changeset 9:1bfc7254232e draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/trim_galore commit f971832d2b34a182314e5201ea6895dd207c5923

--- a/trim_galore.xml	Fri Mar 18 07:56:01 2016 -0400
+++ b/trim_galore.xml	Thu Mar 16 13:48:46 2017 -0400
@@ -1,15 +1,15 @@
 <tool id="trim_galore" name="Trim Galore!" version="0.4.2">
     <!-- Wrapper compatible with Trim Galore! version 0.4 -->
-    <description>adaptive quality and adapter trimmer</description>
+    <description>Quality and adapter trimmer of reads</description>
     <macros>
         <macro name="adapter_trimming">
             <conditional name="trimming">
-                <param name="trimming_select" type="select" label="Trimming reads?">
+                <param name="trimming_select" type="select" label="Adapter sequence to be trimmed">
                     <option value="">Automatic detection</option>
                     <option value="--illumina">Illumina universal</option>
                     <option value="--nextera">Nextera transposase</option>
                     <option value="--small_rna">Illumina small RNA adapters</option>
-                    <option value="user">User defined adapter trimming</option>
+                    <option value="user">User defined adapter sequence</option>
                 </param>
                 <when value=""/>
                 <when value="--illumina"/>
@@ -36,10 +36,10 @@
                     This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality.
                     (--three_prime_clip_R1)</help>
             </param>
-            <param name="three_prime_clip_R2" type="integer" value="" optional="True" label="Remove N bp from the 3' end of read 1">
+            <param name="three_prime_clip_R2" type="integer" value="" optional="True" label="Remove N bp from the 3' end of read 2">
                 <help>Instructs Trim Galore! to remove N bp from the 3' end of read 2 after
                     adapter/quality trimming has been performed. This may remove some unwanted bias from
-                    the 3' end that is not directly related to adapter sequence or basecall quality. (--three_prime_clip_R2)</help>
+                    the 3' end that is not directly related to adapter sequence or basecall quality.</help>
             </param>
         </macro>
     </macros>
@@ -249,14 +249,14 @@
             <when value="default" />
             <!-- Full/advanced params. -->
             <when value="custom">
-                <param name="quality" type="integer" value="20" label="Trim low-quality ends from reads in addition to adapter removal"
+                <param name="quality" type="integer" value="20" label="Trim low-quality ends from reads in addition to adapter removal (Enter phred quality score threshold)"
                     help="For more information please see below." />
                 <param name="stringency" type="integer" value="1" label="Overlap with adapter sequence required to trim a sequence" />
                 <param name="error_rate" type="float" value="0.1" label="Maximum allowed error rate" />
-                <param name="min_length" type="integer" value="20" label="Discard reads that became shorter than length INT" />
+                <param name="min_length" type="integer" value="20" label="Discard reads that became shorter than length N" />
 
-                <param name="clip_R1" type="integer" optional="True" min="0" label="Instructs Trim Galore! to remove INT bp from the 5' end of read 1" />
-                <param name="clip_R2" type="integer" optional="True" min="0" label="Instructs Trim Galore! to remove INT bp from the 5' end of read 2" />
+                <param name="clip_R1" type="integer" optional="True" min="0" label="Instructs Trim Galore! to remove N bp from the 5' end of read 1" />
+                <param name="clip_R2" type="integer" optional="True" min="0" label="Instructs Trim Galore! to remove N bp from the 5' end of read 2 (Only for paired-end reads)" />
 
                 <param name="report" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Generate a report file" help="" />
 
@@ -287,7 +287,7 @@
                 <param name="rrbs" type="boolean" truevalue="--rrbs" falsevalue="" checked="True"
                     label="Specifies that the input file was an MspI digested RRBS sample" />
                 <param name="non_directional" type="boolean" truevalue="--non_directional" falsevalue="" checked="False"
-                    label="Selecting this option for non-directional RRBS libraries" />
+                    label="Screen quality-trimmed sequences for 'CAA' or 'CGA' at the start of the read and, if found, removes the first two basepairs" />
             </when>  <!-- full -->
         </conditional>  <!-- params -->
 
@@ -418,7 +418,142 @@
 .. _Trim Galore!: http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/
 
