Mercurial > repos > pjbriggs > trimmomatic
annotate trimmomatic.xml @ 7:77dd0fe954c5 draft
Uploaded v0.36.2 which add support for fastq.gz.
| author | pjbriggs |
|---|---|
| date | Fri, 24 Feb 2017 04:57:13 -0500 |
| parents | b9415df5fc32 |
| children | a923b799c77c |
| rev | line source |
|---|---|
| 7 | 1 <tool id="trimmomatic" name="Trimmomatic" version="0.36.2"> |
| 1 | 2 <description>flexible read trimming tool for Illumina NGS data</description> |
|
5
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
3 <macros> |
|
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
4 <import>trimmomatic_macros.xml</import> |
|
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
5 </macros> |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
6 <requirements> |
| 4 | 7 <requirement type="package" version="0.36">trimmomatic</requirement> |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
8 </requirements> |
| 7 | 9 <command detect_errors="aggressive"><![CDATA[ |
|
5
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
10 @CONDA_TRIMMOMATIC_JAR_PATH@ && |
|
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
11 @CONDA_TRIMMOMATIC_ADAPTERS_PATH@ && |
| 7 | 12 #if $readtype.single_or_paired == "pair_of_files" |
| 13 #set r1_ext = $readtype.fastq_r1_in.extension | |
| 14 #set r2_ext = $readtype.fastq_r2_in.extension | |
| 15 ln -s '$readtype.fastq_r1_in' fastq_r1.'$r1_ext' && | |
| 16 ln -s '$readtype.fastq_r2_in' fastq_r2.'$r2_ext' && | |
| 17 #elif $readtype.single_or_paired == "collection" | |
| 18 #set r1_ext = $readtype.fastq_pair.forward.extension | |
| 19 #set r2_ext = $readtype.fastq_pair.reverse.extension | |
| 20 ln -s '$readtype.fastq_pair.forward' fastq_r1.'$r1_ext' && | |
| 21 ln -s '$readtype.fastq_pair.reverse' fastq_r2.'$r2_ext' && | |
| 22 #else | |
| 23 ln -s '$fastq_in' fastq_in.'$fastq_in.extension' && | |
| 24 #end if | |
| 25 java \${_JAVA_OPTIONS:--Xmx8G} -jar \$TRIMMOMATIC_JAR_PATH/trimmomatic.jar | |
| 26 #if $readtype.single_or_paired in ["pair_of_files","collection"] | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
27 PE -threads \${GALAXY_SLOTS:-6} -phred33 |
| 7 | 28 fastq_r1.'$r1_ext' fastq_r2.'$r2_ext' |
| 29 fastq_out_r1_paired.'$r1_ext' fastq_out_r1_unpaired.'$r1_ext' | |
| 30 fastq_out_r2_paired.'$r2_ext' fastq_out_r2_unpaired.'$r2_ext' | |
| 1 | 31 #else |
| 7 | 32 SE -threads \${GALAXY_SLOTS:-6} -phred33 fastq_in.'$fastq_in.extension' fastq_out.'$fastq_in.extension' |
| 1 | 33 #end if |
| 34 ## ILLUMINACLIP option | |
| 35 #if $illuminaclip.do_illuminaclip | |
|
5
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
36 ILLUMINACLIP:\$TRIMMOMATIC_ADAPTERS_PATH/$illuminaclip.adapter_fasta:$illuminaclip.seed_mismatches:$illuminaclip.palindrome_clip_threshold:$illuminaclip.simple_clip_threshold |
| 1 | 37 #end if |
| 38 ## Other operations | |
| 39 #for $op in $operations | |
| 40 ## SLIDINGWINDOW | |
| 41 #if str( $op.operation.name ) == "SLIDINGWINDOW" | |
| 42 SLIDINGWINDOW:$op.operation.window_size:$op.operation.required_quality | |
| 43 #end if | |
| 44 ## MINLEN:36 | |
| 45 #if str( $op.operation.name ) == "MINLEN" | |
| 46 MINLEN:$op.operation.minlen | |
| 47 #end if | |
| 48 #if str( $op.operation.name ) == "LEADING" | |
| 49 LEADING:$op.operation.leading | |
| 50 #end if | |
| 51 #if str( $op.operation.name ) == "TRAILING" | |
| 52 TRAILING:$op.operation.trailing | |
| 53 #end if | |
| 54 #if str( $op.operation.name ) == "CROP" | |
| 55 CROP:$op.operation.crop | |
| 56 #end if | |
| 57 #if str( $op.operation.name ) == "HEADCROP" | |
| 58 HEADCROP:$op.operation.headcrop | |
| 59 #end if | |
| 4 | 60 #if str( $op.operation.name ) == "AVGQUAL" |
| 61 AVGQUAL:$op.operation.avgqual | |
| 62 #end if | |
| 63 #if str( $op.operation.name ) == "MAXINFO" | |
| 64 MAXINFO:$op.operation.target_length:$op.operation.strictness | |
| 65 #end if | |
| 1 | 66 #end for |
|
5
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
67 2>&1 | tee trimmomatic.log && |
|
b0315888eb4d
Test for version which is compatible with conda dependency resolver.
