#start idev session if you need to
idev

#copy over the exercise directory
cds
cd rad_intro/
cp -r /work/02260/grovesd/lonestar/intro_to_rad_2017/mapping/denovo_2bRAD .
cd denovo_2bRAD/

#look at starting trimmed fastq files
ls *.trim

		sampleA.trim  sampleB.trim  sampleC.trim

#run uniquerOne.pl
#(this is analogous to making 'stacks' in STACKS (Fig1A Catchen et al. (2011))
#finds the unique RAD tags from each fastq

uniquerOne.pl sampleA.trim > sampleA.trim.uni
uniquerOne.pl sampleB.trim > sampleB.trim.uni
uniquerOne.pl sampleC.trim > sampleC.trim.uni

# merging uniqued files
#(Fig1B Catchen et al. (2011))
mergeUniq.pl uni minDP=2 >mydataMerged.uniq

#generates a merged set of unique tags:
		mergedUniqTags.fasta

# clustering allowing for up to 3 mismatches (-c 0.91); the most abundant sequence becomes reference
#This is equivalent to calling loci (Fig1C-D Catchen et al. (2011))
module load cd-hit
cd-hit-est -i mergedUniqTags.fasta -o cdh_alltags.fas -aL 1 -aS 1 -g 1 -c 0.91 -M 0 -T 0

#now we have called de novo loci based on the tags
#assemble them into an artificial reference for re-mapping and genotyping
concatFasta.pl fasta=cdh_alltags.fas num=8

#index the artificial reference with bowtie
module load bowtie
bowtie2-build cdh_alltags_cc.fasta cdh_alltags_cc.fasta

#now map the reads back to the artificial reference
bowtie2 --no-unal -x cdh_alltags_cc.fasta -U sampleC.trim -S sampleC.trim.bt2.sam
bowtie2 --no-unal -x cdh_alltags_cc.fasta -U sampleB.trim -S sampleB.trim.bt2.sam
bowtie2 --no-unal -x cdh_alltags_cc.fasta -U sampleA.trim -S sampleA.trim.bt2.sam

#The alignment files can now be used for whichever genotyping method you prefer