view metagene_annotator.xml @ 0:f225878bab7a draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/metagene_annotator commit 6d8b6e0fa2f1b47b337dbf21f5bc320586ccbd4c

<tool id="metagene_annotator" name="MetaGeneAnnotator" version="1.0.0">
    <description>gene-finding program for prokaryote and phage (used by sixgill)</description>
    <requirements>
        <requirement type="package">metagene_annotator</requirement>
        <requirement type="package">python</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #set $output_list = str($output_formats).split(',')
        touch mga_output
        #for $input in $inputs:
            && mga ${input} $multiple_species >> mga_output
        #end for
        #if 'tsv' in $output_list or 'bed' in $output_list:
            && python '$__tool_directory__/convert_mga.py' mga_output -v 
            #if 'tsv' in $output_list
                --tsv '$mga_tsv'
            #end if
            #if 'bed' in $output_list
                --bed '$mga_bed'
            #end if
        #end if
    ]]></command>
    <inputs>
        <param name="inputs" type="data" format="fasta" multiple="true" label="prokaryote DNA sequences"/>
        <param name="multiple_species" type="boolean" truevalue="-m" falsevalue="-s" checked="true" 
               label="MetaGenomic - Sequences are from multiple organisms" />
        <param name="output_formats" type="select" multiple="true" display="checkboxes" label="output formats">
            <option value="txt" selected="true">MetaGeneAnnotator text report</option>
            <option value="tsv">MetaGeneAnnotator tabular report with sequence columns</option>
            <option value="bed">MetaGeneAnnotator in BED format</option>
        </param>
    </inputs>
    <outputs>
        <data name="mga_txt" format="txt" from_work_dir="mga_output" label="${tool.name} on ${on_string} metagenefile">
            <filter>'txt' in output_formats</filter>
        </data>
        <data name="mga_tsv" format="tabular" label="${tool.name} on ${on_string} mga table">
            <filter>'tsv' in output_formats</filter>
            <actions>
                <action name="column_names" type="metadata" 
                 default="seq_ID,seq_model,seq_gc,seq_rbs,gene ID,start pos,end pos,strand,frame,complete/partial,gene score,used model,rbs start,rbs end,rbs score"/>
            </actions>
        </data>
        <data name="mga_bed" format="bed" label="${tool.name} on ${on_string} mga bed">
            <filter>'bed' in output_formats</filter>
            <actions>
                <action name="column_names" type="metadata" 
                 default="chrom,chromStart,chromEnd,name,score,strand,thickStart,thickEnd,itemRgb,blockCount,blockSizes,blockStarts"/>
            </actions>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="inputs" value="metasequences.fasta" ftype="fasta"/>
            <param name="multiple_species" value="True"/>
            <param name="output_formats" value="txt"/>
            <output name="mga_txt"> 
                <assert_contents>
                    <has_text_matching expression="# 1/1\s# gc = 0.275862, rbs = -1\s# self: -" />
                    <has_text_matching expression="gene_1\t1812\t1994\t-\t0\t11\t14.10\d+\tb\t2002\t2007\t2.11\d+" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="inputs" value="metasequences.fasta" ftype="fasta"/>
            <param name="multiple_species" value="False"/>
            <param name="output_formats" value="txt"/>
            <output name="mga_txt"> 
                <assert_contents>
                    <has_text_matching expression="# 1/1\s# gc = 0.275862, rbs = 0.428571\s# self: b" />
                    <has_text_matching expression="gene_1\t1812\t1994\t-\t0\t11\t12.48\d+\tb\t2002\t2007\t0.49\d+" />
                </assert_contents>
            </output>
        </test>
        <!-- Try these later
        <test>
            <param name="inputs" value="metasequences1.fasta,metasequences2.fasta" ftype="fasta"/>
            <param name="multiple_species" value="True"/>
            <param name="output_formats" value="txt"/>
            <output name="mga_txt"> 
                <assert_contents>
                    <has_text_matching expression="# 1/1.*# 10/1" />
                    <has_text_matching expression="gene_1\t1812\t1994\t-\t0\t11\t14.10\d+\tb\t2002\t2007\t2.11\d+" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="inputs" value="metasequences.fasta" ftype="fasta"/>
            <param name="multiple_species" value="True"/>
            <param name="output_formats" value="txt,tsv,bed"/>
            <output name="mga_txt"> 
                <assert_contents>
                    <has_text_matching expression="# 1/1\s# gc = 0.275862, rbs = -1\s# self: -" />
                    <has_text_matching expression="gene_1\t1812\t1994\t-\t0\t11\t14.10\d+\tb\t2002\t2007\t2.11\d+" />
                </assert_contents>
            </output>
            <output name="mga_tsv"> 
                <assert_contents>
                    <has_text_matching expression="#seq_id\tseq_model\tseq_gc\tseq_rbs" />
                    <has_text_matching expression="1/1\t-\t0.27\d+\t-1\tgene_1\t1812\t1994\t-\t0\t11\t14.1035\tb\t2002\t2007\t2.11\d+" />
                </assert_contents>
            </output>
            <output name="mga_bed"> 
                <assert_contents>
                    <has_text_matching expression="1/1\t1811\t1994\t1/1:gene_1\t15\t-\t1811\t1994\t0\t1\t183\t0" />
                </assert_contents>
            </output>
        </test>
        -->
    </tests>
    <help><![CDATA[
**MetaGeneAnnotator (mga)**

