diff frogsfunc_functions.xml @ 9:7bf54edaba24 draft

planemo upload for repository https://github.com/geraldinepascal/FROGS-wrappers/ commit 3d595459e82ea1674c83543f41c18169c159450e-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/frogsfunc_functions.xml	Thu May 12 10:44:30 2022 +0000
@@ -0,0 +1,176 @@
+<?xml version="1.0"?>
+<!--
+# Copyright (C) 2022 INRAE
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+-->
+<tool id="FROGSFUNC_step3_functions" name="FROGSFUNC_step3_functions" version= "@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
+    <description>Predicting of functions weighted by the relative abundance of OTUs in the community. Inferring the metagenomes of the communities.</description>
+
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+
+    <expand macro="requirements_frogsfunc" />
+
+    <stdio>
+        <exit_code range="1:" />
+        <exit_code range=":-1" />
+    </stdio>
+    <command >
+       frogsfunc_functions.py
+            --input-biom $input_biom
+            --function $function
+            --marker $marker
+            --max-nsti $max_nsti
+            --function-abund $function_abund
+            --seqtab $seqtab
+            --weighted $weighted
+            --excluded $excluded
+            --html $summary_file
+    </command> 
+    <inputs>
+        <!-- Input files -->
+        <param argument="--input-biom" format="biom1" name="input_biom" type="data" label="Biom file" help="The abundance file i.e. FROGSFUNC_step1_placeseqs tool output file (frogsfunc_placeseqs.biom)." optional="false"/>
+        <param argument='--function' format="tabular" type="data" label="Function file" help="Copy number table of functions present in the predicted genome for each OTU i.e. FROGSFUNC_step2_copynumbers tool output file (frogsfunc_copynumbers_predicted_functions.tsv)." optional="false"/>
+        <param argument='--marker' format="tabular" type="data" label="Marker file" help="Table of predicted marker copy number i.e. FROGSFUNC_step2_copynumbers output (frogsfunc_copynumbers_marker.tsv)." optional="false"/>
+        
+        <!-- Parameters-->
+        <param argument="--max-nsti" name="max_nsti" type="float" label="NSTI cut-off" help="Any sequence with an NSTI above this threshold will be out. (default: 2)" value="2" min="0" optional="false" /> 
+    </inputs>
+    <outputs>
+        <data format="html" name="summary_file" label="${tool.name}: report.html" from_work_dir="report.html"/>
+        <data format="tabular" name="seqtab" label="${tool.name}: frogsfunc_functions_marker_norm.tsv" from_work_dir="frogsfunc_functions_marker_norm.tsv.tsv"/> 
+        <data format="tabular" name="weighted" label="${tool.name}: frogsfunc_functions_weighted_nsti.tsv" from_work_dir="frogsfunc_functions_weighted_nsti.tsv"/> 
+        <data format="tabular" name="excluded" label="${tool.name}: frogsfunc_functions_excluded.tsv" from_work_dir="frogsfunc_functions_excluded.tsv"/>
+        <data format="tabular" name="function_abund" label="${tool.name}:   frogsfunc_functions_unstrat.tsv" from_work_dir=" frogsfunc_functions_unstrat.tsv"/> 
+    </outputs>
+
+
+    <tests>
+        <test>
+            <param name="input_biom" value="references/25-frogsfunc_placeseqs.biom" />
+            <param name="function" value="references/26-frogsfunc_copynumbers_predicted_functions.tsv" />
+            <param name="marker" value="references/26-frogsfunc_copynumbers_marker.tsv"/>
+            <param name="max_nsti" value="2" />
+            <param name="min_reads" value="1" />
+            <param name="min_samples" value="1" />
+            <param name="strat" value="false" />
+
+            <output name="function_abund" file="references/27-frogsfunc_functions_unstrat.tsv" compare="diff" lines_diff="0" />
+            <output name="seqtab" file="references/27-frogsfunc_functions_marker_norm.tsv" compare="diff" lines_diff="0" />
+            <output name="weighted" file="references/27-frogsfunc_functions_weighted_nsti.tsv" compare="diff" lines_diff="0" />
+            <output name="summary_file" file="references/27-frogsfunc_functions_report.html" compare="diff" lines_diff="0" />
+            <output name="excluded" file="references/27-frogsfunc_functions_excluded.txt" compare="diff" lines_diff="0" />
+        </test>
+    </tests>
+
+     <help>
+
+@HELP_LOGO@
+
+.. class:: infomark page-header h2
+
+What it does
+
+Predicting of functions weighted by the relative abundance of OTUs in the community. Inferring the metagenomes of the communities with `PICRUSt2 &lt;https://github.com/picrust/picrust2&gt;`_.