pjbriggs
parents:
4
diff
changeset
|
68 if [ -z "\$(tail -1 trimmomatic.log | grep "Completed successfully")" ]; then echo "Trimmomatic did not finish successfully" >&2 ; exit 1 ; fi |
| 7 | 69 && |
| 70 #if $readtype.single_or_paired == "pair_of_files" | |
| 71 mv fastq_out_r1_paired.'$r1_ext' '${fastq_out_r1_paired}' && | |
| 72 mv fastq_out_r1_unpaired.'$r1_ext' '${fastq_out_r1_unpaired}' && | |
| 73 mv fastq_out_r2_paired.'$r2_ext' '${fastq_out_r2_paired}' && | |
| 74 mv fastq_out_r2_unpaired.'$r2_ext' '${fastq_out_r2_unpaired}' | |
| 75 #elif $readtype.single_or_paired == "collection" | |
| 76 mv fastq_out_r1_paired.'$r1_ext' '${fastq_out_paired.forward}' && | |
| 77 mv fastq_out_r1_unpaired.'$r1_ext' '${fastq_out_unpaired.forward}' && | |
| 78 mv fastq_out_r2_paired.'$r2_ext' '${fastq_out_paired.reverse}' && | |
| 79 mv fastq_out_r2_unpaired.'$r2_ext' '${fastq_out_unpaired.reverse}' | |
| 80 #else | |
| 81 mv fastq_out.'$fastq_in.extension' '${fastq_out}' | |
| 82 #end if | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
83 ]]></command> |
| 1 | 84 <inputs> |
| 7 | 85 <conditional name="readtype"> |
| 86 <param name="single_or_paired" type="select" label="Single-end or paired-end reads?"> | |
| 87 <option value="se" selected="true">Single-end</option> | |
| 88 <option value="pair_of_files">Paired-end (two separate input files)</option> | |
| 89 <option value="collection">Paired-end (as collection)</option> | |
| 90 </param> | |
| 91 <when value="se"> | |
| 92 <param name="fastq_in" type="data" format="fastqsanger,fastqsanger.gz" label="Input FASTQ file" /> | |
| 1 | 93 </when> |
| 7 | 94 <when value="pair_of_files"> |
| 95 <param name="fastq_r1_in" type="data" format="fastqsanger,fastqsanger.gz" | |
| 96 label="Input FASTQ file (R1/first of pair)" /> | |
| 97 <param name="fastq_r2_in" type="data" format="fastqsanger,fastqgsanger.gz" | |
| 98 label="Input FASTQ file (R2/second of pair)" /> | |
| 1 | 99 </when> |
| 7 | 100 <when value="collection"> |
| 101 <param name="fastq_pair" format="fastqsanger,fastqsanger.gz" type="data_collection" collection_type="paired" label="Select FASTQ dataset collection with R1/R2 pair" /> | |
| 102 </when> | |
| 1 | 103 </conditional> |
| 104 <conditional name="illuminaclip"> | |
| 7 | 105 <param name="do_illuminaclip" type="boolean" label="Perform initial ILLUMINACLIP step?" help="Cut adapter and other illumina-specific sequences from the read" truevalue="yes" falsevalue="no" checked="False" /> |
| 106 <when value="yes"> | |
| 107 <param name="adapter_fasta" type="select" label="Adapter sequences to use"> | |
| 108 <option value="TruSeq2-SE.fa">TruSeq2 (single-ended, for Illumina GAII)</option> | |
| 109 <option value="TruSeq3-SE.fa">TruSeq3 (single-ended, for MiSeq and HiSeq)</option> | |
| 110 <option value="TruSeq2-PE.fa">TruSeq2 (paired-ended, for Illumina GAII)</option> | |
| 111 <option value="TruSeq3-PE.fa">TruSeq3 (paired-ended, for MiSeq and HiSeq)</option> | |
| 112 <option value="TruSeq3-PE-2.fa">TruSeq3 (additional seqs) (paired-ended, for MiSeq and HiSeq)</option> | |
| 113 <option value="NexteraPE-PE.fa">Nextera (paired-ended)</option> | |
| 114 </param> | |
| 115 <param name="seed_mismatches" type="integer" label="Maximum mismatch count which will still allow a full match to be performed" value="2" /> | |
| 116 <param name="palindrome_clip_threshold" type="integer" label="How accurate the match between the two 'adapter ligated' reads must be for PE palindrome read alignment" value="30" /> | |
