Mercurial > repos > proteore > proteore_filter_keywords_values
diff filter_kw_val.xml @ 0:a55e8b137c6b draft
planemo upload commit 688c456ca57914a63c20eba942ec5fe81e896099-dirty
author | proteore |
---|---|
date | Wed, 19 Sep 2018 05:01:15 -0400 |
parents | |
children | cb9555653b09 |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/filter_kw_val.xml Wed Sep 19 05:01:15 2018 -0400 @@ -0,0 +1,271 @@ +<tool id="MQoutputfilter" name="Filter by keywords or numerical value" version="2018.08.22"> + <description></description> + <requirements> + </requirements> + <stdio> + <exit_code range="1:" /> + </stdio> + <command><![CDATA[ + python $__tool_directory__/filter_kw_val.py + -i "$input1,$header" + -o "$output1" + --filtered_file "$filtered_file" + --operator "$operator" + + ## Keywords + #for $key in $keyword + #if $key.k.kw != "None" + #if $key.k.kw == "text" + --kw "$key.k.txt" "$key.ncol" "$key.match" + #else if $key.k.kw == "file" + --kw_file "$key.k.file" "$key.ncol" "$key.match" + #end if + #end if + #end for + + ## value to filter + #for $val in $value + #if $val.v.val != "None" + --value + #if $val.v.val == "Equal" + $val.v.equal "$val.ncol" "=" + #else if $val.v.val == "Higher" + $val.v.higher "$val.ncol" ">" + #else if $val.v.val == "Equal or higher" + $val.v.equal_higher "$val.ncol" ">=" + #else if $val.v.val == "Lower" + $val.v.lower "$val.ncol" "<" + #else if $val.v.val == "Equal or lower" + $val.v.equal_lower "$val.ncol" "<=" + #else + $val.v.different "$val.ncol" "!=" + #end if + #end if + #end for + + ##range of values to keep + #for $vr in $values_range + #if vr + --values_range $vr.bottom_value $vr.top_value $vr.ncol $vr.inclusive + #end if + #end for + + #if $sort_column != "" + --sort_col "$sort_column,$reversed_sort" + #end if + + ]]></command> + <inputs> + <param type="data" name="input1" format="txt,tabular" label="Input file" help="Input file is a tab-delimited file containing proteomics identification and/or quantitative results" /> + <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" /> + <param name="operator" type="select" label="Please select an operator for your filters" help="OR : only one filter must be satisfied to filter a row, AND : all your filters must be satisfied to filter a row" > + <option value="OR" selected="True">OR</option> + <option value="AND">AND</option> + </param> + <param name="sort_column" type="text" value="" label="If you want to sort the result files by values from a column, please enter a column number" help="For example : fill in 'c1' if you want to sort your result file by the column 1 values." /> + <param name="reversed_sort" type="boolean" checked="false" truevalue="true" falsevalue="false" label="Sort in descending order ?"/> + <repeat name="keyword" title="Filter by keywords" > + <param name="ncol" type="text" value="c1" label="Please specify the column number of the input file on which you want to apply the filter" help='For example, fill in "c1" if the keywords you want to filter out are listed in the first column' /> + <param type="boolean" name="match" truevalue="True" label="Would you like to search for exact match?" help='Choosing "Yes" will only filter out exact match (i.e. case sensitive), see below for more details' /> + <conditional name="k" > + <param argument="--kw" type="select" label="Filter by keyword" > + <option value="None" selected="True">---</option> + <option value="text">Enter keywords (copy/paste)</option> + <option value="file">Choose a file containing keywords</option> + </param> + <when value="None" /> + <when value="text" > + <param name="txt" type="text" label="Copy/paste keywords to be filtered out" help='Keywords should be separated by ";", for example: A8K2U0;Q5TA79;O43175' > + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="__sq__"/> + </mapping> + </sanitizer> + </param> + </when> + <when value="file" > + <param name="file" type="data" format="txt,tabular" label="Choose a file containing keywords" /> + </when> + </conditional> + </repeat> + <repeat name="value" title="Filter by value" > + <param name="ncol" type="text" value="c1" label="Please specify the column number of the input file on which you want to apply the filter" help='For example, fill in "c1" if the keywords you want to filter out are listed in the first column' /> + <conditional name="v" > + <param argument="--val" type="select" label="Filter by value" > + <option value="None">---</option> + <option value="Equal">=</option> + <option value="Higher">></option> + <option value="Equal or higher">>=</option> + <option value="Lower"><</option> + <option value="Equal or lower"><=</option> + <option value="Different">!