comparison ident_params.xml @ 1:fa76abf69433 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/peptideshaker commit e09348a0c372d4355c5dda6519e52ff17e0e8621-dirty

0:8b99cb00e1c4

        <import>macros_basic.xml</import>
    </macros>
    <requirements>
      	<requirement type="package" version="@SEARCHGUI_VERSION@">searchgui</requirement>
      	<requirement type="package" version="3.0">zip</requirement>
    </requirements>
    <expand macro="stdio" />
    <command>
<![CDATA[
        #set $temp_stderr = "searchgui_stderr"

        mkdir output;
        cwd=`pwd`;
        export HOME=\$cwd;

        echo "DB: ${input_database.display_name} sequences: ${input_database.metadata.sequences}";

        #####################################################
        ## generate IdentificationParameters for SearchGUI ##
        #####################################################
        (searchgui eu.isas.searchgui.cmd.IdentificationParametersCLI
            --exec_dir="\$cwd/${bin_dir}"
            -out "\$cwd/SEARCHGUI_IdentificationParameters.par"

          ## SPECTRUM MATCHING PARAMETERS

            -db "${input_database}"

            -frag_tol '${spectrum_matching_options.fragment_tol}'
            -frag_ppm '${spectrum_matching_options.fragment_tol_units}'
            -prec_tol '${spectrum_matching_options.precursor_ion_tol}'
            -prec_ppm '${spectrum_matching_options.precursor_ion_tol_units}'

            ## end if


            ## PTM LOCALIZATION

            -ptm_score "${advanced_options.ptm_localization_options.ptm_score.ptm_score_selector}"
            #if $advanced_options.ptm_localization_options.ptm_score.ptm_score_selector == 1
                -score_neutral_losses "${advanced_options.ptm_localization_options.ptm_score.neutral_losses}"
                #if str($advanced_options.ptm_localization_options.ptm_score.ptm_threshold) != ''
                    -ptm_threshold "${advanced_options.ptm_localization_options.ptm_score.ptm_threshold}"
                #end if
            #end if
            -ptm_alignment "${advanced_options.ptm_localization_options.ptm_alignment}"
            -ptm_sequence_matching_type "${advanced_options.ptm_localization_options.ptm_sequence_matching_type}"


            ## GENE ANNOTATION

            $advanced_options.gene_annotation_options.use_gene_mapping

            ## TODO: PROTEIN INFERENCE


            ## TODO: VALIDATION LEVELS

            -protein_fdr "${advanced_options.validation_levels_options.protein_fdr}"
            -peptide_fdr "${advanced_options.validation_levels_options.peptide_fdr}"
            -psm_fdr "${advanced_options.validation_levels_options.psm_fdr}"


            ## FRACTION ANALYSIS

            -protein_fraction_mw_confidence "${advanced_options.fraction_analysis_options.protein_fraction_mw_confidence}"


            ## -- SEARCH ENGINES SPECIFIC PARAMETERS --

            ## MSGF+ ADVANCED PARAMETERS

            #if $advanced_options.searchengines_advanced_options.msgf.msgf_advanced == "yes"
                -msgf_decoy ${advanced_options.searchengines_advanced_options.msgf.msgf_decoy}
                -msgf_min_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_min_pep_length}
                -msgf_max_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_max_pep_length}
                -msgf_termini ${advanced_options.searchengines_advanced_options.msgf.msgf_termini}
                -msgf_num_ptms ${advanced_options.searchengines_advanced_options.msgf.msgf_num_ptms}
                -msgf_instrument ${advanced_options.searchengines_advanced_options.msgf.msgf_instrument}
                -msgf_fragmentation ${advanced_options.searchengines_advanced_options.msgf.msgf_fragmentation}
                -msgf_protocol ${advanced_options.searchengines_advanced_options.msgf.msgf_protocol}
                -msgf_num_matches ${advanced_options.searchengines_advanced_options.msgf.msgf_num_matches}
                -msgf_additional ${advanced_options.searchengines_advanced_options.msgf.msgf_additional}
            #end if