| 117 <param name="simple_clip_threshold" type="integer" label="How accurate the match between any adapter etc. sequence must be against a read" value="10" /> | |
| 118 </when> | |
| 119 <when value="no" /> <!-- empty clause to satisfy planemo lint --> | |
| 1 | 120 </conditional> |
| 121 <repeat name="operations" title="Trimmomatic Operation" min="1"> | |
| 122 <conditional name="operation"> | |
| 7 | 123 <param name="name" type="select" label="Select Trimmomatic operation to perform"> |
| 124 <option selected="true" value="SLIDINGWINDOW">Sliding window trimming (SLIDINGWINDOW)</option> | |
| 125 <option value="MINLEN">Drop reads below a specified length (MINLEN)</option> | |
| 126 <option value="LEADING">Cut bases off the start of a read, if below a threshold quality (LEADING)</option> | |
| 127 <option value="TRAILING">Cut bases off the end of a read, if below a threshold quality (TRAILING)</option> | |
| 128 <option value="CROP">Cut the read to a specified length (CROP)</option> | |
| 129 <option value="HEADCROP">Cut the specified number of bases from the start of the read (HEADCROP)</option> | |
| 130 <option value="AVGQUAL">Drop reads with average quality lower than a specified level (AVGQUAL)</option> | |
| 131 <option value="MAXINFO">Trim reads adaptively, balancing read length and error rate to maximise the value of each read (MAXINFO)</option> | |
| 132 </param> | |
| 133 <when value="SLIDINGWINDOW"> | |
| 134 <param name="window_size" type="integer" label="Number of bases to average across" value="4" /> | |
| 135 <param name="required_quality" type="integer" label="Average quality required" value="20" /> | |
| 136 </when> | |
| 137 <when value="MINLEN"> | |
| 138 <param name="minlen" type="integer" label="Minimum length of reads to be kept" value="20" /> | |
| 139 </when> | |
| 140 <when value="LEADING"> | |
| 141 <param name="leading" type="integer" label="Minimum quality required to keep a base" value="3" help="Bases at the start of the read with quality below the threshold will be removed" /> | |
| 142 </when> | |
| 143 <when value="TRAILING"> | |
| 144 <param name="trailing" type="integer" label="Minimum quality required to keep a base" value="3" help="Bases at the end of the read with quality below the threshold will be removed" /> | |
| 145 </when> | |
| 146 <when value="CROP"> | |
| 147 <param name="crop" type="integer" label="Number of bases to keep from the start of the read" value="" /> | |
| 148 </when> | |
| 149 <when value="HEADCROP"> | |
| 150 <param name="headcrop" type="integer" label="Number of bases to remove from the start of the read" value="" /> | |
| 151 </when> | |
| 152 <when value="AVGQUAL"> | |
| 153 <param name="avgqual" type="integer" label="Minimum average quality required to keep a read" value="" /> | |
| 154 </when> | |
| 155 <when value="MAXINFO"> | |
| 156 <param name="target_length" type="integer" label="Target read length" value="" help="The read length which is likely to allow the location of the read within the target sequence to be determined." /> | |
| 157 <param name="strictness" type="float" label="Strictness" value="" help="Set between zero and one - specifies the balance between preserving read length versus removal of incorrect bases; low values (<0.2) favours longer reads, high values (>0.8) favours read correctness." /> | |
| 158 </when> | |
| 1 | 159 </conditional> |
| 160 </repeat> | |
| 161 </inputs> | |
| 162 <outputs> | |
