prep_gbs_ref.sge

#!/bin/bash

#prep_gbs_ref.sge
#sge submission script to prepare already qc'd reads for alignment to the reference
	#removes reads with improper restriction site
	#removes samples with no data
#M. Supple
#last modified 8 August 2016

#usage qsub stacks_final.sge <prep.input> <proper_read_start>
#<prep.input>:  see prep.example.input or example at end of this script
#<proper_read_start> is expected start of each read (PstI=TGCAG) 

#requires

#output
#interleaved fastq file for each sample



#$ -N prep_gbs_ref.sge
#$ -o prep_gbs_ref.output
#$ -l virtual_free=3g,h_vmem=3.1g
#$ -j y
#$ -cwd

#print some useful sge information
echo Job $JOB_NAME started `date` in queue $QUEUE with id=$JOB_ID on `hostname` 

#read in input
source $1
reseq=$2

#get list of samples
samples=($(ls $gbs_path/$user/$lane_name/qc/qc_S*_il.fastq.gz))

#loop over each sample
for ((a=0; a<${#samples[@]}; a++))
	do
		echo -e "processing sample ${samples[a]}"
		#remove bad reads
		remove_bad_restriction_sites.pl ${samples[a]} $reseq
	done

#remove samples with no data
for fullfile in $( ls clean_*gz ); do
        filename=$(basename "$fullfile")
        filesize=$( stat -c%s $fullfile )
        if [ "$filesize" -lt "21" ]; then
   		rm $filename     
 		echo "$filename failed"
        fi
done


#print note that job completed
echo done `date`