comparison MutCount.xml @ 5:0ba551449008 draft

planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 273a9af69b672b2580cd5dec4c0e67a4a96fb0fe

4:5766f80370e7

<?xml version="1.0"?>

<tool name="MutCount" id="mutcount" version="2.0">
    <description>
        This tool proceeds to count codons, amino acids on each species of a set of species, and then proceeds to permutation tests.
    </description>

    <macros>
        <import>macros.xml</import>
    </macros>

    <requirements>
        <expand macro="python_required" />
    </requirements>

    <command>
    <![CDATA[
    
        ln -s $__tool_directory__/scripts/functions.py . &&
        
        #if str($method.method_run) == "concat" :
            python '$__tool_directory__/scripts/S01a_mutcount_pairs.py' $method.num_sampled $method.num_iter $method.list_species
            &&
            python '$__tool_directory__/scripts/S02a_codon_counting.py' ${method.concat_nuc} 
        #end if
        
        #if str($method.method_run) == "separated" :
            #set $infiles = ""
            #for $input in $method.sep_file

                cp '$__tool_directory__/scripts/amino_acid_properties.csv' .
                &&
                python '$__tool_directory__/scripts/S01b_study_seq_composition_aa.py' '$infiles' ${method.concat_phy}
            #end if
        #end if
    ]]>
    </command>

    <inputs>
        <conditional name="method">

                <option value="separated">Set of separated genes (from ORF_Search output "output zip containing files with CDS without indel")</option>
            </param>

            <when value="concat">
                <param name="concat_nuc" type="data" format="fasta" label="Choose your fasta file in nucleic format" help="It must contain the concatenated file in NUCLEIC format from Phylogeny tool" />
                <param name="num_sampled" type="integer" value="100" min="0" label="Number of iterations"/>
                <param name="num_iter" type="integer" value="100" min="0" label="Number of sampled codons"/>
                <param name="list_species" type="text" size="100" label="List of species" help="List the species separated with a comma (for e.g Ap,As,Ct,Gt,Yu)" />
            </when>

            <when value="separated">
                <param name="format_run" type="select" label="Which format do you want to use for this tool (concatenation and RAxML run) ? ">
                    <option value="nucleic">Nucleic format</option>

        </conditional>
    </inputs>

    <outputs>
        <!-- output concat -->
        <!--
        <data format="txt" name="output1" label="counts.txt" from_work_dir="counts.txt" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="txt" name="output2" label="biases.txt" from_work_dir="biases.txt" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        -->
        <data format="csv" name="codons_counts" label="codons_counts.csv" from_work_dir="codons_counts.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aa_counts" label="aa_counts.csv" from_work_dir="aa_counts.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aatypes_counts" label="aatypes_counts.csv" from_work_dir="aatypes_counts.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="gc_counts" label="gc_counts.csv" from_work_dir="gc_counts.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aa_transitions" label="aa_transitions.csv" from_work_dir="aa_transitions.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aatypes_transitions" label="aatypes_transitions.csv" from_work_dir="aatypes_transitions.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>

        <!-- outputs separated - nucleic -->
        <data format="csv" name="nuc_comp" label="nuc_compositions.csv" from_work_dir="OUT/nuc_compositions.csv" >

            <filter>(method['method_run']=='separated' and method['format_run']== 'proteic')</filter>
        </data>
        
    </outputs>

    <tests>
        <test>
            <conditional name="method" >
                <param name="method_run" value="concat" />
                <param name="concat_nuc" ftype="fasta" value="test_07_output_phylogeny_concatenation.fasta" />
                <param name="num_sampled" value="100" />
                <param name="num_iter" value="100" />
                <param name="list_species" ftype="text" value="Ac,Am,Ap,Pu" />
            </conditional>            
            <output name="codons_counts" value="OUT_concat/codons_counts.csv" lines_diff="8"/>
            <output name="aa_counts" value="OUT_concat/aa_counts.csv" lines_diff="8"/>
            <output name="aatypes_counts" value="OUT_concat/aatypes_counts.csv" lines_diff="8"/>
            <output name="gc_counts" value="OUT_concat/gc_counts.csv"/>
            <output name="aa_transitions" value="OUT_concat/aa_transitions.csv" lines_diff="14"/>
            <output name="aatypes_transitions" value="OUT_concat/aatypes_transitions.csv" lines_diff="14"/>
        </test>

