Mercurial > repos > jjohnson > find_in_reference
annotate find_in_reference.xml @ 1:e83e0ce8fb68
Add option to reverse the search, find reference field in input field
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Wed, 13 Aug 2014 15:01:33 -0500 |
| parents | e7e56b51d156 |
| children | c4fd2ea4f988 |
| rev | line source |
|---|---|
| 0 | 1 <?xml version="1.0"?> |
|
1
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
2 <tool id="find_in_reference" name="find in reference" version="0.0.2"> |
| 0 | 3 <description>filter peptides that are present in proteins</description> |
| 4 <command interpreter="python">find_in_reference.py --input "$input" | |
| 5 --reference "$reference" | |
| 6 #if $column.set == 'yes': | |
| 7 --input_column $column.input_column | |
| 8 --reference_column $column.reference_column | |
| 9 #end if | |
|
1
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
10 $case_insensitive $reverse_find |
| 0 | 11 #if 'novel' in $outputs.__str__ or not 'found' in $outputs.__str__: |
| 12 --output "$novel" | |
| 13 #end if | |
| 14 #if 'found' in $outputs.__str__: | |
| 15 --filtered "$found" | |
| 16 #if $annotate.from_ref == 'yes' and str($annotate.annotation_columns) != 'None': | |
| 17 --annotation_columns $annotate.annotation_columns | |
| 18 #if $annotate.annotation_separator != '': | |
| 19 --annotation_separator '$annotate.annotation_separator' | |
| 20 #end if | |
| 21 #if $annotate.annotation_col_sep != '': | |
| 22 --annotation_col_sep '$annotate.annotation_col_sep' | |
| 23 #end if | |
| 24 #end if | |
| 25 #end if | |
| 26 </command> | |
| 27 <inputs> | |
| 28 <param name="input" type="data" format="tabular" label="Input file to be filtered" | |
| 29 help="e.g. a peptide fasta converted to tabular"/> | |
| 30 <param name="reference" type="data" format="tabular" label="reference file to search" | |
| 31 help="e.g. a protein fasta converted to tabular"/> | |
| 32 <conditional name="column"> | |
| 33 <param name="set" type="select" label="select columns to compare"> | |
| 34 <option value="no" selected="true">Use last column of input and reference</option> | |
| 35 <option value="yes">Choose the column of input and reference to compare</option> | |
| 36 </param> | |
| 37 <when value="no"/> | |
| 38 <when value="yes"> | |
| 39 <param name="input_column" type="data_column" data_ref="input" label="column in input (defaults to last column)" | |
| 40 help=""/> | |
| 41 <param name="reference_column" type="data_column" data_ref="reference" label="column in reference (defaults to last column)" | |
| 42 help=""/> | |
| 43 </when> | |
| 44 </conditional> | |
| 45 <param name="case_insensitive" type="boolean" truevalue="--case_insensitive" falsevalue="" checked="false" label="Ignore case when comparing"/> | |
|
1
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
46 <param name="reverse_find" type="boolean" truevalue="--reverse_find" falsevalue="" checked="false" label="reverse search: find the reference in the input" /> |
| 0 | 47 <param name="outputs" type="select" multiple="true" display="checkboxes" label="Choose outputs"> |
| 48 <option value="novel" selected="true">lines with no match in reference</option> | |
| 49 <option value="found">lines with match in reference</option> | |
| 50 </param> | |
| 51 <conditional name="annotate"> | |
| 52 <param name="from_ref" type="select" label="Annotate found input entries with columns from reference"> | |
| 53 <option value="no" selected="true">No</option> | |
| 54 <option value="yes">Yes</option> | |
| 55 </param> | |
| 56 <when value="no"/> | |
| 57 <when value="yes"> | |
| 58 <param name="annotation_columns" type="data_column" data_ref="reference" multiple="true" label="columns from reference to append to found input lines" | |
