diff trycycler_consensus.xml @ 0:93c6a7423090 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/trycycler commit 9d7c4277b0f96aacd466f2d497e08edcca3fa238"
author iuc
date Thu, 11 Feb 2021 19:24:35 +0000
parents
children e59bee4565b3
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/trycycler_consensus.xml	Thu Feb 11 19:24:35 2021 +0000
@@ -0,0 +1,145 @@
+<tool id='trycycler_consensus' name='Trycycler consensus' version='@TOOL_VERSION@' profile='21.01'>
+    <description>generate a consensus contig sequence for each cluster</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro='edam_ontology'/>
+    <expand macro='requirements'/>
+    <version_command>trycycler --version</version_command>
+    <command detect_errors='exit_code'><![CDATA[
+        mkdir -p 'selected_cluster' &&
+        ln -s '${cluster_all_seqs}' 'selected_cluster/2_all_seqs.fasta' &&
+        ln -s '${reconcile_msa}' 'selected_cluster/3_msa.fasta' &&
+        ln -s '${partition_reads}' 'selected_cluster/4_reads.fastq' &&
+        trycycler consensus --cluster_dir 'selected_cluster'
+            #if $linear
+                --linear
+            #end if
+            --min_aligned_len $min_aligned_len
+            --min_read_cov $min_read_cov
+            --threads \${GALAXY_SLOTS:-2} &&
+            mv 'selected_cluster/7_final_consensus.fasta' $consensus
+    ]]></command>
+    <inputs>
+        <param name='cluster_all_seqs' type='data' 
+            format='fasta' label='Reconciled cluster' 
+            help='Reconciled sequences file' />
+        <param name='reconcile_msa' type='data' 
+            format='fasta' label='Reconcile msa' 
+            help='Multiple sequence alignment file' />
+        <param name='partition_reads' type='data' 
+            format='fastq' label='Partition reads' 
+            help='Partitioned reads' />
+        <param name='reads' type='data' 
+            format='fastq,fastq.gz' label='Long-read datasets' 
+            help='Long reads (FASTQ format) used to generate the assemblies' />
+        <param argument='--linear' type='boolean' 
+            truevalue='--linear' falsevalue='' 
+            label='Input contigs are not circular' 
+            help='Use this option if your input contigs are not circular. It will disable the circularisation-correction steps in Trycycler reconcile.' />
+        <param argument='--min_aligned_len' type='integer' min='500' max='3500' 
+            value='1000' label='Min bases aligned' 
+            help='Reads with less than this many bases aligned (default = 1000) will be ignored.' />
+        <param argument='--min_read_cov' type='integer' min='0' max='100' 
+            value='90' label='Min read length covered by alignments' 
+            help='Reads with less than this percentage of their length covered by alignments (default = 90.0) will be ignored.' />
+    </inputs>
+    <outputs>
+        <data name='consensus' format='fasta' label='${tool.name} on ${on_string}'/>
+    </outputs>
+    <tests>
+        <test>
+            <param name='cluster_all_seqs' value='reconciled_cluster_01.fasta'/>
+            <param name='reconcile_msa' value='aligned_cluster_01.fasta'/>
+            <param name='partition_reads' value='partition_01.fastq'/>
+            <param name='reads' value='reads.fastq.gz'/>
+            <param name='min_aligned_len' value='1200'/>
+            <param name='min_read_cov' value='95'/>
+            <output name='consensus' file='consensus_sequence_01.fasta'/>
+        </test>
+        <test>
+            <param name='cluster_all_seqs' value='reconciled_cluster_02.fasta'/>
+            <param name='reconcile_msa' value='aligned_cluster_02.fasta'/>
+            <param name='partition_reads' value='partition_01.fastq'/>
+            <param name='reads' value='reads.fastq.gz'/>
+            <param name='min_aligned_len' value='1100'/>
+            <param name='min_read_cov' value='90'/>
+            <output name='consensus' file='consensus_sequence_02.fasta'/>
+        </test>
+        <test>
+            <param name='cluster_all_seqs' value='reconciled_cluster_03.fasta'/>
+            <param name='reconcile_msa' value='aligned_cluster_03.fasta'/>
+            <param name='partition_reads' value='partition_01.fastq'/>
+            <param name='reads' value='reads.fastq.gz'/>
+            <param name='min_aligned_len' value='1300'/>
+            <param name='min_read_cov' value='97'/>
+            <output name='consensus' file='consensus_sequence_03.fasta'/>
+        </test>
+        <test>
+            <param name='cluster_all_seqs' value='reconciled_cluster_03.fasta'/>
+            <param name='reconcile_msa' value='aligned_cluster_03.fasta'/>
+            <param name='partition_reads' value='partition_01.fastq'/>
+            <param name='reads' value='reads.fastq.gz'/>
+            <param name='min_aligned_len' value='1000'/>
+            <param name='min_read_cov' value='87'/>
+            <output name='consensus' file='consensus_sequence_04.fasta'/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+.. class:: infomark
+
+**Purpose**
+
+**Trycycler consensus** generate a consensus contig sequence for each cluster. It does this by converting the MSA into a graph form. When there is a tie between options, Trycycler aligns the reads to the alternative sequences and chooses the option with the best read alignment scores.
+
+    ::
+
+        GGAGGAGCTTTT-CGCCGCAGTCAACGAA-TAGCGTCTGAAAACGTGTATCAT
+        GGAGGAGCTTTTTCGCCGCAGTCAAC--A-TAGCGTCTGAAAACGTGTATCAT
+        GGAGGAGCTTTTTCGCCGCAGTCAAC--ATTAGCGTCTGAAAACGTGTATCAT
+        GGAGGAGCTTTTTCGCCGCAGTCAAC--A-TAGCGTCTGAAAACGTGTATCAT
+        GGAGGAGCTTTT-CGCCGCAGTCAAC--A-TAGCGTCTGAAAACGTGTATCAT
+
+From the hypothetical MSA, Trycycler generates a variation graph:
+
+    ::
+
+                     ↗ - ↘               ↗ GAA- ↘
+                     ↗ T ↘               ↗ --A- ↘
+        GGAGGAGCTTTT → T → CGCCGCAGTCAAC → --AT → TAGCGTCTGAAAACGTGTATCAT
+                     ↘ T ↗               ↘ --A- ↗
+                     ↘ - ↗               ↘ --A- ↗
+
+
+
+The first thing Trycycler uses to choose variants is minimum total Hamming distance to the other variants. In cases of a minimum total Hamming distance tie, Trycycler will align the reads to each possibility and choose the option with the highest total read alignment score. Read alignment scores are calculated using a simple scheme: match score = 1, mismatch penalty = 1, gap open/extension penalty = 1. More information in the `documentation <https://github.com/rrwick/Trycycler/wiki/How-variants-are-chosen-for-the-consensus-sequence/>`_.
+
+
+
+----
+                    
+.. class:: infomark
+                    
+**Input**
+
+This tool requires the output generated by **Trycylcler reconcile**, **Trycycler msa** and **Trycycler partition**.
+
+
+----
+                    
+.. class:: infomark
+                    
+**Output**
+                    
+It generates a fasta file with the consesus sequence the cluster.
+
+
+----                                                                                                    
+                                                                                                        
+.. class:: infomark
+
+@PIPELINE@
+    ]]></help>
+    <expand macro='citations'/>
+</tool>