Mercurial > repos > gbcs-embl-heidelberg > je_markdupes
annotate je-markdupes.xml @ 4:384b972e43bc draft
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 1c7680ac36888721d2c0b72f4e6d27415fe07b43
| author | gbcs-embl-heidelberg |
|---|---|
| date | Tue, 01 Aug 2017 03:43:03 -0400 |
| parents | 4ccf1406832d |
| children | e2d1b5e1eb11 |
| rev | line source |
|---|---|
|
3
4ccf1406832d
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit dd9e62bdb01d1252a90ce778103ce9b6b4a8cd52-dirty
gbcs-embl-heidelberg
parents:
0
diff
changeset
|
1 <tool id="je_markdupes" name="Je-MarkDuplicates" version="@VERSION_STRING@"> |
| 0 | 2 <description>to filter BAM files for read duplicates taking UMIs into account</description> |
| 3 <macros> | |
| 4 <import>macros.xml</import> | |
| 5 </macros> | |
| 6 <stdio> | |
| 7 <exit_code range="1:" level="fatal" description="Tool exception" /> | |
| 8 </stdio> | |
| 9 <version_command>echo '1.0'</version_command> | |
| 10 <command interpreter="bash"> | |
| 11 <![CDATA[ | |
| 12 je markdupes | |
| 13 | |
| 14 ## picard MarkDuplicates defaults | |
| 15 INPUT="${inputFile}" | |
| 16 OUTPUT="${outFile}" | |
| 17 | |
| 18 METRICS_FILE="${metrics_file}" | |
| 19 | |
| 20 REMOVE_DUPLICATES="${remove_duplicates}" | |
| 21 ASSUME_SORTED="${assume_sorted}" | |
| 22 | |
| 23 #for $element in $adv_options.comments: | |
| 24 COMMENT="${element.comment}" | |
| 25 #end for | |
| 26 | |
| 27 DUPLICATE_SCORING_STRATEGY="${adv_options.duplicate_scoring_strategy}" | |
| 28 | |
| 29 #import pipes | |
| 30 READ_NAME_REGEX=${ pipes.quote( str( $adv_options.read_name_regex ) ) or "''" } | |
| 31 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${adv_options.optical_duplicate_pixel_distance}" | |
| 32 | |
| 33 VALIDATION_STRINGENCY="${adv_options.validation_stringency}" | |
| 34 QUIET=true | |
| 35 VERBOSITY=ERROR | |
| 36 | |
| 37 ## Je Markdupes Specific | |
| 38 MM=${MM} | |
| 39 #if str($MAX_N) != "": | |
| 40 MAX_N=${MAX_N} | |
| 41 #end if | |
| 42 @barcode_option_cmd@ | |
| 43 | |
| 44 #for $i, $option in enumerate( $repeat_slots ) | |
| 45 #if str($option.SLOTS) != "": | |
| 46 SLOTS=${option.SLOTS} | |
| 47 #end if | |
| 48 #end for | |
| 49 | |
| 50 #if str($trim_conditional.T) == "true": | |
| 51 T=${trim_conditional.T} | |
| 52 #for $i, $option in enumerate( $trim_conditional.repeat_tslots ) | |
| 53 #if str($option.TSLOTS) != "": | |
| 54 TSLOTS=${option.TSLOTS} | |
| 55 #end if | |
| 56 #end for | |
| 57 #end if | |
| 58 ]]> | |
| 59 </command> | |
| 60 <configfiles> | |
| 61 <expand macro="barcode_config_file"></expand> | |
| 62 </configfiles> | |
| 63 | |
| 64 <inputs> | |
| 65 <param format="bam,sam" name="inputFile" type="data" label="Select SAM/BAM dataset" | |
| 66 help="If empty, upload or import a SAM/BAM dataset"/> | |
| 67 <param name="remove_duplicates" type="boolean" label="If true do not write duplicates to the output file | |
| 68 instead of writing them with appropriate flags set" help="REMOVE_DUPLICATES; default=False"/> | |
| 69 <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" | |
| 70 truevalue="true" falsevalue="false" help="ASSUME_SORTED; default=True"/> | |
| 71 <conditional name="barcodes"> | |
| 72 <param name="barcode_list_type_con" type="select" label="Do you have a predefined list of UMIs"> | |
| 73 <option value="file" selected="true">A one column txt file from the history</option> | |
| 74 <option value="text">Paste the UMI list in a text field</option> | |
| 75 <option value="no_barcodes">No predefined list</option> | |
| 76 </param> | |
| 77 | |
| 78 <when value="file"> | |
| 79 <param name="BARCODE_FILE" type="data" format="tabular,txt" label="UMI file" | |
| 80 help="BARCODE_FILE. Pre-defined list of Unique Molecular Identifiers that can be expected. | |