| 59 help=""/> | |
| 60 <param name="annotation_separator" type="text" value=";" optional="true" label="separator to place between annotations from different reference lines" | |
| 61 help="defaults to ;"> | |
| 62 <validator type="regex" message="Single quote character is not allowed">^[^']*$</validator> | |
| 63 <sanitizer> | |
| 64 <valid initial="string.printable"> | |
| 65 <remove value="'"/> | |
| 66 </valid> | |
| 67 <mapping initial="none"> | |
| 68 <add source="'" target=""/> | |
| 69 </mapping> | |
| 70 </sanitizer> | |
| 71 </param> | |
| 72 <param name="annotation_col_sep" type="text" value="," optional="true" label="separator to place between annotation columns from the same reference line" | |
| 73 help="defaults to ,"> | |
| 74 <validator type="regex" message="Single quote character is not allowed">^[^']*$</validator> | |
| 75 <sanitizer> | |
| 76 <valid initial="string.printable"> | |
| 77 <remove value="'"/> | |
| 78 </valid> | |
| 79 <mapping initial="none"> | |
| 80 <add source="'" target=""/> | |
| 81 </mapping> | |
| 82 </sanitizer> | |
| 83 </param> | |
| 84 </when> | |
| 85 </conditional> | |
| 86 </inputs> | |
| 87 <stdio> | |
| 88 <exit_code range="1:" level="fatal" description="Error" /> | |
| 89 </stdio> | |
| 90 <outputs> | |
| 91 <data name="found" metadata_source="input" format_source="input" label="${tool.name} on ${on_string}: found"> | |
| 92 <filter>'found' in str(outputs)</filter> | |
| 93 </data> | |
| 94 <data name="novel" metadata_source="input" format_source="input" label="${tool.name} on ${on_string}: novel"> | |
| 95 <filter>'novel' in str(outputs) or not 'found' in str(outputs)</filter> | |
| 96 </data> | |
| 97 </outputs> | |
| 98 <tests> | |
| 99 <test> | |
| 100 <param name="input" value="human_peptides.tabular" ftype="tabular" dbkey="hg19"/> | |
| 101 <param name="reference" value="human_proteins.tabular" ftype="tabular" dbkey="hg19"/> | |
| 102 <output name="novel" file="novel_peptides.tabular"/> | |
| 103 </test> | |
|
1
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
104 <test> |
|
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
105 <param name="input" value="human_proteins.tabular" ftype="tabular" dbkey="hg19"/> |
|
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
106 <param name="reference" value="human_peptides.tabular" ftype="tabular" dbkey="hg19"/> |
|
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
107 <param name="reverse_find" value="True"/> |
|
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
108 <param name="outputs" value="found"/> |
|
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
109 <output name="found" file="found_proteins.tabular"/> |
|
e83e0ce8fb68
Add option to reverse the search, find reference field in input field
Jim Johnson <jj@umn.edu>
parents:
0
diff
changeset
|
110 </test> |
| 0 | 111 </tests> |
| 112 <help> | |
| 113 **Find in Reference** | |
| 114 | |
| 115 Filters lines of a tabular input file by checking if the selected input column value | |
| 116 is a substring of the selected column of any line in the reference file. | |
| 117 | |
| 118 This can be used to check if peptides sequences are present in a set of reference proteins, | |
| 119 as a means of filtering out uninteresting peptide sequences. | |
| 120 | |
| 121 For Example with:: | |
| 122 | |
| 123 Input | |
| 124 >pep1 LIL | |
| 125 >pep2 WTF | |
| 126 >pep3 ISK | |
| 127 | |
| 128 Reference | |
| 129 >prot1 RLET | |
| 130 >prot2 LLIL | |
| 131 >prot3 LAPSE | |
| 132 >prot3 RISKY | |
| 133 | |
| 134 The outputs | |
| 135 | |
| 136 Not found in reference | |
| 137 >pep2 WTF | |
| 138 | |
| 139 Found in reference | |
| 140 >pep1 LIL | |
| 141 >pep3 ISK | |
| 142 | |
| 143 | |
| 144 </help> | |
| 145 </tool> |