tranfer group_humann2 tool

tools/group_humann2_uniref_abundances_to_GO/.shed.yml

@@ -0,0 +1,7 @@
+categories: 
+  - Metagenomics
+description: "Group abundances of UniRef50 gene families obtained with HUMAnN2 to Gene Ontology (GO) slim terms with relative abundances"
+name: group_humann2_uniref_abundances_to_go
+owner: bebatut
+homepage_url: https://github.com/bgruening/galaxytools/tree/master/tools/group_humann2_uniref_abundances_to_GO
+remote_repository_url: https://github.com/bgruening/galaxytools/tree/master/tools/group_humann2_uniref_abundances_to_GO

tools/group_humann2_uniref_abundances_to_GO/group_humann2_uniref_abundances_to_go.xml

@@ -0,0 +1,97 @@
+<tool id="group_humann2_uniref_abundances_to_go" name="Group abundances" version="1.2.3">
+    <description> of UniRef50 gene families obtained (HUMAnN2 output) to Gene Ontology (GO) slim terms</description>
+
+    <requirements>
+        <requirement type="package" version="1.9">numpy</requirement>
+        <requirement type="package" version="0.6.4">goatools</requirement>
+        <requirement type="package" version="0.11.2">humann2</requirement>
+        <requirement type="package" version="1.3.0">group_humann2_uniref_abundances_to_go</requirement>
+    </requirements>
+
+    <stdio>
+        <exit_code range="1:" />
+        <regex match="IOError"
+               source="both"
+               level="fatal"
+               description="Python file error" />
+        <regex match="pkg_resources"
+               source="both"
+               level="fatal"
+               description="PKG Error" />
+    </stdio>
+    <command><![CDATA[
+        group_humann2_uniref_abundances_to_GO.sh
+            -i '$humann2_gene_families_abundance'
+            -m '$molecular_function_abundance'
+            -b '$biological_process_abundance'
+            -c '$cellular_component_abundance'
+
+            #if $gene_ontology_file:
+                -a '$gene_ontology_file'
+            #end if
+
+            #if $slim_gene_ontology_file:
+                -s '$slim_gene_ontology_file'
+            #end if
+
+            #if $uniref50_go_file:
+                -u '$uniref50_go_file'
+            #end if
+
+            -g `which map_to_slim.py | xargs -n1 dirname`
+            -p `which humann2 | xargs -n1 dirname`
+    ]]></command>
+
+    <inputs>
+        <param name="humann2_gene_families_abundance" type="data" format="tabular,tsv,txt" label="HUMAnN2 output with UniRef50 gene family abundance" help="(-i)"/>
+
+        <param name="gene_ontology_file" optional="true" type="data" format="txt" label="Custom Gene Ontology (Optional)" help="By default, the used Gene Ontology is the core ontology downloaded on the Gene Ontology website"/>
+
+        <param name="slim_gene_ontology_file" optional="true" type="data" format="txt" label="Custom Slim Gene Ontology (Optional)" help="By default, the used slim Gene Ontology is the metagenomics slim developed by Jane Lomax and the InterPro group"/>
+
+        <param name="uniref50_go_file" optional="true" type="data" format="txt" label="Custom correspondance between UniRef50 and GO (Optional)" help="By default, the used correspondance is the one proposed in HUMAnN2"/>
+    </inputs>
+
+    <outputs>
+        <data format="tabular" name="molecular_function_abundance" label="${tool.name} on ${on_string}: Molecular function abundance"/>
+        <data format="tabular" name="biological_process_abundance" label="${tool.name} on ${on_string}: Biological process abundance"/>
+        <data format="tabular" name="cellular_component_abundance" label="${tool.name} on ${on_string}: Cellular component abundance"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="humann2_gene_families_abundance" value="humann2_gene_families.csv"/>
+            <param name="slim_gene_ontology_file" value="goslim_metagenomics_02_22_2016.obo" />
+            <param name="uniref50_go_file" value="map_infogo1000_uniref50_02_22_2016_trimmed.txt"/>
+            <output name="cellular_component_abundance" file="expected_cellular_component_abundance.txt"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+**What it does**
+
+HUMAnN2 is a pipeline to profile the presence/absence and abundance of microbial pathways in community of microbiota sequencing data. One output is a file with UniRef50 gene family abundances. HUMAnN2 proposes a script to regroup Uniref50 to GO, but used GO terms are too precise to get a broad overview of the ontology content.
+
+The tool described here contains scripts to group UniRef50 abundances obtained using main HUMAnN2 script (Gene families) to GO slim terms. GO slim is a subset of the terms in the whole GO. For this tool, metagenomics GO slim terms developed by Jane Lomax and the InterPro group.
+
+More information on `dedicated GitHub repository <https://github.com/ASaiM/group_humann2_uniref_abundances_to_GO>`_.
+
+**Inputs**
+
+This tool takes as input a file with UniRef50 gene family abundances generated with HUMAnN2.
+
+Several optional inputs can also be given: a custom Gene Ontology file with the core ontology, a custom slim Gene Ontology with description of slim GO terms to use and a custom mapping file which map UniRef50 gene families to GO terms.
+
+**Outputs**
+
+3 outputs are generated: abundances of GO slim terms grouped in 3 groups (molecular functions, biological processes and cellular components). 
+
+Each file is a tabular file with 3 columns: GO slim term id, name and abundance.
+    ]]></help>
+
+    <citations>
+        <citation type="doi">10.5281/zenodo.50086</citation>
+        <citation type="doi">10.5281/zenodo.31628</citation>
+        <citation type="doi">10.1371/journal.pcbi.1002358</citation>
+    </citations>
+</tool>

tools/group_humann2_uniref_abundances_to_GO/test-data/expected_cellular_component_abundance.txt

@@ -0,0 +1,2 @@
+GO id	GO name	Abundance
+GO:0005739	mitochondrion	68.84