Post date: Sep 06, 2013 8:6:25 PM
#First, I copied the catfastqContigs.pl script from greenhouse to sunflower.
scp catfastqContigs.pl lauren@sunflower.uwyo.edu:/data/local/july13_ut/
#Then on sunflower, I ran this script. (The unassembled reads is really a fastq file, not a fasta file)
catfastqContigs.pl stygoparnus_15mil_qc_mmp84.fasta
#Reference made from 226532 contigs
mv pruned_ref_contig stygoparnus_ref.fasta
#Ran the fixnames.pl script just in case there's still a space at the end of some individual names:
scp fixnames.pl lauren@sunflower.uwyo.edu:/data/local/july13_ut/
perl fixnames.pl parsed_clean_lane3_Undetermined_R1.cat.fastq
scp eurycea_script_ref_18ii12.txt lauren@sunflower.uwyo.edu:/data/local/july13_ut/
mv eurycea_script_ref_18ii12.txt stygoparnus_script_ref_6ix13.txt
#made a new directory in /node4raid/assem/
mkdir stygoparnus/
#I changed the following in the reference-based assembly script:
#!/usr/bin/xng
setDefaultDirectory defaultDirectory: "/node4raid/assem/stygoparnus/"
project kind: targeted_exome
workflow kind: large_templated
diskPath path: "/node4raid/assem/stygoparnus/"
AssembleTemplate template: {
{
file: "/data/local/july13_ut/stygoparnus_ref.fasta"
}
}
query: {
{
file : "/data/local/july13_ut/mod_parsed_clean_lane3_Undetermined_R1.cat.fastq"
SeqTech: Illumina
}
}
directoryQueryMer: "/node4raid/assem/stygoparnus/ref_6ix13/ref_6ix13/mers"
directoryTemplateMer: "/node4raid/assem/stygoparnus/ref_6ix13/TemplateMers/"
hits: "/node4raid/assem/stygoparnus/ref_6ix13/ref_6ix13/ref_6ix13.hits"
layout: "/node4raid/assem/stygoparnus/ref_6ix13/ref_6ix13/ref_6ix13.layout"
results: "/node4raid/assem/stygoparnus/ref_6ix13/ref_6ix13.txt"
unassembled: "/node4raid/assem/stygoparnus/ref_6ix13/ref_6ix13-shared/ref_6ix13_unassembled.fastq"
output: "/node4raid/assem/stygoparnus/ref_6ix13/ref_6ix13"
format: BAM
merSize: 51
merSkipQuery: 2
LayoutType: once
minMatchPercent: 90
gapPenalty: 25
mismatchPenalty: 20
matchScore: 10
MaxGap: 5
SplitTemplateContigs: false
minAlignedLength: 60
repeatCnt: 100
autoTrim: true
onePackage: true
maxN: 3
deleteIntermediates: notTemplateMer
openInSeqMan: true
quit
#Then I ran the ref-based assembly:
xng stygoparnus_script_ref_6ix13.txt &
#I checked back a couple hours later, it was finished. 50% assembled, 74,574,634 reads. (Compared to 3,489,195 for Heterelmis, 7,511,165 for Stygobromus, 15,309,963 for Eurycea). See ref_6ix13-0.info for this number.