Mercurial > repos > george-weingart > graphlan_import

changeset 23:01ba9f83f9a7 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Renamed the function to import rather than export
author george-weingart
date Thu, 04 Sep 2014 16:43:30 -0400
parents b43531754e71
children 6d14a0188d69
files import2graphlan.xml
diffstat 1 files changed, 201 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/import2graphlan.xml	Thu Sep 04 16:43:30 2014 -0400
@@ -0,0 +1,201 @@
+<tool id="import2graphlan" name="import2graphlan" version="1.0.0">
+  <description>Export to Graphlan</description>
+  <command  interpreter="python">
+    export2graphlan.py 
+	-i $inp_data 
+	-o $out_data
+	-t $output_tree_file 
+	-a $output_annot_file 
+
+	--annotations $export_annotations 
+	--external_annotations $export_external_annotations
+	--background_levels  $background_levels 
+	#if $str($background_clades)  != " ":
+               	--background_clades  $background_clades
+	#end if
+	#if $str($background_colors)  != " ":
+               	--background_colors  $background_colors
+	#end if
+	#if $str($export_title)  != " ":
+               	--title $export_title
+	#end if
+	--title_font_size  $title_font_size 
+	--def_clade_size  $def_clade_size 
+	--min_clade_size  $min_clade_size 
+	--max_clade_size  $max_clade_size 
+	--def_font_size  $def_font_size 
+	--min_font_size  $min_font_size 
+	--max_font_size  $max_font_size 
+        --annotation_legend_font_size $annotation_legend_font_size
+	--abundance_threshold $abundance_threshold
+	--least_biomarkers $least_biomarkers
+
+	--skip_rows 1,2 
+   </command>
+   
+	<inputs>
+		<param format="tabular" name="inp_data" type="data" label="Input used to run Lefse" 	help="This is the file that was used as input for Lefse"/>
+		<param format="lefse_internal_res" name="out_data" type="data" label="Output of  Lefse"  help="This is the  Lefse output file"/>	
+	   	 <param name="export_annotations" type="text" format="text" label="Annotations" value="2,3"/>
+	   	 <param name="export_external_annotations" type="text" format="text" label="External Annotations" value="4,5,6"/>   
+		<param name="background_levels" type="text" format="text" label="Background Levels" value="1,2,3"/>   
+		<param name="background_clades" type="text" format="text" label="Background Clades" value=" " />  
+		<param name="background_colors" type="text" format="text" label="Background Colors" value=" " />  
+	    	<param name="export_title" type="text" format="text" label="Title" value=" "/>
+	    	<param name="title_font_size"  type="integer" size="4" value="15"   label="Title font size"/>
+	    	<param name="def_clade_size"  type="integer" size="4" value="0"   label="Default Clade size"/>
+	    	<param name="min_clade_size"  type="integer" size="4" value="20"   label="Minimum Clade size that are Biomarkers"/>
+	    	<param name="max_clade_size"  type="integer" size="4" value="200"   label="Maximum Clade size that are Biomarkers"/>
+	    	<param name="def_font_size"  type="integer" size="4" value="10"   label="Default font size"/>
+	    	<param name="min_font_size"  type="integer" size="4" value="8"   label="Minimum font size "/>
+	    	<param name="max_font_size"  type="integer" size="4" value="12"   label="Maximum font size "/>
+	    	<param name="annotation_legend_font_size"  type="integer" size="4" value="10"   label="Annotation legend font size "/>
+	    	<param name="abundance_threshold"  type="float"   value="20.0"   label="Abundance threshold: minimun abundace value for a clade to be annotated"/>
+	    	<param name="most_abundant"  type="integer" size="4" value="0"   label=" When only lefse_input is provided, you can specify how many clades to highlight "/>
+	    	<param name="least_biomarkers"  type="integer" size="4" value="0"   label="Minimum number of biomarkers to extract  "/>
+
+    </inputs>
+	<outputs>
+            <data  name="output_annot_file"  format="circl"  />
+            <data  name="output_tree_file"  format="circl"  />
+	</outputs>
+                                  
+  <help>
+Overview
+========
+**export2graphlan** is an *OPTIONAL* tool that automatically convert **LEfSe**, **MetaPhlAn2**, and **HUMAnN** input and/or output files, to **GraPhlAn**. Input file can be also given in BIOM (both 1 and 2) format.
+
+The aim of this tool is to support biologists, helping them by provide the tree and the annotation file for GraPhlAn, automatically.
+
+Input files
+-----------
+
+As shown in the image below, export2graphlan can work with just one of the following files or with both of them.
+
+ * **Result of MetaPhlAn or HUMAnN analysis**: As depicted in the image below, this file can be the result of a MetaPhlAn analysis or a HUMAnN analysis. Generally, it is a tab separated file that have for each row a taxonomy and an abundance value.
+
+ * **Output of LEfSe**: This file is the result of LEfSe execute on the *Result of MetaPhlAn or HUMAnN analysis* file. This file allow GraPhlAn to highlight for you the found biomarkers.