| 81 Format: one column text file, one UMI per line. All UMIs MUST have the same length."/> | |
| 82 </when> | |
| 83 | |
| 84 <when value="text"> | |
| 85 <param name="barcode_text" type="text" area="True" size="10x30" | |
| 86 value="barcode\n" label="Barcode file" | |
| 87 help="BARCODE_FILE. Pre-defined list of Unique Molecular Identifiers that can be expected. | |
| 88 Format: one column text file, one UMI per line. All UMIs MUST have the same length."> | |
| 89 <sanitizer> | |
| 90 <valid initial="string.printable"></valid> | |
| 91 <mapping initial="none"/> | |
| 92 </sanitizer> | |
| 93 </param> | |
| 94 </when> | |
| 95 <when value="no_barcodes"/> | |
| 96 </conditional> | |
| 97 <repeat name="repeat_slots" min="1" title="Unique Molecular Identifier location"> | |
| 98 <param name="SLOTS" type="text" value="-1" label="Where to find the UMIs in the read name" | |
| 99 help="SLOTS. The last position is considered by default (-1). See help below."/> | |
| 100 </repeat> | |
| 101 <param name="MM" type="integer" value="1" min="0" | |
| 102 label="Number of maximum mismatches to consider two Unique Molecular Identifiers (UMIs) similar" | |
| 103 help="MISMATCHES"/> | |
| 104 <param name="MAX_N" type="text" value="" label="Maximum number of Ns a UMI can contain" | |
| 105 help="MAX_NUMBER_OF_N. Above this value, reads are placed in a 'undefined' group. | |
| 106 Default value is the MISMATCHES number."/> | |
| 107 <param name="SPLIT" type="text" value=":" label="Character to split up the header" help="SPLIT"/> | |
| 108 <conditional name="trim_conditional"> | |
| 109 <param name="T" type="select" | |
| 110 label="Should barcode information be removed from read names in the output BAM" help="TRIM_HEADERS"> | |
| 111 <option value="true">Yes</option> | |
| 112 <option value="false" selected="true">No</option> | |
| 113 </param> | |
| 114 <when value="true"> | |
| 115 <repeat name="repeat_tslots" min="1" title="Unique Molecular Identifier location for trimming"> | |
| 116 <param name="TSLOTS" type="text" value="-1" | |
| 117 label="Where to find the UMIs in the read name that should be removed from the header" | |
| 118 help="TSLOTS. Value for SLOTS is considered by default. See help below"/> | |
| 119 </repeat> | |
| 120 </when> | |
| 121 <when value="false"/> | |
| 122 </conditional> | |
| 123 <section name="adv_options" title="Advanced Options" expanded="False"> | |
| 124 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> | |
| 125 <param name="comment" type="text" label="Add this comment to BAM dataset"/> | |
| 126 </repeat> | |
| 127 | |
| 128 <param name="duplicate_scoring_strategy" type="select" label="The scoring strategy for choosing the | |
| 129 non-duplicate among candidates" help="DUPLICATE_SCORING_STRATEGY; default=SUM_OF_BASE_QUALITIES"> | |
| 130 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option> | |
| 131 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option> | |
| 132 </param> | |
| 133 | |
| 134 <param name="read_name_regex" type="text" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*." | |
| 135 label="Regular expression that can be used to parse read names in the incoming SAM/BAM dataset" | |
| 136 help="READ_NAME_REGEX; Read names are parsed to extract three variables: tile/region, x coordinate and | |
| 137 y coordinate. These values are used to estimate the rate of optical duplication in order to give a more | |
| 138 accurate estimated library size. See help below for more info; | |
| 139 default=[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."> | |
| 140 <sanitizer> | |
| 141 <valid initial="string.printable"> | |
| 142 </valid> | |
| 143 </sanitizer> | |
| 144 </param> | |
| 145 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" | |
| 146 label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" | |