| 7 | 163 <data name="fastq_out_r1_paired" label="${tool.name} on ${readtype.fastq_r1_in.name} (R1 paired)" format_source="fastq_r1_in"> |
| 164 <filter>readtype['single_or_paired'] == "pair_of_files"</filter> | |
| 1 | 165 </data> |
| 7 | 166 <data name="fastq_out_r2_paired" label="${tool.name} on ${readtype.fastq_r2_in.name} (R2 paired)" format_source="fastq_r2_in"> |
| 167 <filter>readtype['single_or_paired'] == "pair_of_files"</filter> | |
| 1 | 168 </data> |
| 7 | 169 <data name="fastq_out_r1_unpaired" label="${tool.name} on ${readtype.fastq_r1_in.name} (R1 unpaired)" format_source="fastq_r1_in"> |
| 170 <filter>readtype['single_or_paired'] == "pair_of_files"</filter> | |
| 1 | 171 </data> |
| 7 | 172 <data name="fastq_out_r2_unpaired" label="${tool.name} on ${readtype.fastq_r2_in.name} (R2 unpaired)" format_source="fastq_r2_in"> |
| 173 <filter>readtype['single_or_paired'] == "pair_of_files"</filter> | |
| 1 | 174 </data> |
| 7 | 175 <data name="fastq_out" label="${tool.name} on ${readtype.fastq_in.name}" format_source="fastq_in"> |
| 176 <filter>readtype['single_or_paired'] == 'se'</filter> | |
| 1 | 177 </data> |
| 7 | 178 <collection name="fastq_out_paired" type="paired" label="${tool.name} on ${readtype.fastq_pair.name}: paired"> |
| 179 <filter>readtype['single_or_paired'] == "collection"</filter> | |
| 180 <data name="forward" label="${tool.name} on ${readtype.fastq_pair.forward.name} (R1 paired)" format_source="fastq_pair['forward']"/> | |
| 181 <data name="reverse" label="${tool.name} on ${readtype.fastq_pair.reverse.name} (R2 paired)" format_source="fastq_pair['reverse']"/> | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
182 </collection> |
| 7 | 183 <collection name="fastq_out_unpaired" type="paired" label="${tool.name} on ${readtype.fastq_pair.name}: unpaired"> |
| 184 <filter>readtype['single_or_paired'] == "collection"</filter> | |
| 185 <data name="forward" label="${tool.name} on ${readtype.fastq_pair.forward.name} (R1 unpaired)" format_source="fastq_pair['forward']"/> | |
| 186 <data name="reverse" label="${tool.name} on ${readtype.fastq_pair.reverse.name} (R2 unpaired)" format_source="fastq_pair['reverse']"/> | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
187 </collection> |
| 7 | 188 |
| 1 | 189 </outputs> |
| 190 <tests> | |
| 191 <test> | |
| 192 <!-- Single-end example --> | |
| 7 | 193 <param name="single_or_paired" value="se" /> |
| 1 | 194 <param name="fastq_in" value="Illumina_SG_R1.fastq" ftype="fastqsanger" /> |
| 195 <param name="operations_0|operation|name" value="SLIDINGWINDOW" /> | |
| 196 <output name="fastq_out" file="trimmomatic_se_out1.fastq" /> | |
| 197 </test> | |
| 198 <test> | |
| 7 | 199 <!-- Single-end example - gzipped --> |
| 200 <param name="single_or_paired" value="se" /> | |
| 201 <param name="fastq_in" value="Illumina_SG_R1.fastq.gz" ftype="fastqsanger.gz" /> | |
| 202 <param name="operations_0|operation|name" value="SLIDINGWINDOW" /> | |
| 203 <output name="fastq_out" file="trimmomatic_se_out1.fastq.gz" /> | |
| 204 </test> | |
| 205 <test> | |
| 206 <!-- Paired-end example - gzipped --> | |
| 207 <param name="single_or_paired" value="pair_of_files" /> | |
| 208 <param name="fastq_r1_in" value="Illumina_SG_R1.fastq.gz" ftype="fastqsanger.gz" /> | |
| 209 <param name="fastq_r2_in" value="Illumina_SG_R2.fastq.gz" ftype="fastqsanger.gz" /> | |
| 210 <param name="operations_0|operation|name" value="SLIDINGWINDOW" /> | |
| 211 <output name="fastq_out_r1_paired" file="trimmomatic_pe_r1_paired_out1.fastq.gz" /> | |