+
+Input parameters
+----------------
+ 
+    --annotations ANNOTATIONS
+                        List which levels should be annotated in the tree. Use
+                        a comma separate values form, e.g.,
+                        --annotation_levels 1,2,3. Default is None
+    --external_annotations EXTERNAL_ANNOTATIONS
+                        List which levels should use the external legend for
+                        the annotation. Use a comma separate values form,
+                        e.g., --annotation_levels 1,2,3. Default is None
+    --background_levels BACKGROUND_LEVELS
+                        List which levels should be highlight with a shaded
+                        background. Use a comma separate values form, e.g.,
+                        --background_levels 1,2,3
+    --background_clades BACKGROUND_CLADES
+                        Specify the clades that should be highlight with a
+                        shaded background. Use a comma separate values form
+                        and surround the string with " if it contains spaces.
+                        Example: --background_clades "Bacteria.Actinobacteria,
+                        Bacteria.Bacteroidetes.Bacteroidia,
+                        Bacteria.Firmicutes.Clostridia.Clostridiales"
+    --background_colors BACKGROUND_COLORS
+                        Set the color to use for the shaded background. Colors
+                        can be either in RGB or HSV (using a semi-colon to
+                        separate values, surrounded with ()) format. Use a
+                        comma separate values form and surround the string
+                        with " if it contains spaces. Example:
+                        --background_colors "#29cc36, (150; 100; 100), (280;
+                        80; 88)"
+    --title TITLE         If specified set the title of the GraPhlAn plot.
+                        Surround the string with " if it contains spaces,
+                        e.g., --title "Title example"
+    --title_font_size TITLE_FONT_SIZE
+                        Set the title font size. Default is 15
+    --def_clade_size DEF_CLADE_SIZE
+                        Set a default size for clades that are not found as
+                        biomarkers by LEfSe. Default is 10
+    --min_clade_size MIN_CLADE_SIZE
+                        Set the minimum value of clades that are biomarkers.
+                        Default is 20
+    --max_clade_size MAX_CLADE_SIZE
+                        Set the maximum value of clades that are biomarkers.
+                        Default is 200
+    --def_font_size DEF_FONT_SIZE
+                        Set a default font size. Default is 10
+    --min_font_size MIN_FONT_SIZE
+                        Set the minimum font size to use. Default is 8
+    --max_font_size MAX_FONT_SIZE
+                        Set the maximum font size. Default is 12
+    --annotation_legend_font_size ANNOTATION_LEGEND_FONT_SIZE
+                        Set the font size for the annotation legend. Default
+                        is 10
+    --abundance_threshold ABUNDANCE_THRESHOLD
+                        Set the minimun abundace value for a clade to be
+                        annotated. Default is 20.0
+    --most_abundant MOST_ABUNDANT
+                        When only lefse_input is provided, you can specify how
+                        many clades highlight. Since the biomarkers are
+                        missing, they will be chosen from the most abundant
+    --least_biomarkers LEAST_BIOMARKERS
+                        When only lefse_input is provided, you can specify the
+                        minimum number of biomarkers to extract. The taxonomy
+                        is parsed, and the level is choosen in order to have
+                        at least the specified number of biomarkers
+    --discard_otus        If specified the OTU ids will be discarde from the
+                        taxonmy. Default behavior keep OTU ids in taxonomy
+    --internal_levels     If specified sum-up from leaf to root the abundances
+                        values. Default behavior do not sum-up abundances on
+                        the internal nodes
+
+    input parameters:
+
+    -i LEFSE_INPUT, --lefse_input LEFSE_INPUT 
+                   
+    -o LEFSE_OUTPUT, --lefse_output LEFSE_OUTPUT
+
+    output parameters:
+
+    -t TREE, --tree TREE  Output filename where save the input tree for GraPhlAn
+
+    -a ANNOTATION, --annotation ANNOTATION :  This is the Output filename where to save GraPhlAn annotation
+  
+    Input data matrix parameters:
+    --sep SEP
+    --out_table OUT_TABLE   : This is where to write the  processed data matrix to file
+
+    --fname_row FNAME_ROW   :  Row number containing the names of the features (default 0, specify -1 if no names are present in the matrix)
+
+    --sname_row SNAME_ROW
+                        column number containing the names of the samples (default 0, specify -1 if no names are present in the matrix)
+    --metadata_rows METADATA_ROWS
+                        Row numbers to use as metadata[default None, meaning
+                        no metadata
+    --skip_rows SKIP_ROWS
+                        Row numbers to skip (0-indexed, comma separated) from
+                        the input file[default None, meaning no rows skipped
+    --sperc SPERC         Percentile of sample value distribution for sample
+                        selection
+    --fperc FPERC         Percentile of feature value distribution for sample
+                        selection
+    --stop STOP           Number of top samples to select (ordering based on
+                        percentile specified by --sperc)
+    --ftop FTOP           Number of top features to select (ordering based on
+                        percentile specified by --fperc)
+    --def_na DEF_NA       Set the default value for missing values [default None
+                        which means no replacement]
+
+Integration
+===========
+
+A graphical representation of how **export2graphlan** can be integrated in the analysis pipeline:
+
+.. image:: https://bitbucket.org/repo/oL6bEG/images/3364692296-graphlan_integration.png
+    :height: 672
+    :width: 800
+
+Want to know more?
+==================
+
+If you want to know more about **export2graphlan** please have a look at the tutorial
+  </help>
+</tool>