| 147 help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/> | |
| 148 | |
| 149 <param name="validation_stringency" type="select" label="Select validation stringency" | |
| 150 help="Setting stringency to SILENT can improve performance when processing a BAM file in which | |
| 151 variable-length data (read, qualities, tags) do not otherwise need to be decoded."> | |
| 152 <option value="LENIENT" selected="True">Lenient</option> | |
| 153 <option value="SILENT">Silent</option> | |
| 154 <option value="STRICT">Strict</option> | |
| 155 </param> | |
| 156 </section> | |
| 157 </inputs> | |
| 158 <outputs> | |
| 159 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: Je-MarkDuplicates BAM output"/> | |
| 160 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: Je-MarkDuplicate metrics"/> | |
| 161 </outputs> | |
| 162 | |
| 163 <tests> | |
| 164 <test> | |
| 165 <!-- picard markduplicates default test --> | |
| 166 <param name="inputFile" value="markdupes_DNase_sorted.bam" ftype="bam"/> | |
| 167 <param name="barcode_list_type_con" value="file"/> | |
| 168 <param name="BARCODE_FILE" value="markdupes_umis.txt" ftype="txt"/> | |
| 169 <param name="repeat_slots_0|SLOTS" value="-1"/> | |
| 170 <param name="repeat_slots_1|SLOTS" value="-2"/> | |
| 171 <param name="MM" value="2"/> | |
| 172 <param name="MAX_N" value="1"/> | |
| 173 <param name="comment" value="test-run"/> | |
| 174 <param name="assume_sorted" value="True"/> | |
| 175 <param name="remove_duplicates" value="True"/> | |
| 176 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/> | |
| 177 <param name="optical_duplicate_pixel_distance" value="100"/> | |
| 178 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> | |
| 179 <param name="validation_stringency" value="LENIENT"/> | |
| 180 <output name="outFile" file="markdupes_DNase_sorted_marked.bam" ftype="bam" lines_diff="2"/> | |
| 181 <output name="metrics_file" file="markdupes_metrics.txt" ftype="txt" lines_diff="4"/> | |
| 182 </test> | |
| 183 </tests> | |
| 184 | |
| 185 | |
| 186 <help> | |
| 187 <![CDATA[ | |
| 188 **What it does** | |
| 189 | |
| 190 Je MarkDupes: Examines aligned records in the supplied SAM or BAM file to locate duplicate molecules taking into account | |
| 191 molecular barcodes (Unique Molecular Identifiers or UMIs) found in read header. | |
| 192 All records are then either written to the output file with the duplicate records flagged or trashed. | |
| 193 | |
| 194 Input file is a bam file. | |
| 195 | |
| 196 Author: Charles Girardot (charles.girardot@embl.de). | |
| 197 | |
| 198 Wrapper by: Jelle Scholtalbers (jelle.scholtalbers@embl.de). | |
| 199 | |
| 200 ------ | |
| 201 | |
| 202 **Know what you are doing** | |
| 203 | |
| 204 .. class:: warningmark | |
| 205 | |
| 206 You will want to read the `documentation`__. | |
| 207 | |
| 208 .. __: http://gbcs.embl.de/portal/Je | |
| 209 | |
| 210 ------ | |
| 211 | |
| 212 **Parameter list** | |
| 213 | |
| 214 This is an exhaustive list of options:: | |
| 215 | |
| 216 INPUT=String | |
| 217 I=String | |
| 218 | |
| 219 One or more input SAM or BAM files to analyze. Must be coordinate sorted. | |
| 220 | |
| 221 Default value: null. This option may be specified 0 or more times. | |
| 222 | |
| 223 OUTPUT=File | |
| 224 O=File | |
| 225 | |
| 226 The output file to write marked records to | |
| 227 | |
| 228 Required. | |
| 229 | |
| 230 MISMATCHES=Integer | |
| 231 MM=Integer | |
| 232 | |
| 233 Number of MisMatches (inclusive) to still consider two Unique Molecular Identifiers | |
| 234 (UMIs) the same i.e. this option buffers for sequencing errors. | |
| 235 Indeed, in case of a sequencing error, 2 duplicate reads would not be considered | |
| 236 duplicates anymore. | |
| 237 Note that N are not considered mismatches during comparison ie ATTNGG and NTTANG are seen | |