+There are two steps performed at this stage:
+
+    (i) The read depth per OTU is divided by the predicted marker (16S/ITS/18S) copy numbers. This is performed to help control for variation in marker copy numbers across organisms, which can result in interpretation issues.
+        For instance, imagine an organism with five identical copies of the 16S gene that is at the same absolute abundance as an organism with one 16S gene. The OTU corresponding to the first organism would erroneously be inferred to be at higher relative abundance simply because this organism had more copies of the 16S gene.
+         
+    (ii) The OTU read depths per sample (after normalizing by marker (16S/ITS/18S) copy number) are multiplied by the predicted function copy numbers per OTU.         
+
+
+.. class:: infomark page-header h2
+
+Inputs/Outputs
+
+
+.. class:: h3
+
+Inputs
+
+
+**Biom file**:
+
+ The OTUs biom file from FROGSFUNC_step1_placeseqs tool (format `biom1 &lt;http://biom-format.org/documentation/format_versions/biom-1.0.html&gt;`_). (frogsfunc_placeseqs.biom)
+
+**Function file**:
+
+ The table of predicted function abundance from FROGSFUNC_step2_copynumbers tool. (frogsfunc_copynumbers_predicted_functions.tsv)
+
+**Marker file**:
+
+ Output table of predicted marker gene copy numbers per sequence from FROGSFUNC_step2_copynumbers tool. (frogsfunc_copynumbers_marker.tsv)
+
+**NSTI cut-off**:
+
+ Nearest Sequenced Taxon Index (`NSTI &lt;https://www.nature.com/articles/nbt.2676&gt;`_) is the phylogenetic distance between the OTU and the nearest sequenced reference genome. This metric can be used to identify OTUs that are highly distant from all reference sequences (the predictions for these sequences are less reliable!). The higher the NSTI score, the less the affiliations are relevant. Any OTUs with a NSTI value higher than 2 are typically either from uncharacterized phyla or off-target sequences. 
+         
+
+.. class:: h3
+
+Outputs
+
+**Report file**: (report.html)
+
+.. image:: FROGS_frogsfunc_functions_piechart.png
+    :height: 500
+    :width: 1352
+
+OTUs are out if the NSTI associated is above the threshold.
+
+.. image:: FROGS_frogsfunc_functions_table.png
+    :height: 580
+    :width: 1352
+ 
+
+.. image:: FROGS_frogsfunc_functions_sunburst.png
+
+
+Gene families/function from KEGG or Metacyc databases are classified according to 3 hierarchy levels. The graph shows the proportion of each level within the selected samples.
+
+**Function abundance file**:
+ 
+ It is the function abundance predictions of metagenome, per sample. (frogsfunc_functions_unstrat.tsv)
+ 
+ - Classification column: the hierarchy classification of the gene function. 
+ - db_link column: the url on the link accession ID (*observation_name*) of the function. 
+ - observation_name: Accession identifier 
+ - last columns: Abundances of these functions in each samples.
+
+**Excluded sequences**:
+
+ Information (FROGS taxonomy, PICRUSt2 taxonomy, NSTI) about removed sequences that have a NSTI value aboved the NSTI threshold chosen in this step.
+
+**Normalized OTU abundance table**:
+
+ Table with normalized abundance per marker copy number. (frogsfunc_functions_marker_norm.tsv)
+
+**Weighted NSTI file**:
+
+ It is the table with average NSTI calculated per sample. (frogsfunc_functions_weighted_nsti.tsv)
+
+
+
+
+@HELP_CONTACT@
+
+    </help>
+
+
+    <expand macro="citations" />
+    
+</tool>