comparison dbbuilder.xml @ 9:0f641df3f28a draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/dbbuilder commit b3726245d52acb0d0efcb46ef978d75e2b0f2453

8:3f6354b7eb94

<tool id="dbbuilder" name="Protein Database Downloader" version="0.3.3">
    <description></description>
    <requirements>
        <requirement type="package" version="1.20.1">wget</requirement>
        <requirement type="package" version="3.8">python</requirement>
        <requirement type="package" version="2.20.1">requests</requirement>

        <!-- http://maxquant.org/contaminants.zip -->
        <!-- ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.protein.faa.gz-->
    <command>
<![CDATA[
        #if $source.from == "uniprot"
            #if $source.set:
                #set $modified_set = '&' + str($source.set) 
            #else
                #set $modified_set = ''
            #end if
            #if $source.taxon_id
                #set $taxon_id = $source.taxon_id
            #else
                #set $taxon_id = $source.taxon
            #end if
            #set $url = 'https://rest.uniprot.org/uniprotkb/stream?compressed=true&format=fasta&query=taxonomy_id:"' + str($taxon_id) + '"' + str($modified_set) + str($source.reviewed) + str($source.include_isoform)
            #set $type = "uniprotkb_stream"
        #elif $source.from == "cRAP"
            ##set $url = "ftp://ftp.thegpm.org/fasta/cRAP/crap.fasta"
            #set $url = "https://raw.githubusercontent.com/pravs3683/cRAP/master/cRAP_protein_database.fasta"
            #set $type = "direct"

                    </options>
                </param>
                <param name="taxon_id" type="integer" value="" min="1" optional="true" help="Specify a NCBI taxon id to override species selection"/>
                <param name="reviewed" type="select" help="UniProtKB/TrEMBL (unreviewed)is a large, automatically annotated database- may contain redundant sequences, but there is a higher chance peptides will be identified. UniProtKB/Swiss-Prot (reviewed) is a smaller, manually annotated database- less of a chance peptides will be identified but less sequence redundancy">
                    <option value="">UniProtKB</option>
                    <option value="+reviewed%3Atrue">UniProtKB/Swiss-Prot (reviewed only)</option>
                    <option value="+reviewed%3Afalse">UniProtKB/TrEMBL (unreviewed only)</option>
                    <sanitizer>
                        <valid>
                            <add value="%"/>
                        </valid>
                    </sanitizer>
                </param>
                <param name="set" type="select" label="Proteome Set">
                    <option value="">Any</option>
                    <option value="keyword%3aKW-1185" selected="true">Reference Proteome Set</option>
                    <sanitizer>
                        <valid>
                            <add value="%"/>
                        </valid>
                    </sanitizer>
                </param>
                <param name="include_isoform" type="boolean" truevalue="&amp;includeIsoform=true" falsevalue="" 
                    label="Include isoform data" help="several different forms of a given protein are incorporated into database" />
            </when>
            <when value="cRAP" />
            <when value="HMP">
                <param name="site" type="select" label="Proteome for body site">

                <assert_contents>
                    <has_text text="SPIKE_SARS2" />
                </assert_contents>
            </output>
        </test>
        <test>
            <conditional name="source">
                <param name="from" value="uniprot" />
                <param name="taxon_id" value="2697049"/>
                <param name="reviewed" value="+reviewed%3Atrue"/>
                <param name="set" value=""/>
            </conditional>
            <output name="output_database">
                <assert_contents>
                    <has_text text=">sp|P0DTC1|R1A_SARS2" />
                    <not_has_text text=">tr|A0A679G4D8|A0A679G4D8_SARS2" />
                </assert_contents>
            </output>
        </test>
        <test>
            <conditional name="source">
                <param name="from" value="uniprot" />
                <param name="taxon_id" value="2697049"/>
                <param name="reviewed" value="+reviewed%3Afalse"/>
                <param name="set" value=""/>
            </conditional>
            <output name="output_database">
                <assert_contents>
                    <has_text text=">tr|A0A679G4D8|A0A679G4D8_SARS2" />
                    <not_has_text text=">sp|P0DTC1|R1A_SARS2" />
                </assert_contents>
            </output>
        </test>

        <test>

9:0f641df3f28a

<tool id="dbbuilder" name="Protein Database Downloader" version="0.3.4">
    <description></description>
    <requirements>
        <requirement type="package" version="1.20.1">wget</requirement>
        <requirement type="package" version="3.8">python</requirement>
        <requirement type="package" version="2.20.1">requests</requirement>