            ## MSAMANDA ADVANCED PARAMETERS

                -novor_fragmentation ${advanced_options.searchengines_advanced_options.novor.novor_fragmentation}
                -novor_mass_analyzer ${advanced_options.searchengines_advanced_options.novor.novor_mass_analyzer}
            #end if

        2> $temp_stderr);

        exit_code_for_galaxy=\$?;
        cat $temp_stderr 2>&1;
        (exit \$exit_code_for_galaxy)
]]>

                        <option value="no" selected="True">Default</option>
                    </param>
                    <when value="no" />
                    <when value="yes">
                        <param name="msgf_decoy" type="boolean" truevalue="1" falsevalue="0" checked="false"
                            label="MSGF: Search Decoys" help="If yes then a decoy database will be generated and searched. Assumed input database contains no decoys"/>
                        <param name="msgf_min_pep_length" type="integer" value="6"
                            label="MSGF: Minimum Peptide Length" help="Minimum length for a peptide to be considered"/>
                        <param name="msgf_max_pep_length" type="integer" value="30"
                            label="MSGF: Maximum Peptide Length" help="Maximum length for a peptide to be considered"/>
                        <param name="msgf_termini" type="select" format="txt"
                            label="MSGF: Number of tolerable termini" help="Searches will take much longer if selecting a value other than 2">
                            <option value="0">0 (ie non-specific cleavage)</option>
                            <option value="1">1 (ie semi-tryptic cleavage)</option>
                            <option value="2" selected="true">2 (ie fully-tryptic cleavage)</option>
                        </param>
                        <param name="msgf_num_ptms" label="MSGF: Max PTMs per peptide" type="integer" value="2"/>

                        <param name="msgf_instrument" label="MSGF: Instrument type" type="select" help="Identifier of the instrument to generate MS/MS spectra (used to determine the scoring model)">
                            <option value="0" selected="True">Low-res LCQ/LTQ</option>
                            <option value="1" >High-res LTQ</option>
                            <option value="2" >TOF</option>
                            <option value="3" >Q-Exactive</option>
                        </param>
                        <param name="msgf_fragmentation" label="MSGF: Fragmentation type" type="select" help="Fragmentation method identifier (used to determine the scoring model)">
                            <option value="0" selected="True">As written in the spectrum or CID if no info</option>
                            <option value="1" >CID</option>
                            <option value="2" >ETD</option>
                            <option value="3" >HCD</option>
                        </param>
                        <param name="msgf_protocol" label="MSGF: Protocol type" type="select" help="Protocol identifier. Protocols are used to enable scoring parameters for enriched and/or labeled samples">
                            <option value="0" selected="True">Automatic</option>
                            <option value="1" >Phosphorylation</option>
                            <option value="2" >iTRAQ</option>
                            <option value="3" >iTRAQPhospho</option>
                            <option value="4" >TMT</option>
                            <option value="5" >Standard</option>
                        </param>
                        <param name="msgf_num_matches" label="MSGF: Maximum Number of Spectrum Matches" type="integer" value="1" help="Number of peptide matches per spectrum to report" />
                        <param name="msgf_additional" label="MS-GF+ additional features" type="select" help="Additional features to export">
                            <option value="0" selected="True">output basic scores only</option>
                            <option value="1" >output additional features</option>
                        </param>
                    </when>
                </conditional>

                  <!-- MS-AMANDA ADVANCED PARAMETERS  -->
                <conditional name="ms_amanda">

            </section>
        </section>

    </inputs>
    <outputs>
        <data name="Searchgui_Identification_Parameters" format="par" from_work_dir="SEARCHGUI_IdentificationParameters.par" label="${tool.name}: PAR file on ${on_string}" />
    </outputs>
    <tests>

        <!-- Test that default parameters generates a standar par file -->
        <test>
            <param name="input_database" value="searchgui_tinydb1_concatenated_target_decoy.fasta" ftype="fasta"/>
            <output name="Searchgui_Identification_Parameters" file="Identification_Parameters_default.par" ftype="par" compare="sim_size" delta="1000" />
        </test>
        <!-- Test specific parameters -->
        <test>
            <param name="input_database" value="searchgui_tinydb1_concatenated_target_decoy.fasta" ftype="fasta"/>
            <param name="precursor_ion_tol" value="100"/>

            <param name="variable_modifications" value="Oxidation of M"/>
            <param name="min_charge" value="1"/>
            <param name="max_charge" value="3"/>
            <param name="xtandem_advanced" value="yes"/>
            <param name="xtandem_refine_selector" value="yes"/>
            <output name="Searchgui_Identification_Parameters" file="Identification_Parameters_specific.par" ftype="par" compare="sim_size" delta="5000" />
        </test>

    </tests>
    <help>
**What it does**

Creates a parameters file which can be used independently by SearchGUI or PeptideShaker apps.

