggs within the Bioinformatics Core | |
| 282 Facility at the University of Manchester. It runs the pal_finder package which can be | |
| 283 obtained from http://sourceforge.net/projects/palfinder/: | |
| 284 | |
| 285 * PLoS One. 2012; 7(2): e30953 "Rapid Microsatellite Identification from Illumina Paired-End | |
| 286 Genomic Sequencing in Two Birds and a Snake" Todd A. Castoe, Alexander W. Poole, A. P. | |
| 287 Jason de Koning, Kenneth L. Jones, Diana F. Tomback, Sara J. Oyler-McCance, Jennifer A. | |
| 288 Fike, Stacey L. Lance, Jeffrey W. Streicher, Eric N. Smith, and David D. Pollock | |
| 289 | |
| 290 The paper is available at http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3279355/ | |
| 291 | |
| 292 This tool is compatible with pal_finder version 0.02.04, which in turn runs the | |
| 293 primer3_core program (version 2.0.0-alpha is required, available from | |
| 294 http://primer3.sourceforge.net/releases.php): | |
| 295 | |
| 296 * Steve Rozen and Helen J. Skaletsky (2000) "Primer3 on the WWW for general users and for | |
| 297 biologist programmers". In: Krawetz S, Misener S (eds) Bioinformatics Methods and | |
| 298 Protocols: Methods in Molecular Biology. Humana Press, Totowa, NJ, pp 365-386 | |
| 299 | |
| 300 The paper is available at | |
| 301 http://purl.com/STEVEROZEN/papers/rozen-and-skaletsky-2000-primer3.pdf | |
| 302 | |
| 2 | 303 The filtering and assembly of the pal_finder output for Illumina data is performed |
| 304 using a Python utility written by Graeme Fox at the University of Manchester, and which | |
| 305 is included with this tool; this utility uses the BioPython and PANDAseq packages. | |
| 0 | 306 |
| 307 Please kindly acknowledge both this Galaxy tool, the pal_finder and primer3 packages, and | |
| 2 | 308 the utility script and its dependencies if you use it in your work. |
| 0 | 309 </help> |
| 310 <citations> | |
| 311 <!-- | |
| 312 See https://wiki.galaxyproject.org/Admin/Tools/ToolConfigSyntax#A.3Ccitations.3E_tag_set | |
| 313 Can be either DOI or Bibtex | |
| 314 Use http://www.bioinformatics.org/texmed/ to convert PubMed to Bibtex | |
| 315 --> | |
| 316 <citation type="doi">10.1371/journal.pone.0030953</citation> | |
| 317 <citation type="bibtex">@Article{pmid10547847, | |
| 2 | 318 Author="Rozen, S. and Skaletsky, H. ", |
| 0 | 319 Title="{{P}rimer3 on the {W}{W}{W} for general users and for biologist programmers}", |
| 320 Journal="Methods Mol. Biol.", | |
| 321 Year="2000", | |
| 322 Volume="132", | |
| 323 Pages="365--386", | |
| 324 URL="{http://purl.com/STEVEROZEN/papers/rozen-and-skaletsky-2000-primer3.pdf}" | |
| 325 }</citation> | |
| 2 | 326 <citation type="doi">10.1093/bioinformatics/btp163</citation> |
| 327 <citation type="doi">10.1186/1471-2105-13-31</citation> | |
| 0 | 328 </citations> |
| 329 </tool> |