| 212 <output name="fastq_out_r1_unpaired" file="trimmomatic_pe_r1_unpaired_out1.fastq.gz" /> | |
| 213 <output name="fastq_out_r2_paired" file="trimmomatic_pe_r2_paired_out1.fastq.gz" /> | |
| 214 <output name="fastq_out_r2_unpaired" file="trimmomatic_pe_r2_unpaired_out1.fastq.gz" /> | |
| 215 </test> | |
| 216 <test> | |
| 1 | 217 <!-- Paired-end example --> |
| 7 | 218 <param name="single_or_paired" value="pair_of_files" /> |
| 1 | 219 <param name="fastq_r1_in" value="Illumina_SG_R1.fastq" ftype="fastqsanger" /> |
| 220 <param name="fastq_r2_in" value="Illumina_SG_R2.fastq" ftype="fastqsanger" /> | |
| 221 <param name="operations_0|operation|name" value="SLIDINGWINDOW" /> | |
| 222 <output name="fastq_out_r1_paired" file="trimmomatic_pe_r1_paired_out1.fastq" /> | |
| 223 <output name="fastq_out_r1_unpaired" file="trimmomatic_pe_r1_unpaired_out1.fastq" /> | |
| 224 <output name="fastq_out_r2_paired" file="trimmomatic_pe_r2_paired_out1.fastq" /> | |
| 225 <output name="fastq_out_r2_unpaired" file="trimmomatic_pe_r2_unpaired_out1.fastq" /> | |
| 226 </test> | |
| 227 <test> | |
| 228 <!-- Single-end example (cropping) --> | |
| 7 | 229 <param name="single_or_paired" value="se" /> |
| 1 | 230 <param name="fastq_in" value="Illumina_SG_R1.fastq" ftype="fastqsanger" /> |
| 231 <param name="operations_0|operation|name" value="CROP" /> | |
| 232 <param name="operations_0|operation|crop" value="10" /> | |
| 233 <output name="fastq_out" file="trimmomatic_se_out2.fastq" /> | |
| 234 </test> | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
235 <test> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
236 <!-- Paired-end with dataset collection --> |
| 7 | 237 <param name="single_or_paired" value="collection" /> |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
238 <param name="fastq_pair"> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
239 <collection type="paired"> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
240 <element name="forward" value="Illumina_SG_R1.fastq" ftype="fastqsanger" /> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
241 <element name="reverse" value="Illumina_SG_R2.fastq" ftype="fastqsanger"/> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
242 </collection> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
243 </param> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
244 <param name="operations_0|operation|name" value="SLIDINGWINDOW" /> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
245 <output_collection name="fastq_out_paired" type="paired"> |
| 7 | 246 <element name="forward" file="trimmomatic_pe_r1_paired_out1.fastq" /> |
| 247 <element name="reverse" file="trimmomatic_pe_r2_paired_out1.fastq" /> | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
248 </output_collection> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
249 <output_collection name="fastq_out_unpaired" type="paired"> |
| 7 | 250 <element name="forward" file="trimmomatic_pe_r1_unpaired_out1.fastq" /> |
| 251 <element name="reverse" file="trimmomatic_pe_r2_unpaired_out1.fastq" /> | |
| 252 </output_collection> | |
| 253 </test> | |
| 254 <test> | |
| 255 <!-- Paired-end with dataset collection - gzipped --> | |
| 256 <param name="single_or_paired" value="collection" /> | |
| 257 <param name="fastq_pair"> | |
| 258 <collection type="paired"> | |
| 259 <element name="forward" value="Illumina_SG_R1.fastq.gz" ftype="fastqsanger.gz" /> | |