=</option> + </param> + <when value="None" > + </when> + <when value="Equal" > + <param name="equal" type="float" value="" label="Value" /> + </when> + <when value="Higher" > + <param type="float" name="higher" value="" label="Value" /> + </when> + <when value="Equal or higher" > + <param type="float" name="equal_higher" value="" label="Value" /> + </when> + <when value="Lower" > + <param type="float" name="lower" value="" label="Value" /> + </when> + <when value="Equal or lower" > + <param type="float" name="equal_lower" value="" label="Value" /> + </when> + <when value="Different"> + <param type="float" name="different" value="" label="Value"/> + </when> + </conditional> + </repeat> + <repeat name="values_range" title="Filter by range of values"> + <param name="ncol" type="text" value="c1" label="Please specify the column number of the input file on which you want to apply the filter" help='For example, fill in "c1" if the keywords you want to filter out are listed in the first column' /> + <param name="bottom_value" type="float" value="" label="Please enter the bottom value" /> + <param name="top_value" type="float" value="" label="Please enter the top value" /> + <param name="inclusive" type="boolean" label="inclusive range ?" checked="false" truevalue="true" falsevalue="false" /> + </repeat> + </inputs> + <outputs> + <data name="output1" format="tabular" label="${tool.name} on ${input1.name}" /> + <data name="filtered_file" format="tabular" label="${tool.name} on ${input1.name} - Filtered lines" /> + </outputs> + <tests> + <test> + <param name="input1" value="Lacombe_et_al_2017_OK.txt" /> + <param name="header" value="true" /> + <param name="operator" value="OR"/> + <param name="sort_column" value="c1"/> + <param name="reversed_sort" value="false"/> + <repeat name="keyword"> + <param name="ncol" value="c1" /> + <param name="match" value="True" /> + <conditional name="k"> + <param name="kw" value="text" /> + <param name="txt" value="P04264;P35908;P13645;Q5D862;Q5T749;Q8IW75;P81605;P22531;P59666;P78386" /> + </conditional> + </repeat> + <repeat name="value"> + <param name="ncol" value="c3"/> + <conditional name="v"> + <param name="val" value="Higher"/> + <param name="higher" value="20" /> + </conditional> + </repeat> + <output name="output1" file="output.csv" /> + <output name="filtered_file" file="filtered_output.csv" /> + </test> + </tests> + <help><![CDATA[ +This tool allows to remove unneeded data (e.g. contaminants, non-significant values) from a proteomics results file (e.g. MaxQuant or Proline output). + +**Filter by keyword(s)** + +Several options can be used. For each option, you can fill in the field or upload a file which contains the keywords. + +- If you choose to fill in the field, the keywords should be separated by ";", for example: A8K2U0;Q5TA79;O43175 + +- If you choose to upload a file in a text format in which each line is a keyword, for example: + +REV + +TRYP_PIG + +ALDOA_RABBIT + +**The line that contains these keywords will be eliminated from input file.** + +**Keywords search can be applied by performing either exact match or partial one by using the following option** + +- If you choose **Yes**, only the fields that contains exactly the same content will be removed. + +- If you choose **No**, all the fields containing the keyword will be removed. + +For example: + +**Yes** option (exact match) selected using the keyword "kinase": only lines which contain exactly "kinase" is removed. + +**No** option (partial match) for "kinase": not only lines which contain "kinase" but also lines with "alpha-kinase" (and so on) are removed. + +----- + +**Filter by values** + +You can filter your data by a column of numerical values. +Enter the column to be use and select one operator in the list : + +- = +- != +- < +- <= +- > +- >= + +Then enter the value to filter and specify the column to apply that option. +If a row contains a value that correspond to your settings, it will be filtered. + +----- + +**Filter by a range of values** + +You can also set a range of values to filter your file. +In opposition to value filter, rows with values inside of the defined range are kept. + +Rows with values outside of the defined range will be filtered. + +----- + +**AND/OR operator** + +Since you can add as many filters as you want, you can choose how filters apply on your data. + +AND or OR operator option works on all filters : + +- OR : only one filter to be satisfied to remove one row +- AND : all filters must be satisfied to remove one row + +----- + +**Sort the results files** + +You can sort the result file if you wish, it can help you to check results. + +In order to do so : enter the column to be used, all columns will be sorted according to the one filled in. + +Rows stay intact, just in different order like excel. +You can also choose ascending or descending order, by default ascending order is set. + +----- + +**Output** + +The tool will produce 2 output files. + +* A text file containing the resulting filtered input file. + +* A text file containing the rows removed from the input file. + +----- + +.. class:: infomark + +**Authors** + +T.P. Lien Nguyen, David Christiany, Florence Combes, Yves Vandenbrouck - CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR + +Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux - INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR + +This work has been partially funded through the French National Agency for Research (ANR) IFB project. + +Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool. + + ]]></help> + <citations> + </citations> +</tool>