|
| 1 | +<tool id="iuc_pear" name="Pear" version="0.9.6.1"> |
| 2 | + <description>Paired-End read merger</description> |
| 3 | + <stdio> |
| 4 | + <exit_code range="1:" /> |
| 5 | + <exit_code range=":-1" /> |
| 6 | + <regex match="Error:" /> |
| 7 | + <regex match="Exception:" /> |
| 8 | + </stdio> |
| 9 | + <command> |
| 10 | +<![CDATA[ |
| 11 | + pear |
| 12 | + #if str( $library.type ) == "paired": |
| 13 | + -f "$library.forward" |
| 14 | + -r "$library.reverse" |
| 15 | + #if $library.forward.is_of_type( 'fastqillumina' ): |
| 16 | + --phred-base 64 |
| 17 | + #else: |
| 18 | + --phred-base 33 |
| 19 | + #end if |
| 20 | + #else |
| 21 | + ## prepare collection |
| 22 | + -f "$library.input_collection.forward" |
| 23 | + -r "$library.input_collection.reverse" |
| 24 | + #if $library.input_collection.forward.is_of_type( 'fastqillumina' ): |
| 25 | + --phred-base 64 |
| 26 | + #else: |
| 27 | + --phred-base 33 |
| 28 | + #end if |
| 29 | + #end if |
| 30 | +
|
| 31 | + --output pear |
| 32 | + --p-value $pvalue |
| 33 | + --min-overlap $min_overlap |
| 34 | + #if int($max_assembly_length) > 0: |
| 35 | + --max-asm-length $max_assembly_length |
| 36 | + #end if |
| 37 | + --min-asm-length $min_assembly_length |
| 38 | + --min-trim-length $min_trim_length |
| 39 | + --quality-theshold $quality_threshold |
| 40 | + --max-uncalled-base $max_uncalled_base |
| 41 | + --test-method $test_method |
| 42 | + --empirical-freqs $empirical_freqs |
| 43 | + -j "\${GALAXY_SLOTS:-8}" |
| 44 | + --score-method $score_method |
| 45 | + --cap $cap |
| 46 | + $nbase |
| 47 | +]]> |
| 48 | + </command> |
| 49 | + <inputs> |
| 50 | + <conditional name="library"> |
| 51 | + <param name="type" type="select" label="Dataset type"> |
| 52 | + <option value="paired">Paired-end</option> |
| 53 | + <option value="paired_collection">Paired-end Dataset Collection</option> |
| 54 | + </param> |
| 55 | + <when value="paired"> |
| 56 | + <param name="forward" type="data" format="fastqillumina,fastqsanger" |
| 57 | + label="Name of file that contains the forward paired-end reads" help="-f" /> |
| 58 | + <param name="reverse" type="data" format="fastqillumina,fastqsanger" |
| 59 | + label="Name of file that contains the reverse paired-end reads" help="-r" /> |
| 60 | + </when> |
| 61 | + <when value="paired_collection"> |
| 62 | + <param name="input_collection" format="fastqillumina,fastqsanger" |
| 63 | + type="data_collection" collection_type="paired" |
| 64 | + label="FASTQ Paired Dataset" help="Nucleotide-space: Must have PHRED-scaled quality values. (-f and -r)" /> |
| 65 | + </when> |
| 66 | + </conditional> |
| 67 | + |
| 68 | + <!-- optional --> |
| 69 | + <param name="pvalue" type="float" value="0.01" min="0" optional="True" max="1" label="Specify a p-value for the statistical test" |
| 70 | + help="If the computed p-value of a possible assembly exceeds the specified p-value then the paired-end read will not be assembled. Setting 1.0 disables the test. (--p-value)" /> |
| 71 | + |
| 72 | + <param name="min_overlap" type="integer" value="10" optional="True" label="Minimum overlap size" |
| 73 | + help="The minimum overlap may be set to 1 when the statistical test is used. However, further restricting the minimum overlap size to a proper value may reduce false-positive assembles. (--min-overlap)" /> |
| 74 | + |
| 75 | + <param name="max_assembly_length" type="integer" value="0" optional="True" label="Maximum possible length of the assembled sequences" |
| 76 | + help="Setting this value to 0 disables the restriction and assembled sequences may be arbitrary long. (--max-assembly-length)" /> |
| 77 | + |
| 78 | + <param name="min_assembly_length" type="integer" value="50" optional="True" label="Minimum possible length of the assembled sequences" |
| 79 | + help="Setting this value to 0 disables the restriction and assembled sequences may be arbitrary short. (--min-assembly-length)" /> |
| 80 | + |
| 81 | + <param name="min_trim_length" type="integer" value="1" optional="True" label="Minimum length of reads after trimming the low quality part" |
| 82 | + help="See option -q. (--min-trim-length)" /> |
| 83 | + |
| 84 | + <param name="quality_threshold" type="integer" value="0" optional="True" label="Quality score threshold for trimming the low quality part of a read" |
| 85 | + help="If the quality scores of two consecutive bases are strictly less than the specified threshold, the rest of the read will be trimmed. (--quality-threshold)" /> |
| 86 | + |
| 87 | + <param name="max_uncalled_base" type="float" value="1.0" min="0" optional="True" max="1" label="Maximal proportion of uncalled bases in a read" |
| 88 | + help="Setting this value to 0 will cause PEAR to discard all reads containing uncalled bases. The other extreme setting is 1 which causes PEAR to process all reads independent on the number of uncalled bases. (--max-uncalled-base)" /> |