| 260 <element name="reverse" value="Illumina_SG_R2.fastq.gz" ftype="fastqsanger.gz"/> | |
| 261 </collection> | |
| 262 </param> | |
| 263 <param name="operations_0|operation|name" value="SLIDINGWINDOW" /> | |
| 264 <output_collection name="fastq_out_paired" type="paired"> | |
| 265 <element name="forward" file="trimmomatic_pe_r1_paired_out1.fastq.gz" /> | |
| 266 <element name="reverse" file="trimmomatic_pe_r2_paired_out1.fastq.gz" /> | |
| 267 </output_collection> | |
| 268 <output_collection name="fastq_out_unpaired" type="paired"> | |
| 269 <element name="forward" file="trimmomatic_pe_r1_unpaired_out1.fastq.gz" /> | |
| 270 <element name="reverse" file="trimmomatic_pe_r2_unpaired_out1.fastq.gz" /> | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
271 </output_collection> |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
272 </test> |
| 4 | 273 <test> |
| 274 <!-- Single-end using AVGQUAL --> | |
| 7 | 275 <param name="single_or_paired" value="se" /> |
| 4 | 276 <param name="fastq_in" value="Illumina_SG_R1.fastq" ftype="fastqsanger" /> |
| 277 <param name="operations_0|operation|name" value="AVGQUAL" /> | |
| 278 <param name="operations_0|operation|avgqual" value="30" /> | |
| 279 <output name="fastq_out" file="trimmomatic_avgqual.fastq" /> | |
| 280 </test> | |
| 281 <test> | |
| 282 <!-- Single-end using MAXINFO --> | |
| 7 | 283 <param name="single_or_paired" value="se" /> |
| 4 | 284 <param name="fastq_in" value="Illumina_SG_R1.fastq" ftype="fastqsanger" /> |
| 285 <param name="operations_0|operation|name" value="MAXINFO" /> | |
| 286 <param name="operations_0|operation|target_length" value="75" /> | |
| 287 <param name="operations_0|operation|strictness" value="0.8" /> | |
| 288 <output name="fastq_out" file="trimmomatic_maxinfo.fastq" /> | |
| 289 </test> | |
| 1 | 290 </tests> |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
291 <help><![CDATA[ |
| 1 | 292 .. class:: infomark |
| 293 | |
| 294 **What it does** | |
| 295 | |
| 296 Trimmomatic performs a variety of useful trimming tasks for illumina paired-end and | |
| 297 single ended data. | |
| 298 | |
| 299 This tool allows the following trimming steps to be performed: | |
| 300 | |
| 301 * **ILLUMINACLIP:** Cut adapter and other illumina-specific sequences from the read | |
| 302 * **SLIDINGWINDOW:** Perform a sliding window trimming, cutting once the average | |
| 303 quality within the window falls below a threshold | |
| 304 * **MINLEN:** Drop the read if it is below a specified length | |
| 305 * **LEADING:** Cut bases off the start of a read, if below a threshold quality | |
| 306 * **TRAILING:** Cut bases off the end of a read, if below a threshold quality | |
| 307 * **CROP:** Cut the read to a specified length | |
| 308 * **HEADCROP:** Cut the specified number of bases from the start of the read | |
| 4 | 309 * **AVGQUAL:** Drop the read if the average quality is below a specified value |
| 7 | 310 * **MAXINFO:** Trim reads adaptively, balancing read length and error rate to |
| 4 | 311 maximise the value of each read |
| 1 | 312 |
| 313 If ILLUMINACLIP is requested then it is always performed first; subsequent options | |
| 314 can be mixed and matched and will be performed in the order that they have been | |
| 315 specified. | |
| 316 | |
| 317 .. class:: warningmark | |
| 318 | |
| 319 Note that trimming operation order is important. | |
| 320 | |
| 321 ------------- | |
| 322 | |
| 323 .. class:: infomark | |
| 324 | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