        <test>
            <conditional name="method" >
                <param name="method_run" value="separated" />

@HELP_AUTHORS@

<![CDATA[

**Last Version** : Victor Mataigne and Gildas Le Corguillé
--------

**Description**

This script counts the number of codons, amino acids, and types of amino acids in sequences, as well as the mutation bias from one item to another between 2 sequences. Counting is then compared to empirical p-values, obtained from bootstrapped sequences obtained from a subset of sequences.

**Parameters**

There are parameters only for the "Concatenated" method :

- The number of iterations : the number of alignments that will be generated (effect on the resolution of the gaussian distribution). Shouldn't be lower than 1000 to have a relatively smooth gaussian distribution.

- The number of sampled codons : the number of pairs of codons in each generated alignments (effect on the robustness on the countings performed on this alignement). Shouldn't be lower than 1000 to detect codons with relatively low occurence (<1%).

- The list of species, separated by commas and without space (e.g : sp1,sp2,sp3,sp4). You can run the tool on subgroup of species, not only on the total number of species present in the previous tools. You can also write 'all' to include every species.

--------

**Outputs**

---------

Changelog
---------

**Version 2.1 - 10/01/2017**

- Splitted output of concatenated method in several csv files.
- Bug corrected in output files of separated method.

**Version 2.0 - 12/07/2017**

5:0ba551449008

<?xml version="1.0"?>

<tool name="MutCount" id="mutcount" version="2.1">
    <description>
        This tool proceeds to count codons, amino acids on each species of a set of species, and then proceeds to permutation tests.
    </description>

    <macros>
        <import>macros.xml</import>
    </macros>

    <requirements>
        <expand macro="python_required" />
        <requirement type="package" version="0.20.0">pandas</requirement>
        <requirement type="package" version="1.12.0">numpy</requirement>
    </requirements>

    <command>
    <![CDATA[
    
        ln -s $__tool_directory__/scripts/functions.py . &&
        
        #if str($method.method_run) == "concat" :            
            python '$__tool_directory__/scripts/S01a_codons_counting.py' ${method.concat_nuc} '$method.list_species' '$method.list_species_boot' $method.num_iter $method.num_sampled > ${log}
        #end if
        
        #if str($method.method_run) == "separated" :
            #set $infiles = ""
            #for $input in $method.sep_file

                cp '$__tool_directory__/scripts/amino_acid_properties.csv' .
                &&
                python '$__tool_directory__/scripts/S01b_study_seq_composition_aa.py' '$infiles' ${method.concat_phy}
            #end if
        #end if
        
    ]]>
    </command>

    <inputs>
        <conditional name="method">

                <option value="separated">Set of separated genes (from ORF_Search output "output zip containing files with CDS without indel")</option>
            </param>

            <when value="concat">
                <param name="concat_nuc" type="data" format="fasta" label="Choose your fasta file in nucleic format" help="It must contain the concatenated file in NUCLEIC format from Phylogeny tool" />
                <param name="list_species" type="text" size="100" label="List of species for countings" help="List the species separated with a comma (for e.g Ap,As,Ct,Gt,Yu)" />
                <param name="list_species_boot" type="text" size="100" label="List of species used for resampling" help="List the species separated with a comma (for e.g Ap,As,Ct,Gt,Yu)" />
                <param name="num_iter" type="integer" value="1000" min="0" label="Number of sampled codons" help="Sets the length (in codons) of the resampled sequences"/>
                <param name="num_sampled" type="integer" value="1000" min="0" label="Number of iterations" help="Sets the number of resampled sequences"/>
            </when>

            <when value="separated">
                <param name="format_run" type="select" label="Which format do you want to use for this tool (concatenation and RAxML run) ? ">
                    <option value="nucleic">Nucleic format</option>