| 89 | + |
| 90 | + <param name="cap" type="integer" value="40" optional="True" label="Specify the upper bound for the resulting quality score" |
| 91 | + help="If set to zero, capping is disabled. (--cap)" /> |
| 92 | + |
| 93 | + <param name="test_method" type="select" label="Type of statistical test" help="(--test-method)"> |
| 94 | + <option value="1" selected="True">Given the minimum allowed overlap, test using the highest OES (1)</option> |
| 95 | + <option value="2">Use the acceptance probability (2)</option> |
| 96 | + </param> |
| 97 | + |
| 98 | + <param name="empirical_freqs" type="boolean" truevalue="-e" falsevalue="" checked="false" |
| 99 | + label="Disable empirical base frequencies" help="(--empirical-freqs)" /> |
| 100 | + <param name="nbase" type="boolean" truevalue="--nbase" falsevalue="" checked="false" |
| 101 | + label="Use N base if uncertain" help="When merging a base-pair that consists of two non-equal bases out of which none is degenerate, set the merged base to N and use the highest quality score of the two bases. (--nbase)" /> |
| 102 | + |
| 103 | + <param name="score_method" type="select" label="Scoring method" help="(--score-method)"> |
| 104 | + <option value="1">OES with +1 for match and -1 for mismatch</option> |
| 105 | + <option value="2" selected="True">Assembly score (AS) use +1 for match and -1 for mismatch multiplied by base quality scores</option> |
| 106 | + <option value="3">Ignore quality scores and use +1 for a match and -1 for a mismatch</option> |
| 107 | + </param> |
| 108 | + |
| 109 | + <param name="outputs" type="select" display="checkboxes" optional="False" multiple="True" label="Output files"> |
| 110 | + <option value="assembled" selected="True">Assembled reads</option> |
| 111 | + <option value="forward">Forward unassembled reads</option> |
| 112 | + <option value="reverse">Reverse unassembled reads</option> |
| 113 | + <option value="discarded">Discarded reads</option> |
| 114 | + </param> |
| 115 | + </inputs> |
| 116 | + <outputs> |
| 117 | + <data format="input" name="assembled_reads" from_work_dir="pear.assembled.fastq" label="${tool.name} on ${on_string}: Assembled reads"> |
| 118 | + <filter>'assembled' in outputs</filter> |
| 119 | + </data> |
| 120 | + <data format="input" name="unassembled_forward_reads" from_work_dir="pear.unassembled.forward.fastq" label="${tool.name} on ${on_string}: Unassembled forward reads"> |
| 121 | + <filter>'forward' in outputs</filter> |
| 122 | + </data> |
| 123 | + <data format="input" name="unassembled_reverse_reads" from_work_dir="pear.unassembled.reverse.fastq" label="${tool.name} on ${on_string}: Unassembled reverse reads"> |
| 124 | + <filter>'reverse' in outputs</filter> |
| 125 | + </data> |
| 126 | + <data format="input" name="discarded_reads" from_work_dir="pear.discarded.fastq" label="${tool.name} on ${on_string}: Discarded reads"> |
| 127 | + <filter>'discarded' in outputs</filter> |
| 128 | + </data> |
| 129 | + </outputs> |
| 130 | + <tests> |
| 131 | + <test> |
| 132 | + <param name="forward" value="forward.fastq" ftype="fastqsanger" /> |
| 133 | + <param name="reverse" value="reverse.fastq" ftype="fastqsanger" /> |
| 134 | + <param name="min_overlap" value="10" /> |
| 135 | + <param name="min_assembly_length" value="50" /> |
| 136 | + <param name="cap" value="0" /> |
| 137 | + <param name="outputs" value="assembled,forward" /> |
| 138 | + <output name="assembled_reads" file="pear_assembled_results1.fastq" ftype="fastqsanger"/> |
| 139 | + <output name="unassembled_forward_reads" file="pear_unassembled_forward_results1.fastq" ftype="fastqsanger"/> |
| 140 | + </test> |
| 141 | + </tests> |
| 142 | + <help> |
| 143 | +<![CDATA[ |
| 144 | +
|
| 145 | +**What it does** |
| 146 | +
|
| 147 | +PEAR_ is an ultrafast, memory-efficient and highly accurate pair-end read merger. |
| 148 | +PEAR evaluates all possible paired-end read overlaps and without requiring the target fragment |
| 149 | +size as input. In addition, it implements a statistical test for minimizing false-positive results. |
| 150 | +Together with a highly optimized implementation, it can merge millions of paired end reads within a couple of minutes |
| 151 | +on a standard desktop computer. |
| 152 | +
|
| 153 | +For more information please look at the documentation_ and `github repository`_. |
| 154 | +
|
| 155 | +.. _PEAR: http://sco.h-its.org/exelixis/web/software/pear/ |
| 156 | +.. _documentation: http://sco.h-its.org/exelixis/web/software/pear/doc.html |
| 157 | +.. _github repository: https://github.com/xflouris/PEAR |
| 158 | +
|
| 159 | +
|
| 160 | +]]> |
| 161 | + </help> |
| 162 | + <citations> |
| 163 | + <citation type="doi">10.1093/bioinformatics/btt593</citation> |
| 164 | + </citations> |
| 165 | +</tool> |
0 commit comments