325 **Inputs** |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
326 |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
327 For single-end data this Trimmomatic tool accepts a single FASTQ file; for |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
328 paired-end data it will accept either two FASTQ files (R1 and R2), or a |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
329 dataset collection containing the R1/R2 FASTQ pair. |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
330 |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
331 .. class:: infomark |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
332 |
| 1 | 333 **Outputs** |
| 334 | |
| 335 For paired-end data a particular strength of Trimmomatic is that it retains the | |
| 336 pairing of reads (from R1 and R2) in the filtered output files: | |
| 337 | |
| 338 * Two FASTQ files (R1-paired and R2-paired) contain one read from each pair where | |
| 339 both have survived filtering. | |
| 340 * Additionally two FASTQ files (R1-unpaired and R2-unpaired) contain reads where | |
| 341 one of the pair failed the filtering steps. | |
| 342 | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
343 .. class:: warningmark |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
344 |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
345 If the input consists of a dataset collection with the R1/R2 FASTQ pair then |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
346 the outputs will also inclue two dataset collections: one for the 'paired' |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
347 outputs and one for the 'unpaired' (as described above) |
|
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
348 |
| 1 | 349 Retaining the same order and number of reads in the filtered output fastq files is |
| 350 essential for many downstream analysis tools. | |
| 351 | |
| 352 For single-end data the output is a single FASTQ file containing just the filtered | |
| 353 reads. | |
| 354 | |
| 355 ------------- | |
| 356 | |
| 357 .. class:: infomark | |
| 358 | |
| 359 **Credits** | |
| 360 | |
| 361 This Galaxy tool has been developed within the Bioinformatics Core Facility at the | |
| 7 | 362 University of Manchester, with contributions from Peter van Heusden and Marius |
| 363 van den Beek. | |
| 364 | |
| 365 It runs the Trimmomatic program which has been developed | |
| 1 | 366 within Bjorn Usadel's group at RWTH Aachen university. |
| 367 | |
| 368 Trimmomatic website (including documentation): | |
| 369 | |
| 7 | 370 * http://www.usadellab.org/cms/index.php?page=trimmomatic |
| 1 | 371 |
| 372 The reference for Trimmomatic is: | |
| 373 | |
| 374 * Bolger, A.M., Lohse, M., & Usadel, B. (2014). Trimmomatic: A flexible trimmer | |
| 375 for Illumina Sequence Data. Bioinformatics, btu170. | |
| 376 | |
| 377 Please kindly acknowledge both this Galaxy tool and the Trimmomatic program if you | |
| 378 use it. | |
|
3
a7139c612c45
Updated to version 0.32.3: add support for FASTQ pairs (dataset collections)
pjbriggs
parents:
2
diff
changeset
|
379 ]]></help> |
| 1 | 380 <citations> |
| 381 <!-- | |
| 382 See https://wiki.galaxyproject.org/Admin/Tools/ToolConfigSyntax#A.3Ccitations.3E_tag_set | |
| 383 Can be either DOI or Bibtex | |
| 384 Use http://www.bioinformatics.org/texmed/ to convert PubMed to Bibtex | |
| 385 --> | |
| 386 <citation type="doi">10.1093/bioinformatics/btu170</citation> | |
| 387 </citations> | |
| 388 </tool> |