FASTA file used by this app must be kept in the history as the generated .par file will reference to it.

A FASTA file with decoy sequences is recommended if SearchGUI and PeptideShaker are going to be used.

    </help>
    <expand macro="citations" />
</tool>

1:fa76abf69433

        <import>macros_basic.xml</import>
    </macros>
    <requirements>
      	<requirement type="package" version="@SEARCHGUI_VERSION@">searchgui</requirement>
      	<requirement type="package" version="3.0">zip</requirement>
        <requirement type="package">JQ</requirement>
    </requirements>
    <expand macro="stdio" />
    <command>
<![CDATA[
        #set $temp_stderr = "searchgui_stderr"

        mkdir output;
        cwd=`pwd`;
        export HOME=\$cwd;

        echo 'DB: ${input_database.display_name} sequences: ${input_database.metadata.sequences}';

        ## copy the input FASTA file to the working folder
        cp '${input_database}' './input_database.fasta';


        #####################################################
        ## generate IdentificationParameters for SearchGUI ##
        #####################################################
        (searchgui eu.isas.searchgui.cmd.IdentificationParametersCLI
            --exec_dir="./bin/"
            -out './SEARCHGUI_IdentificationParameters_temp.par'

          ## SPECTRUM MATCHING PARAMETERS

            -db './input_database.fasta'

            -frag_tol '${spectrum_matching_options.fragment_tol}'
            -frag_ppm '${spectrum_matching_options.fragment_tol_units}'
            -prec_tol '${spectrum_matching_options.precursor_ion_tol}'
            -prec_ppm '${spectrum_matching_options.precursor_ion_tol_units}'

            ## end if


            ## PTM LOCALIZATION

            -ptm_score '${advanced_options.ptm_localization_options.ptm_score.ptm_score_selector}'
            #if $advanced_options.ptm_localization_options.ptm_score.ptm_score_selector == 1
                -score_neutral_losses '${advanced_options.ptm_localization_options.ptm_score.neutral_losses}'
                #if str($advanced_options.ptm_localization_options.ptm_score.ptm_threshold) != ''
                    -ptm_threshold '${advanced_options.ptm_localization_options.ptm_score.ptm_threshold}'
                #end if
            #end if
            -ptm_alignment '${advanced_options.ptm_localization_options.ptm_alignment}'
            -ptm_sequence_matching_type '${advanced_options.ptm_localization_options.ptm_sequence_matching_type}'


            ## GENE ANNOTATION

            $advanced_options.gene_annotation_options.use_gene_mapping

            ## TODO: PROTEIN INFERENCE


            ## TODO: VALIDATION LEVELS

            -protein_fdr '${advanced_options.validation_levels_options.protein_fdr}'
            -peptide_fdr '${advanced_options.validation_levels_options.peptide_fdr}'
            -psm_fdr '${advanced_options.validation_levels_options.psm_fdr}'


            ## FRACTION ANALYSIS

            -protein_fraction_mw_confidence '${advanced_options.fraction_analysis_options.protein_fraction_mw_confidence}'