| 238 as the same barcode and these two reads would be flagged duplicates. | |
| 239 This option takes a single value even when several barcodes are present (see SLOTS). | |
| 240 Note that when declaring several barcodes (see SLOTS) AND providing a predefined set | |
| 241 of barcodes (see BC option), the MM value is applicable in each lookup. When a predefined | |
| 242 set of barcodes is NOT given, the different barcodes (SLOTS) are concatenated first and | |
| 243 the MM value is therefore considered *overall* as the concatenated code is seen as a | |
| 244 unique code. | |
| 245 MM=null is like MM=0 | |
| 246 Use the minimum Hamming distance of the original barcode set (if applicable). | |
| 247 | |
| 248 Required. | |
| 249 | |
| 250 MAX_NUMBER_OF_N=Integer | |
| 251 MAX_N=Integer | |
| 252 | |
| 253 Maximum number of Ns a molecular code can contain (inclusive). Above this value, reads | |
| 254 are placed in a UNDEF group. | |
| 255 More precisely, these 'too degenarate' codes will not : | |
| 256 * be compared to the list of predefined codes [predefined code list situation ie BC | |
| 257 option given] nor | |
| 258 * be considered as a potential independent code [no predefined code list situation ie | |
| 259 BC option not given] | |
| 260 Default value is the MISMATCHES number. | |
| 261 Note that when declaring several barcodes (see SLOTS) AND providing a predefined set | |
| 262 of barcodes (see BC option), the MAX_N value is applicable to each barcode. When a | |
| 263 predefined set | |
| 264 of barcodes is NOT given, the different barcodes (SLOTS) are concatenated first and the | |
| 265 MAX_N value | |
| 266 is therefore considered *overall*. | |
| 267 | |
| 268 Default value: null. | |
| 269 | |
| 270 | |
| 271 SLOTS=Integer | |
| 272 SLOTS=Integer | |
| 273 | |
| 274 Where to find the UMIs (and only the UMIs) in the read name once read name has been | |
| 275 tokenized using the SPLIT character (e.g. ':'). | |
| 276 By default, the UMI is considered to be found at the end of the read header i.e. after | |
| 277 the last ':'. Use this option to indicate other or additional UMI positions (e.g. | |
| 278 multiple UMIs present in read header. | |
| 279 IMPORTANT: counting starts at 1 and negative numbers can be used to start counting from | |
| 280 the end. | |
| 281 For example, consider the following read name that lists 3 different barcodes in the end: | |
| 282 HISEQ:44:C6KC0ANXX:8:2112:20670:79594:CGATGTTT:GATCCTAG:AAGGTACG | |
| 283 to indicate that the three barcodes are molecular codes, use | |
| 284 SLOTS=-1 SLOTS=-2 SLOTS=-3 | |
| 285 if only the 2 last ones should be considered (the third one being a sample encoding | |
| 286 barcode), use | |
| 287 SLOTS=-1 SLOTS=-2 | |
| 288 | |
| 289 Default value: null. This option may be specified 0 or more times. | |
| 290 | |
| 291 BARCODE_FILE=File | |
| 292 BC=File | |
| 293 | |
| 294 Pre-defined list of UMIs that can be expected. Format: one column text file, one barcode | |
| 295 per line. All UMIs MUST have the same length. | |
| 296 | |
| 297 Default value: null. | |
| 298 | |
| 299 TRIM_HEADERS=Boolean | |
| 300 T=Boolean | |
| 301 | |
| 302 Should barcode information be removed from read names in the output BAM? | |
| 303 | |
| 304 Default value: false. This option can be set to 'null' to clear the default value. | |
| 305 Possible values: {true, false} | |
| 306 | |
| 307 TSLOTS=Integer | |
| 308 TSLOTS=Integer | |
| 309 | |
| 310 Where to find *all* barcode(s) (i.e. sample encoding and UMIs) in the read name once has | |
| 311 been tokenized using the SPLIT character (e.g. ':'). | |
| 312 This option is only considered when TRIM_HEADERS=true. When TSLOTS is ommited while | |
| 313 TRIM_HEADERS=true, the values of SLOTS apply. | |
