diff fsd_regions.xml @ 9:eabfdc012d7b draft

planemo upload for repository https://github.com/monikaheinzl/duplexanalysis_galaxy/tree/master/tools/fsd_regions commit 31f11c1cb3303d741ee11a25903c3cc42a23f30d

--- a/fsd_regions.xml	Tue Nov 20 09:51:47 2018 -0500
+++ b/fsd_regions.xml	Mon Nov 26 04:25:26 2018 -0500
@@ -1,16 +1,17 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<tool id="fsd_regions" name="Duplex Sequencing Analysis: fsd_regions" version="1.0.0">
+<tool id="fsd_regions" name="Duplex Sequencing Analysis: fsd_regions" version="1.0.1">
     <description>Family size distribution (FSD) of user-specified regions in the reference genome</description>
     <requirements>
         <requirement type="package" version="2.7">python</requirement>
         <requirement type="package" version="1.4.0">matplotlib</requirement>
     </requirements>
     <command>
-        python2 '$__tool_directory__/fsd_regions.py' --inputFile '$file1' --inputName1 '$file1.name' --ref_genome '$file2' --output_pdf $output_pdf --output_tabular $output_tabular 
+        python2 '$__tool_directory__/fsd_regions.py' --inputFile '$file1' --inputName1 '$file1.name' --bamFile '$file2' --rangesFile '$file3' --output_pdf $output_pdf --output_tabular $output_tabular 
     </command>
     <inputs>
         <param name="file1" type="data" format="tabular" label="Dataset 1: input tags of whole dataset" optional="false" help="Input in tabular format with the family size, tags and the direction of the strand ('ab' or 'ba') for each family."/>
-        <param name="file2" type="data" format="txt" label="Dataset 2: input tags aligned to the reference genome" help="Input in txt format with the regions in the reference genome and the tags, which were aligned to the reference genome."/>
+        <param name="file2" type="data" format="bam" label="Dataset 2: BAM file of aligned reads." help="Input in BAM format with the reads that were aligned to the reference genome."/>
+        <param name="file3" type="data" format="bed" label="Dataset 3: BED file with chromsome, start and stop positions of regions." optional="true" help="BED file with start and stop positions of regions."/>
     </inputs>
     <outputs>
         <data name="output_pdf" format="pdf" />
@@ -18,45 +19,39 @@
     </outputs>
     <tests>
         <test>
-            <param name="file1" value="Test_data.tabular"/>
-            <param name="file2" value="Test_data_regions.txt"/>
-            <output name="output_pdf" file="output_file.pdf" lines_diff="136"/>
-            <output name="output_tabular" file="output_file.tabular"/>
+            <param name="file1" value="fsd_reg.tab"/>
+            <param name="file2" value="fsd_reg.bam"/>
+            <param name="file3" value="fsd_reg_ranges.bed"/>
+            <output name="output_pdf" file="fsd_reg_output.pdf" lines_diff="136"/>
+            <output name="output_tabular" file="fsd_reg_output.tab"/>
         </test>
     </tests>
     <help> <![CDATA[
 
 **What it does**
         
-    This tool will create a distribution of family sizes of all tags, which were aligned to the reference genome. The distribution is separated after the regions of the reference genome.
+This tool will create a distribution of family sizes of all tags, which were aligned to the reference genome. The distribution is separated after the regions of the reference genome.
                
         
 **Input**
         
-    This tools expects a tabular file with the tags of all families, their sizes and information about forward (ab) and reverse (ba) strands. 
-    
-    +-----+----------------------------+----+
-    | 1   | AAAAAAAAAAAATGTTGGAATCTT   | ba |
-    +-----+----------------------------+----+
-    | 10  | AAAAAAAAAAAGGCGGTCCACCCC   | ab |
-    +-----+----------------------------+----+
-    | 28  | AAAAAAAAAAATGGTATGGACCGA   | ab |
-    +-----+----------------------------+----+
+**Dataset 1:** This tools expects a tabular file with the tags of all families, their sizes and information about forward (ab) and reverse (ba) strands. 
+
+    1  AAAAAAAAAAAATGTTGGAATCTT ba
+   10  AAAAAAAAAAAGGCGGTCCACCCC ab
+   28  AAAAAAAAAAATGGTATGGACCGA ab
     
-    
-    In addition, a TXT file with the regions and all tags that were aligned to the reference genome is required.      This file can obtained from a different tool.
-    
-    +-----------+------------------------------+
-    | 87_636    | AAATCAAAGTATGAATGAAGTTGCCT   |
-    +-----------+------------------------------+
-    | 87_636    | AAATTCATAGCATTAATTTCAACGGG   |
-    +-----------+------------------------------+
-    | 656_1143  | GGGGCAGCCATATTGGCAATTATCAT   |
-    +-----------+------------------------------+
+**Dataset 2:** BAM file of the aligned reads. This file can be obtained by the tool "Map with BWA-MEM".
+
+**Dataset 3 (optional):** BED file with start and stop positions of the regions. If it is not provided, then all aligned reads of the BAM file are used in the distribution of family sizes. 
+
+   ACH_TDII   90    633
+   ACH_TDII  659   1140
+   ACH_TDII 1144   1561
     
 **Output**
         
-    The output is a PDF file with the plot and a tabular file with the data of the plot.
+The output is a PDF file with the plot and a tabular file with the data of the plot.
         
         
 **About Author**