 It is developed by Felix Krueger at the Babraham Institute.
-]]>
+
+----
+
+**Main Settings**
+
+* **Adapter sequence to be trimmed**
+
+  * **Automatic detection**
+    
+      | Adapter sequence to be trimmed. Trim Galore will try to auto-detect whether the Illumina universal, Nextera transposase or Illumina small RNA adapter sequence was used.
+
+  * **Illumina universal**
+
+      | Adapter sequence to be trimmed is the first 13bp of the Illumina universal adapter 'AGATCGGAAGAGC' instead of the default auto-detection of adapter sequence.
+      |
+      | *option --illumina*
+
+  * **Nextera transposase**
+
+      | Adapter sequence to be trimmed is the first 12bp of the Nextera adapter 'CTGTCTCTTATA' instead of the default auto-detection of adapter sequence.
+      |
+      | *option --nextera*
+
+  * **Illumina small RNA adapters**
+
+      | Adapter sequence to be trimmed is the first 12bp of the Illumina Small RNA 3' Adapter 'TGGAATTCTCGG' instead of the default auto-detection of adapter sequence. Selecting to trim smallRNA adapters will also lower the --length value to 18bp. If the smallRNA libraries are paired-end then -a2 will be set to the Illumina small RNA 5' adapter automatically (‘GATCGTCGGACT’) unless -a 2 had been defined explicitly.
+      |
+      | *option --small_rna*
+
+  * **User defined adapter trimming**
+
+      | Adapter sequence to be trimmed is the sequence entered by the user instead of the default auto-detection of adapter sequence.
+      |
+      | *option -a*
+
+* **If Single-End Reads**
+
+  * **Remove <int> bp from the 3' end**
+
+      | <int> Instructs Trim Galore to remove <int> bp from the 3' end of read 1 (or single-end reads) AFTER adapter/quality trimming has been performed. This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality. Default: OFF.
+      |
+      | *option --three_prime_clip_R1*
+
+* **If Paired-End Reads**
+
+  * **Trims 1 bp off every read from its 3' end**
+
+      | This may be needed for FastQ files that are to be aligned as paired-end data with Bowtie. This is because Bowtie (1) regards alignments like this:
+      |
+      |   R1 --------------------------->
+      |   R2 <---------------------------
+      |
+      | or this:
+      | 
+      |   R1 ----------------------->
+      |   R2 <-----------------
+      |
+      | as invalid (whenever a start/end coordinate is contained within the other read).
+      |
+      | *option --t*
+
+  * **Remove <int> bp from the 3' end of read 1**
+
+      | <int> Instructs Trim Galore to remove <int> bp from the 3' end of read 1 (or single-end reads) AFTER adapter/quality trimming has been performed. This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality. Default: OFF.
+      |
+      | *option --three_prime_clip_R1*
+
+  * **Remove <int> bp from the 3' end of read 2**
+
+      | <int> Instructs Trim Galore to remove <int> bp from the 3' end of read 2 AFTER adapter/quality trimming has been performed. This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality. Default: OFF.
+      |
+      | *option --three_prime_clip_R2*
+
+----
+
+**Advanced Settings**
+
+* **Trim low-quality ends from reads in addition to adapter removal**
+
+    | For RRBS samples, quality trimming will be performed first, and adapter trimming is carried in a second round. Other files are quality and adapter trimmed in a single pass. The algorithm is the same as the one used by BWA (Subtract <INT> from all qualities; compute partial sums from all indices to the end of the sequence; cut sequence at the index at which the sum is minimal). Default Phred score: 20.
+    |
+    | *option -q*
+
+* **Overlap with adapter sequence required to trim a sequence**
+
+    | Defaults to a very stringent setting of '1', i.e. even a single bp of overlapping sequence will be trimmed of the 3' end of any read.
+    |
+    | *option -s*
+
+* **Maximum allowed error rate**
+
+    | (no. of errors divided by the length of the matching region) (default: 0.1).
+    |
+    | *option -e*
+
+* **Discard reads that became shorter than length <INT>**
+
+    | because of either quality or adapter trimming. A value of '0' effectively disables this behaviour. Default: 20 bp.
+    |
+    | For paired-end files, both reads of a read-pair need to be longer than <INT> bp to be printed out to validated paired-end files (see option --paired). If only one read became too short there is the possibility of keeping such unpaired single-end reads (see --retain_unpaired). Default pair-cutoff: 20 bp.
+    |
+    | *option --length*
+
+* **Instructs Trim Galore! to remove INT bp from the 5' end of read 1**
+
+    | Instructs Trim Galore to remove <INT> bp from the 5' end of read 1 (or single-end reads). This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end. Default: OFF.
+    |
+    | *option --clip_R1*
+
+* **Instructs Trim Galore! to remove INT bp from the 5' end of read 2**
+
+    | Instructs Trim Galore to remove <int> bp from the 5' end of read 2 (paired-end reads only). This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end. For paired-end BS-Seq, it is recommended to remove the first few bp because the end-repair reaction may introduce a bias towards low methylation. Please refer to the M-bias plot section in the Bismark User Guide for some examples. Default: OFF.
+    |
+    | *option --clip_R2*
+
+* **Specify if you would like to retain unpaired reads**
+
+    | If only one of the two paired-end reads became too short, the longer read will be written to either '.unpaired_1.fq' or '.unpaired_2.fq' output files. The length cutoff for unpaired single-end reads is governed by the parameters -r1/--length_1 and -r2/--length_2. Default: OFF.
+    |
+    | *option --retained_unpaired*
+
+----
+
+**RRBS specific settings**
+
+* **Specifies that the input file was an MspI digested RRBS sample (recognition site: CCGG)**
+
+    | Sequences which were adapter-trimmed will have a further 2 bp removed from their 3' end. This is to avoid that the filled-in C close to the second MspI site in a sequence is used for methylation calls. Sequences which were merely trimmed because of poor quality will not be shortened further.
+    |
+    | *option -rrbs*
+
+* **Screen quality-trimmed sequences for 'CAA' or 'CGA' at the start of the read and, if found, removes the first two basepairs**
+
+    | Selecting this option for non-directional RRBS libraries will screen quality-trimmed sequences for 'CAA' or 'CGA' at the start of the read and, if found, removes the first two basepairs. Like with the option '--rrbs' this avoids using cytosine positions that were filled-in during the end-repair step. '--non_directional' requires '--rrbs' to be specified as well.
+    |
+    | *option --non_directional*]]>
     </help>
     <citations></citations>
 </tool>