| 314 IMPORTANT : counting starts at 1 and negative numbers can be used to start counting from | |
| 315 the end. | |
| 316 See SLOT help for examples. | |
| 317 | |
| 318 Default value: null. This option may be specified 0 or more times. | |
| 319 | |
| 320 SPLIT_CHAR=String | |
| 321 SPLIT=String | |
| 322 | |
| 323 Character to use to split up the read header line, default is ':'. | |
| 324 | |
| 325 Default value: ':'. This option can be set to 'null' to clear the default value. | |
| 326 | |
| 327 INPUT=String | |
| 328 I=String | |
| 329 | |
| 330 One or more input SAM or BAM files to analyze. Must be coordinate sorted. | |
| 331 | |
| 332 Default value: null. This option may be specified 0 or more times. | |
| 333 | |
| 334 OUTPUT=File | |
| 335 O=File | |
| 336 | |
| 337 The output file to write marked records to Required. | |
| 338 | |
| 339 METRICS_FILE=File | |
| 340 M=File | |
| 341 | |
| 342 File to write duplication metrics to Required. | |
| 343 | |
| 344 COMMENT=String | |
| 345 CO=String | |
| 346 | |
| 347 Comment(s) to include in the output file's header. | |
| 348 | |
| 349 Default value: null. This option may be specified 0 or more times. | |
| 350 | |
| 351 REMOVE_DUPLICATES=Boolean | |
| 352 | |
| 353 If true do not write duplicates to the output file instead of writing them with | |
| 354 appropriate flags set. | |
| 355 | |
| 356 Default value: false. This option can be set to 'null' to clear | |
| 357 the default value. | |
| 358 Possible values: {true, false} | |
| 359 | |
| 360 ASSUME_SORTED=Boolean | |
| 361 AS=Boolean | |
| 362 | |
| 363 If true, assume that the input file is coordinate sorted even if the header says | |
| 364 otherwise. | |
| 365 | |
| 366 Default value: false. This option can be set to 'null' to clear the default | |
| 367 value. | |
| 368 Possible values: {true, false} | |
| 369 | |
| 370 DUPLICATE_SCORING_STRATEGY=ScoringStrategy | |
| 371 DS=ScoringStrategy | |
| 372 | |
| 373 The scoring strategy for choosing the non-duplicate among candidates. | |
| 374 | |
| 375 Default value: SUM_OF_BASE_QUALITIES. This option can be set to 'null' to clear the default value. | |
| 376 Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} | |
| 377 | |
| 378 READ_NAME_REGEX=String | |
| 379 | |
| 380 Regular expression that can be used to parse read names in the incoming SAM file. Read | |
| 381 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. | |
| 382 These values are used to estimate the rate of optical duplication in order to give a more | |
| 383 accurate estimated library size. Set this option to null to disable optical duplicate | |
| 384 detection. The regular expression should contain three capture groups for the three | |
| 385 variables, in order. It must match the entire read name. Note that if the default regex | |
| 386 is specified, a regex match is not actually done, but instead the read name is split on | |
| 387 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be | |
| 388 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements | |
| 389 are assumed to be tile, x and y values. | |
| 390 | |
| 391 Default value: | |
| 392 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. This option can be set to 'null' to | |
| 393 clear the default value. | |
| 394 | |
| 395 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer | |
| 396 | |
| 397 The maximum offset between two duplicte clusters in order to consider them optical | |
| 398 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) | |
| 399 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in | |
| 400 which case 50-100 is more normal. | |
| 401 | |
| 402 Default value: 100. This option can be set to 'null' | |
| 403 to clear the default value. | |
| 404 | |
| 405 ]]> | |
| 406 </help> | |
| 407 | |
| 408 </tool> |