        <!-- http://maxquant.org/contaminants.zip -->
        <!-- ftp://ftp.ncbi.nih.gov/refseq/H_sapiens/mRNA_Prot/human.protein.faa.gz-->
    <command>
<![CDATA[
        #if $source.from == "uniprot"
            #set $query_fields = [] 
            #if $source.taxon_id
                #silent $query_fields.append('taxonomy_id:' + str($source.taxon_id))
            #else
                #silent $query_fields.append('taxonomy_id:' + str($source.taxon))
            #end if
            #if $source.reviewed:
                #silent $query_fields.append(str($source.reviewed))
            #end if
            #if $source.set:
                #silent $query_fields.append(str($source.set))
            #end if
            #set $query  = '(' + ')+AND+('.join($query_fields) + ')' 
            #set $url = 'https://rest.uniprot.org/uniprotkb/stream?compressed=true&format=fasta' + str($source.include_isoform) + '&query=' + $query
            #set $type = "uniprotkb_stream"
        #elif $source.from == "cRAP"
            ##set $url = "ftp://ftp.thegpm.org/fasta/cRAP/crap.fasta"
            #set $url = "https://raw.githubusercontent.com/pravs3683/cRAP/master/cRAP_protein_database.fasta"
            #set $type = "direct"

                    </options>
                </param>
                <param name="taxon_id" type="integer" value="" min="1" optional="true" help="Specify a NCBI taxon id to override species selection"/>
                <param name="reviewed" type="select" help="UniProtKB/TrEMBL (unreviewed)is a large, automatically annotated database- may contain redundant sequences, but there is a higher chance peptides will be identified. UniProtKB/Swiss-Prot (reviewed) is a smaller, manually annotated database- less of a chance peptides will be identified but less sequence redundancy">
                    <option value="">UniProtKB</option>
                    <option value="reviewed:true">UniProtKB/Swiss-Prot (reviewed only)</option>
                    <option value="reviewed:false">UniProtKB/TrEMBL (unreviewed only)</option>
                    <sanitizer>
                        <valid>
                            <add value=":"/>
                        </valid>
                    </sanitizer>
                </param>
                <param name="set" type="select" label="Proteome Set">
                    <option value="">Any</option>
                    <option value="keyword:KW-1185" selected="true">Reference Proteome Set</option>
                    <sanitizer>
                        <valid>
                            <add value=":"/>
                        </valid>
                    </sanitizer>
                </param>
                <param name="include_isoform" type="boolean" truevalue="&amp;includeIsoform=true" falsevalue=""
                    label="Include isoform data" help="several different forms of a given protein are incorporated into database" />
            </when>
            <when value="cRAP" />
            <when value="HMP">
                <param name="site" type="select" label="Proteome for body site">

                <assert_contents>
                    <has_text text="SPIKE_SARS2" />
                </assert_contents>
            </output>
        </test>

        <test>
            <conditional name="source">
                <param name="from" value="uniprot" />
                <param name="taxon_id" value="2697049"/>
                <param name="reviewed" value="reviewed:true"/>
                <param name="set" value=""/>
            </conditional>
            <output name="output_database">
                <assert_contents>
                    <has_text text=">sp|P0DTC1|R1A_SARS2" />
                    <not_has_text text=">tr|A0A679G4D8|A0A679G4D8_SARS2" />
                </assert_contents>
            </output>
        </test>

        <test>
            <conditional name="source">
                <param name="from" value="uniprot" />
                <param name="taxon_id" value="2697049"/>
                <param name="reviewed" value="reviewed:false"/>
                <param name="set" value=""/>
            </conditional>
            <output name="output_database">
                <assert_contents>
                    <has_text text=">tr|A0A679G4D8|A0A679G4D8_SARS2" />
                    <not_has_text text=">sp|P0DTC1|R1A_SARS2" />
                </assert_contents>
            </output>
        </test>

        <test>
            <conditional name="source">
                <param name="from" value="uniprot" />
                <param name="taxon" value="83333"/>
                <param name="reviewed" value="reviewed:true"/>
                <param name="set" value=""/>
                <param name="include_isoform" value="True"/>
            </conditional>
            <output name="output_database">
                <assert_contents>
                    <has_text text="sp|P06615|REDF_ECOLI" />
                    <has_text text=">sp|P06710-2|DPO3X_ECOLI" />
                </assert_contents>
            </output>
        </test>
        <test>
            <conditional name="source">
                <param name="from" value="uniprot" />
                <param name="taxon" value="83333"/>
                <param name="reviewed" value="reviewed:true"/>
                <param name="set" value=""/>
                <param name="include_isoform" value="False"/>
            </conditional>
            <output name="output_database">
                <assert_contents>
                    <has_text text="sp|P06615|REDF_ECOLI" />
                    <has_text text="REDF_ECOLI" />
                    <not_has_text text=">sp|P06710-2|DPO3X_ECOLI" />
                </assert_contents>
            </output>
        </test>

        <test>