Mercurial > repos > bgruening > text_processing
diff multijoin.xml @ 0:5314e5d6f040 draft
Imported from capsule None
| author | bgruening |
|---|---|
| date | Thu, 29 Jan 2015 07:53:17 -0500 |
| parents | |
| children | 37e1eb05b1b4 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/multijoin.xml Thu Jan 29 07:53:17 2015 -0500 @@ -0,0 +1,133 @@ +<tool id="tp_multijoin_tool" name="Multi-Join" version="@BASE_VERSION@.0"> + <description>(combine multiple files)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"> + <requirement type="package" version="5.18.1">perl</requirement> + <requirement type="package" version="1.0">text_processing_perl_packages</requirement> + </expand> + <command interpreter="perl"> +<![CDATA[ + multijoin + --key '$key_column' + --values '$value_columns' + --filler '$filler' + $ignore_dups + $output_header + $input_header + $first_file + #for $file in $files: + '$file' + #end for + > '$outfile' +]]> + </command> + <inputs> + <param name="first_file" type="data" format="txt" label="File to join"/> + <param name="files" multiple="True" type="data" format="txt" label="add additional file" /> + + <param name="key_column" label="Common key column" type="integer" + value="1" help="Usually gene-ID or other common value" /> + + <param name="value_columns" label="Column with values to preserve" + type="data_column" data_ref="first_file" accept_default="true" multiple="True" display="checkboxes"/> + + <param name="output_header" type="boolean" checked="false" truevalue="--out-header" falsevalue="" label="Add header line to the output file" help="" /> + <param name="input_header" type="boolean" checked="false" truevalue="--in-header" falsevalue="" label="Input files contain a header line (as first line)" help="" /> + <param name="ignore_dups" type="boolean" checked="false" truevalue="--ignore-dups" falsevalue="" label="Ignore duplicated keys" help="If not set, duplicated keys in the same file will cause an error." /> + <param name="filler" type="text" size="20" value="0" label="Value to put in unpaired (empty) fields"> + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + </sanitizer> + </param> + </inputs> + <outputs> + <data name="outfile" format_source="first_file" metadata_source="first_file" /> + </outputs> + <tests> + <test> + <param name="first_file" value="multijoin1.txt" /> + <param name="files" value="multijoin2.txt,multijoin3.txt" /> + <param name="key_column" value="4" /> + <param name="value_columns" value="c7,c8,c9" /> + <param name="output_header" value="True" /> + <output name="outfile" file="multijoin_result1.txt" /> + </test> + </tests> + <help> +<![CDATA[ +**What it does** + +This tool joins multiple tabular files based on a common key column. + +----- + +**Example** + +To join three files, based on the 4th column, and keeping the 7th,8th,9th columns: + +**First file (AAA)**:: + + chr4 888449 890171 FBtr0308778 0 + 266 1527 1722 + chr4 972167 979017 FBtr0310651 0 - 3944 6428 6850 + chr4 972186 979017 FBtr0089229 0 - 3944 6428 6831 + chr4 972186 979017 FBtr0089231 0 - 3944 6428 6831 + chr4 972186 979017 FBtr0089233 0 - 3944 6428 6831 + chr4 995793 996435 FBtr0111046 0 + 7 166 642 + chr4 995793 997931 FBtr0111044 0 + 28 683 2138 + chr4 995793 997931 FBtr0111045 0 + 28 683 2138 + chr4 1034029 1047719 FBtr0089223 0 - 5293 13394 13690 + ... + + +**Second File (BBB)**:: + + chr4 90286 134453 FBtr0309803 0 + 657 29084 44167 + chr4 251355 266499 FBtr0089116 0 + 56 1296 15144 + chr4 252050 266506 FBtr0308086 0 + 56 1296 14456 + chr4 252050 266506 FBtr0308087 0 + 56 1296 14456 + chr4 252053 266528 FBtr0300796 0 + 56 1296 14475 + chr4 252053 266528 FBtr0300800 0 + 56 1296 14475 + chr4 252055 266528 FBtr0300798 0 + 56 1296 14473 + chr4 252055 266528 FBtr0300799 0 + 56 1296 14473 + chr4 252541 266528 FBtr0300797 0 + 56 1296 13987 + ... + +**Third file (CCC)**:: + + chr4 972167 979017 FBtr0310651 0 - 9927 6738 6850 + chr4 972186 979017 FBtr0089229 0 - 9927 6738 6831 + chr4 972186 979017 FBtr0089231 0 - 9927 6738 6831 + chr4 972186 979017 FBtr0089233 0 - 9927 6738 6831 + chr4 995793 996435 FBtr0111046 0 + 5 304 642 + chr4 995793 997931 FBtr0111044 0 + 17 714 2138 + chr4 995793 997931 FBtr0111045 0 + 17 714 2138 + chr4 1034029 1047719 FBtr0089223 0 - 17646 13536 13690 + ... + + +**Joining** the files, using **key column 4**, **value columns 7,8,9** and a **header line**, will return:: + + key AAA__V7 AAA__V8 AAA__V9 BBB__V7 BBB__V8 BBB__V9 CCC__V7 CCC__V8 CCC__V9 + FBtr0089116 0 0 0 56 1296 15144 0 0 0 + FBtr0089223 5293 13394 13690 0 0 0 17646 13536 13690 + FBtr0089229 3944 6428 6831 0 0 0 9927 6738 6831 + FBtr0089231 3944 6428 6831 0 0 0 9927 6738 6831 + FBtr0089233 3944 6428 6831 0 0 0 9927 6738 6831 + FBtr0111044 28 683 2138 0 0 0 17 714 2138 + FBtr0111045 28 683 2138 0 0 0 17 714 2138 + FBtr0111046 7 166 642 0 0 0 5 304 642 + FBtr0300796 0 0 0 56 1296 14475 0 0 0 + ... + +.. class:: infomark + +Input files need not be sorted. + +@REFERENCES@ +]]> + </help> +</tool>