            ## -- SEARCH ENGINES SPECIFIC PARAMETERS --

            ## MSGF+ ADVANCED PARAMETERS

            #if $advanced_options.searchengines_advanced_options.msgf.msgf_advanced == "yes"
                -msgf_decoy ${advanced_options.searchengines_advanced_options.msgf.msgf_decoy}
                -msgf_instrument ${advanced_options.searchengines_advanced_options.msgf.msgf_instrument}
                -msgf_fragmentation ${advanced_options.searchengines_advanced_options.msgf.msgf_fragmentation}
                -msgf_protocol ${advanced_options.searchengines_advanced_options.msgf.msgf_protocol}
                -msgf_termini ${advanced_options.searchengines_advanced_options.msgf.msgf_termini}
                -msgf_min_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_min_pep_length}
                -msgf_max_pep_length ${advanced_options.searchengines_advanced_options.msgf.msgf_max_pep_length}
                -msgf_num_ptms ${advanced_options.searchengines_advanced_options.msgf.msgf_num_ptms}
                -msgf_num_matches ${advanced_options.searchengines_advanced_options.msgf.msgf_num_matches}
                -msgf_additional ${advanced_options.searchengines_advanced_options.msgf.msgf_additional}
                #if $advanced_options.searchengines_advanced_options.msgf.msgf_tasks.msgf_tasks_custom == "yes"
                -msgf_num_tasks ${advanced_options.searchengines_advanced_options.msgf.msgf_tasks.msgf_num_tasks}
                #end if
            #end if


            ## MSAMANDA ADVANCED PARAMETERS

                -novor_fragmentation ${advanced_options.searchengines_advanced_options.novor.novor_fragmentation}
                -novor_mass_analyzer ${advanced_options.searchengines_advanced_options.novor.novor_mass_analyzer}
            #end if

        2> $temp_stderr);

        ## reading from the original .par file
        content_par_target_path=`cat ./SEARCHGUI_IdentificationParameters_temp.par`;
        ## modifying the .par file
        ## First we establish the new content for the path: .searchParameters.fastaFile.path
        new_content_par_target_path=`jq '.searchParameters.fastaFile.path = \$newVal' --arg newVal './input_database.fasta' <<< "\$content_par_target_path"`;
        ## Secondly, for .proteinInferencePreferences.proteinSequenceDatabase.path
        new_content_par_target_path=`jq '.proteinInferencePreferences.proteinSequenceDatabase.path = \$newVal' --arg newVal './input_database.fasta' <<< "\$new_content_par_target_path"`;

        ## we generate a new .par file filled with the new fasta path.
        echo 'Final identification parameters file: ';
        #set $new_par_target_path = './SEARCHGUI_IdentificationParameters.par';
        echo $new_par_target_path;
        echo "\$new_content_par_target_path" >> $new_par_target_path;

        ## compress both parameters and fasta file for the output
        (zip ./IdentificationParametersAndFasta.zip ./SEARCHGUI_IdentificationParameters.par 2>> $temp_stderr)

        &&

        (zip -u ./IdentificationParametersAndFasta.zip ./input_database.fasta 2>> $temp_stderr);

        exit_code_for_galaxy=\$?;
        cat $temp_stderr 2>&1;
        (exit \$exit_code_for_galaxy)
]]>