        </conditional>
    </inputs>

    <outputs>
        <!-- output concat -->
        <data format="txt" name="log" label="MutCount_concat_log.output" />
        <data format="csv" name="codons_freqs" label="codons_freqs.csv" from_work_dir="codons_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aa_freqs" label="aa_freqs.csv" from_work_dir="aa_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aatypes_freqs" label="aatypes_freqs.csv" from_work_dir="aatypes_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="gc_and_others_freqs" label="gc_and_others_freqs.csv" from_work_dir="gc_and_others_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="codons_transitions_freqs" label="codons_transitions_freqs" from_work_dir="codons_transitions_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aa_transitions_freqs" label="aa_transitions_freqs.csv" from_work_dir="aa_transitions_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>
        <data format="csv" name="aatypes_transitions_freqs" label="aatypes_transitions.csv" from_work_dir="aatypes_transitions_freqs.csv" >
            <filter>(method['method_run']=='concat')</filter>
        </data>

        <!-- outputs separated - nucleic -->
        <data format="csv" name="nuc_comp" label="nuc_compositions.csv" from_work_dir="OUT/nuc_compositions.csv" >

            <filter>(method['method_run']=='separated' and method['format_run']== 'proteic')</filter>
        </data>
        
    </outputs>

    <tests>        
        <test>
            <conditional name="method" >
                <param name="method_run" value="concat" />
                <param name="concat_nuc" ftype="fasta" value="concatenation.fasta" />
                <param name="list_species" ftype="text" value="Ps,Pp,Pu,Ac,Ap,Pf,Pg,Ph,Pi" />
                <param name="list_species_boot" ftype="text" value="Ps,Pp,Pu,Pf" />
                <param name="num_iter" value="200" />
                <param name="num_sampled" value="200" /> 
            </conditional>
            <output name="log" value="OUT_concat/MutCount_concat_log.output" lines_diff="2"/>
            <output name="codons_freqs" value="OUT_concat/codons_freqs.csv" lines_diff="18"/>
            <output name="aa_freqs" value="OUT_concat/aa_freqs.csv" lines_diff="18"/>
            <output name="aatypes_freqs" value="OUT_concat/aatypes_freqs.csv" lines_diff="18"/>
            <output name="gc_and_others_freqs" value="OUT_concat/gc_and_others_freqs.csv"/>            
            <output name="codons_transitions_freqs" value="OUT_concat/codons_transitions_freqs.csv" lines_diff="72"/>
            <output name="aa_transitions_freqs" value="OUT_concat/aa_transitions_freqs.csv" lines_diff="72"/>
            <output name="aatypes_transitions_freqs" value="OUT_concat/aatypes_transitions_freqs.csv" lines_diff="72"/>
        </test>

        <test>
            <conditional name="method" >
                <param name="method_run" value="separated" />

@HELP_AUTHORS@

<![CDATA[

**Last Version** : Victor Mataigne and Gildas Le Corguillé

--------

**Description**

This script counts the number of codons, amino acids, and types of amino acids in sequences, as well as the mutation bias from one item to another between 2 sequences. Counting is then compared to empirical p-values, obtained from bootstrapped sequences obtained from a subset of sequences.

**Parameters**

There are parameters only for the "Concatenated" method :

- The list of species for **countings**, separated by commas and without space (e.g : sp1,sp2,sp3,sp4). You can run the tool on subgroup of species, not only on the total number of species present in the previous tools.

- The list of species for **resampling**, separated by commas and without space (e.g : sp1,sp2,sp3,sp4). You can run the tool on subgroup of species, not only on the total number of species present in the previous tools. 

- The number of iterations : the number of alignments that will be generated (effect on the resolution of the gaussian distribution). Shouldn't be lower than 1000 to have a relatively smooth gaussian distribution.

- The number of sampled codons : the number of pairs of codons in each generated alignments (effect on the robustness on the countings performed on this alignement). Shouldn't be lower than 1000 to detect codons with relatively low occurence (<1%).

--------

**Outputs**

---------

Changelog
---------

**Version 2.1 - 26/02/2017**
- Fully re-written the concat method : fixed mistakes + cleaner code
- Splitted output of concatenated method in several csv files.
- Bug corrected in output files of separated method.

**Version 2.0 - 12/07/2017**