A gene-finding program for prokaryote and phage.

The gene annotations can be used by sixgill_ when generating metapeptides from metagenomics shotgun sequencing.

.. image:: Sixgill_MetaGeneAnnotator_Workflow.png
  :height: 213
  :width: 625

usage:
    mga [multi-fasta] <-m/-s>

         -m    (multiple species sequences are individually treated)
         -s    (single species sequences are treated as a unit)

**Input:**
    *A fasta file of metagenomic sequences*


**Outputs:**

    *MetaGeneAnnotator text report*
        Output from the MetaGeneAnnotator mga application::

            # 1/1
            # gc = 0.275862, rbs = -1
            # self: -
            gene_1	1812	1994	-	0	11	14.1035	b	2002	2007	2.11797
            # 2/1
            # gc = 0.338877, rbs = -1
            # self: -
            gene_1	1	414	+	0	01	25.748	b	.	.	.
            gene_2	614	790	+	0	11	0.774142	b	.	.	.
            gene_3	822	1079	+	0	11	20.6507	b	.	.	.

        output format description::

            # [sequence name]
            # gc = [gc%], rbs = [rbs%]
            # self: [(b)acteria/(a)rchaea/(p)hage/unused(-)]
            [gene ID] [start pos.] [end pos.] [strand] [frame] [complete/partial] [gene score] [used model] [rbs start] [rbs end] [rbs score]

            explanations of output column:
                *The value of [frame] (0/1/2) indicates the number of surplus (untranslated) nucleotides at the 5'-end of the predicted ORF.
                *The value of [score] indicates the estimated score of predicted gene. All predicted genes are more than 0.
                *The value of [complete/partial] indicates that the predicted gene structure is whether complete (contains both of start and stop codons[11]) or partial (lacks start[01] or stop[10] or both of them[00]).
                *The value of [model] indicates a selected model ((s)elf/(b)acteria/(a)rchaea/(p)hage) for predicting the gene. 


    *MetaGeneAnnotator tabular report with sequence columns*
        The mga output reformated as a tabular file::

            #seq_id	seq_model	seq_gc	seq_rbs	gene ID	start pos	end pos	strand	frame	complete/partial	gene score	used model	rbs start	rbs end	rbs score
            1/1	 -	0.275862	-1	gene_1	1812	1994	-	0	11	14.1035	b	2002	2007	2.11797
            2/1	 -	0.338877	-1	gene_1	1	414	+	0	01	25.748	b	.	.	.
            2/1	 -	0.338877	-1	gene_2	614	790	+	0	11	0.774142	b	.	.	.
            2/1	 -	0.338877	-1	gene_3	822	1079	+	0	11	20.6507	b	.	.	.


    *MetaGeneAnnotator in BED format*
        The mga output reformatted as a BED file which can be used to extract the DNA sequences for each gene from the fasta file::

            1/1	1811	1994	1/1:gene_1	15	-	1811	1994	0	1	183	0
            2/1	0	414	2/1:gene_1	26	+	0	414	0	1	414	0
            2/1	613	790	2/1:gene_2	1	+	613	790	0	1	177	0
            2/1	821	1079	2/1:gene_3	21	+	821	1079	0	1	258	0


.. _sixgill: https://github.com/dhmay/sixgill
    ]]></help>
    <citations>
        <citation type="doi">10.1093/dnares/dsn027</citation>
    </citations>
</tool>