# HG changeset patch
# User dnbenso
# Date 1643082318 0
# Node ID 1808eaa9d699cdad4e0ccec9dc77c9ec13ca933d
# Parent  03edd7b30f660d8c9b8b42e5d6e47607cb73c163
Uploaded

diff -r 03edd7b30f66 -r 1808eaa9d699 default-masurca-config
--- a/default-masurca-config	Mon Jan 24 00:00:54 2022 +0000
+++ b/default-masurca-config	Tue Jan 25 03:45:18 2022 +0000
@@ -61,3 +61,4 @@
 #DO NOT use if you have less than 15x coverage by long reads.
 FLYE_ASSEMBLY=0
 END 
+
diff -r 03edd7b30f66 -r 1808eaa9d699 masurca.xml
--- a/masurca.xml	Mon Jan 24 00:00:54 2022 +0000
+++ b/masurca.xml	Tue Jan 25 03:45:18 2022 +0000
@@ -41,6 +41,7 @@
         sed -i 's|STDDEV|$stddev|' config.txt &&
         sed -i 's|JELLYFISHSIZE|$jfsize|' config.txt &&
         sed -i 's|USE_LINKING_MATES = 0|USE_LINKING_MATES = $lnkmts|' config.txt &&
+        sed -i 's|MEGA_READS_ONE_PASS=0|MEGA_READS_ONE_PASS=$mega_one_pass|' config.txt &&
         sed -i 's|FLYE_ASSEMBLY=0|FLYE_ASSEMBLY=$flye|' config.txt &&
         masurca config.txt &&
         bash assemble.sh
@@ -100,6 +101,8 @@
             </when>
         </conditional>
         <param type="integer" name="jfsize" value="20000000" label="Jellyfish hash size" help="Set this to about 10x the genome size" />
+        <param type="boolean" name="mega_one_pass" truevalue="1" falsevalue="0" label="MEGA_READS_ONE_PASS"
+            help="set to 0 (default) to do two passes of mega-reads for slower, but higher quality assembly, otherwise set to 1" />
         <param type="boolean" name="flye" truevalue="1" falsevalue="0" label="Set this to use Flye assembler for final assembly of corrected mega-reads"
             help="If you are doing Hybrid Illumina paired end + Nanopore/PacBio assembly ONLY (no Illumina mate pairs or OTHER frg files). DO NOT use if you have less than 15x coverage by long read" />
         <param type="boolean" name="lnkmts" truevalue="1" falsevalue="0" label="Include Linking Mates"
@@ -119,6 +122,13 @@
     </outputs>
     <tests>
         <test>
+        <!--
+            The test files are too large for upload to a toolshed or git repo. 
+            For convenience I've include download instructions in each file so
+            that if you are testing with planemo you can at least download the
+            data and perform a basic test. If anyone has any datasets less than
+            1Mb that can be used to complete an assembly please let me know.
+        -->
             <conditional name="illumina_input">
                 <param name="input_type" value="paired" />
                 <param name="fastq_input1" value="illumina_reads_1.fastq"/>
@@ -138,6 +148,7 @@
             <param name="mean" value="500" />
             <param name="stddev" value="50" />
             <param name="jfsize" value="80349460" />
+            <param name="mega_one_pass" value="0" />
             <param name="flye" value="1" />
             <param name="lnkmts" value="0" />
             <output name="superReads" ftype="fasta">
@@ -149,10 +160,32 @@
     </tests>
     <help><![CDATA[
 
-        This implementation of MaSuRCA uses a config file for more complicated
-        assemblies and to change default settings. Illumina reads (mandatory)
-        and long reads from PACBIO or Oxford Nanopore or both can be included.
+**MaSuRCA**
+
+This implementation of MaSuRCA uses a config file for more complicated assemblies and to change default settings. Illumina reads (mandatory) and long reads from PACBIO or Oxford Nanopore or both can be included.  It is written by `Aleksey Zimin`_ at Johns Hopkins University. Included below is relevant notes from MaSuRCA's `github page`_.
+
+.. _`Aleksey Zimin`: https://github.com/alekseyzimin
+.. _`github page`: https://github.com/alekseyzimin/masurca
+
+-----
+
+**Input data**
+
+The following types of data are supported::
 
+  * Illumina paired end (or single end) reads -- MANDATORY. The mean and stdev parameters are the library insert average length and standard deviation. If the standard deviation is not known, set it to approximately 15% of the mean.If the second (reverse) read set is not available, do not specify it and just specify the forward reads. Files must be in fastq format and can be gzipped.
+  * PacBio/MinION data are supported. Note that you have to have 50x + coverage in Illumina Paired End reads to use PacBio of Oxford Nanopore MinION data. Supply PacBio or MinION reads in a single fasta or fastq file (can be gzipped).
+
+**Parameters**
+
+The following parameter is mandatory::
+
+  * jellyfish hash size, set this to about 10x the genome size.
+
+Optional parameters:
+
+  * linking mates: Most of the paired end reads end up in the same super read and thus are not passed to the assembler. Those that do not end up in the same super read are called ”linking mates” . The best assembly results are achieved by setting this parameter to 1 for Illumina-only assemblies. If you have more than 2x coverage by long (454, Sanger, etc) reads, set this to 0.
+  
     ]]></help>
     <citations>
         <citation type="doi">10.1093/bioinformatics/btt476</citation>