diff single_fastq_filtering.xml @ 9:c2c69c6090f0 draft

Uploaded
author petr-novak
date Fri, 31 Jan 2020 06:55:23 -0500
parents 378565f5a875
children 768883847008
line wrap: on
line diff
--- a/single_fastq_filtering.xml	Mon Dec 09 04:14:48 2019 -0500
+++ b/single_fastq_filtering.xml	Fri Jan 31 06:55:23 2020 -0500
@@ -1,9 +1,9 @@
-<tool id="single_fastq_filtering" name="Preprocessing of fastq reads">
+<tool id="single_fastq_filtering" name="Preprocessing of FASTQ reads">
   <stdio>
     <exit_code range="1:" level="fatal" description="Error" />
   </stdio>
   <description>
-    Preprocessing of fastq files
+    Preprocessing of FASTQ read files
     including trimming, quality filtering, cutadapt filtering and sampling
   </description>
   <requirements>
@@ -35,43 +35,43 @@
   </command>
 
   <inputs>
-    <param format="fastq,fastq.gz" type="data" name="A" label="reads in fastq format" />
+    <param format="fastq,fastq.gz" type="data" name="A" label="Reads in FASTQ format" />
     <conditional name="sampling">
-      <param name="sequence_sampling" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Sequence sampling"/>
+      <param name="sequence_sampling" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Read sampling"/>
 	    <when value="false">
         <!-- do nothing here -->
       </when>
       <when value="true">
-   		  <param name="sample_size" type="integer" label="Sample size(number of reads" help="How many sequence reads should be in resulting dataset" value="500000" min="0"/>
+   		  <param name="sample_size" type="integer" label="Sample size (number of reads)" help="How many reads should be sampled" value="500000" min="0"/>
       </when>
     </conditional>
 
-    <param type="integer" name="cut_off" label="Quality cut-off" value="10" min="0" help="see below how to correctly set quality cut-off" />
-    <param type="integer" name="percent_above" label="percent above cutoff" value="95" min="0"
-           help="Percent of bases in sequence that must have quality equal to / higher than cut-off value" />
+    <param type="integer" name="cut_off" label="Quality cut-off" value="10" min="0" help="See below how to correctly set the quality cut-off" />
+    <param type="integer" name="percent_above" label="Percent above cutoff" value="95" min="0"
+           help="Percentage of bases in the read that must have quality equal to or higher than the cut-off value" />
 
     <conditional name="trimming">
-      <param name="sequence_trimming" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Trim sequences"/>
+      <param name="sequence_trimming" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Trim reads"/>
       <when value="false">
         <!-- do nothing here -->
       </when>      
       <when value="true">
-        <param type="integer" name="trim_start" label="trimming - start position" value="1" min="1"
-               help="sequences are trimmed at specified start" />
-        <param type="integer" name="trim_end" label="trimming - end position" value="100" min="1"
-               help="sequences are trimmed to specified end position, shorted sequences are discarded" />
+        <param type="integer" name="trim_start" label="Start position" value="1" min="1"
+               help="Reads are trimmed at the specified start" />
+        <param type="integer" name="trim_end" label="End position" value="100" min="1"
+               help="Reads are trimmed to the specified end position, shorted sequences are discarded" />
       </when>      
 
     </conditional>
-   	<param name="max_n" type="integer" label="maximum Ns" help="Maximum number of Ns in sequence" value="0" min="0" max="10"/>
+   	<param name="max_n" type="integer" label="maximum Ns" help="Maximal number of Ns allowed in reads" value="0" min="0" max="10"/>
 
     <conditional name="cutadapt">
-      <param name="use_custom" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Do you want to use custom cutadapt options"/>
+      <param name="use_custom" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Custom cutadapt options"/>
 	    <when value="false">
         <!-- do nothing here -->
       </when>
       <when value="true">
-   		  <param name="custom_options" type="text" area="True" size="8x30"  label="Cutadapt custom options" help="Consult cutadapt for usage" value="">
+   		  <param name="custom_options" type="text" area="True" size="8x30"  label="Custom options" help="Consult cutadapt for usage" value="">
           <sanitizer sanitize="False"/>
           </param>>
       </when>
@@ -84,7 +84,7 @@
       </when>
       <when value="true">
 
-   		  <param name="filter_database" format="fasta" type="data" label="Sequence filter database" help="Provide DNA sequences in fasta format. Sequence reads which has at least 90% similarity over 90% of length to sequence in filter database will be removed. This is suitable option if you want to remove organele DNA or contamination"/>
+   		  <param name="filter_database" format="fasta" type="data" label="Sequence filter database" help="Provide DNA sequences in FASTA format. Reads that have at least 90% similarity over 90% of their length to sequence in the filter database will be removed. This option is suitable for removing organellar or other contaminating sequences."/>
       </when>
     </conditional>
 
@@ -92,8 +92,8 @@
 
 
   <outputs>
-    <data format="fasta" name="output" label="filtered fasta reads from datasets ${A.hid}"/>
-    <data format="png" name="png_output" label="nucleotide composition after filtering of ${A.hid}"/>"
+    <data format="fasta" name="output" label="Filtered FASTA reads from datasets ${A.hid}"/>
+    <data format="png" name="png_output" label="Nucleotide composition after filtering of ${A.hid}"/>"
   </outputs>
 
   <tests>