                        <option value="no" selected="True">Default</option>
                    </param>
                    <when value="no" />
                    <when value="yes">
                        <param name="msgf_decoy" type="boolean" truevalue="1" falsevalue="0" checked="false"
                            label="MSGF: Search Decoy Database" help="If yes then a decoy database will be generated and searched. Assumed input database contains no decoys"/>
                        <param name="msgf_instrument" label="MSGF: MS/MS Detector" type="select" help="Identifier of the instrument to generate MS/MS spectra (used to determine the scoring model)">
                            <option value="0" >Low-res LCQ/LTQ</option>
                            <option value="1" >Orbitrap/FTICR</option>
                            <option value="2" >TOF</option>
                            <option value="3" selected="True">Q-Exactive</option>
                        </param>
                        <param name="msgf_fragmentation" label="MSGF: Fragmentation method" type="select" help="Fragmentation method identifier (used to determine the scoring model)">
                            <option value="0" >As written in the spectrum or CID if no info</option>
                            <option value="1" >CID</option>
                            <option value="2" >ETD</option>
                            <option value="3" selected="True">HCD</option>
                            <option value="4" >UVPD</option>
                        </param>
                        <param name="msgf_protocol" label="MSGF: Protocol" type="select" help="Protocol identifier. Protocols are used to enable scoring parameters for enriched and/or labeled samples">
                            <option value="0" selected="True">Automatic</option>
                            <option value="1" >Phosphorylation</option>
                            <option value="2" >iTRAQ</option>
                            <option value="3" >iTRAQPhospho</option>
                            <option value="4" >TMT</option>
                            <option value="5" >Standard</option>
                        </param>
                        <param name="msgf_termini" type="select" format="txt"
                            label="MSGF: Enzymatic Terminals" help="Searches will take much longer if selecting a value other than 2">
                            <option value="0">None required</option>
                            <option value="1">At least one</option>
                            <option value="2" selected="true">Both</option>
                        </param>
                        <param name="msgf_min_pep_length" type="integer" value="8"
                            label="MSGF: Minimum Peptide Length" help="Minimum length for a peptide to be considered"/>
                        <param name="msgf_max_pep_length" type="integer" value="30"
                            label="MSGF: Maximum Peptide Length" help="Maximum length for a peptide to be considered"/>
                        <param name="msgf_num_ptms" label="MSGF: Max Variable PTMs per Peptide" type="integer" value="2"/>
                        <param name="msgf_num_matches" label="MSGF: Number of Spectrum Matches" type="integer" value="10" help="Number of peptide matches per spectrum to report" />
                        <param name="msgf_additional" label="MS-GF+ additional Output" type="select" help="Additional features to export">
                            <option value="0" selected="True">output basic scores only</option>
                            <option value="1" >output additional features</option>
                        </param>
                        <conditional name="msgf_tasks">
                            <param name="msgf_tasks_custom" type="select" label="Number of tasks to use on the threads">
                                <option value="yes">Custom</option>
                                <option value="no" selected="True">Default</option>
                            </param>
                            <when value="no" />
                            <when value="yes">
                                <param name="msgf_num_tasks" type="integer" value="4"
                                    label="MSGF: Custom number of tasks to use on the threads"
                                    help="Manually set the number of tasks to create for the search. More tasks than threads will reduce the memory requirements of the search, but will be slower (how much depends on the inputs). Check the documentation carefully. "/>
                            </when>
                        </conditional>
                    </when>
                </conditional>

                  <!-- MS-AMANDA ADVANCED PARAMETERS  -->
                <conditional name="ms_amanda">

            </section>
        </section>

    </inputs>
    <outputs>
      <!--  <data name="Searchgui_Identification_Parameters" format="par" from_work_dir="SEARCHGUI_IdentificationParameters.par" label="${tool.name}: PAR file on ${on_string}" /> -->
        <data name="Identification_Parameters_And_Fasta" format="zip" from_work_dir="IdentificationParametersAndFasta.zip" label="${tool.name}: Compressed PAR and FASTA files on ${on_string}" />
    </outputs>
    <tests>

        <!-- Test that default parameters generates a standar par file -->
        <test>
            <param name="input_database" value="searchgui_tinydb1_concatenated_target_decoy.fasta" ftype="fasta"/>
            <output name="Identification_Parameters_And_Fasta" file="IdentificationParametersAndFastaDefault.zip" ftype="zip" compare="sim_size" delta="1000" />
        </test>
        <!-- Test specific parameters -->
        <test>
            <param name="input_database" value="searchgui_tinydb1_concatenated_target_decoy.fasta" ftype="fasta"/>
            <param name="precursor_ion_tol" value="100"/>

            <param name="variable_modifications" value="Oxidation of M"/>
            <param name="min_charge" value="1"/>
            <param name="max_charge" value="3"/>
            <param name="xtandem_advanced" value="yes"/>
            <param name="xtandem_refine_selector" value="yes"/>
            <output name="Identification_Parameters_And_Fasta" file="IdentificationParametersAndFastaSpecific.zip" ftype="zip" compare="sim_size" delta="1000" />
        </test>

    </tests>
    <help>
**What it does**

Creates a zip file containing:

- A fasta file.
- A parameters file (.par) which can be used independently by SearchGUI or PeptideShaker apps. It makes reference to the previous fasta file.

A FASTA file with decoy sequences generated by FastaCLI is recommended if SearchGUI and PeptideShaker are going to use the output of this tool.

    </help>
    <expand macro="citations" />
</tool>