# ref_map.sh - run ref_map on An. darlingi RAD data
#ref_map.pl version 1.21 started at 2015-01-13 09:17:46

mkdir $src/filtered_seqs                                                                                         
process_radtags -f $src/raw_sequences -o $src/filtered_seqs \                                     
  -i fastq -c -q —r 

# Take all read 1s and align them to the darlingi genome.  We will use the resulting 
# SAM files to run ref_map.                                                                                           

mkdir $src/rad_alignments
for f in $src/filtered_seqs/*.fastq                                                                                 
do  
  echo "Running bowtie alignments on: $f"
  bowtie /genomes/Anopheles_darlingi/AdarC3 $f -p 30 --sam > ./rad_alignments/$(basename $f | 
    sed 's/\.fastq//').sam 2>>./rad_alignments/alignments.log
done   

# Set up the MYSQL database for the stacks data
# This is required for use of the STACKS web browser
mysql -e 'CREATE DATABASE darlingi_radtags'
mysql darlingi_radtags < /usr/local/share/stacks/sql/stacks.sql

mkdir $stacks

ref_map.pl -o $stacks -n 0 -T 30 -m 5 -O popmap -b 1 -S \
 -B darlingi_radtags -D ‘Melinas RAD database' \
-s ./rad_alignment/A12G002.sam \
-s ./rad_alignment/A12G003.sam \
-s ./rad_alignment/A12G009.sam \
-s ./rad_alignment/A12G010.sam \
-s ./rad_alignment/A12G011.sam \
-s ./rad_alignment/A12G012.sam \
-s ./rad_alignment/A12G013.sam \
-s ./rad_alignment/A12G014.sam \
-s ./rad_alignment/A12G015.sam \
-s ./rad_alignment/A12G016.sam \
-s ./rad_alignment/A12G017.sam \
-s ./rad_alignment/A12G018.sam \
-s ./rad_alignment/A12G019.sam \
-s ./rad_alignment/A12G022.sam \
-s ./rad_alignment/A12G023.sam \
-s ./rad_alignment/A12R012.sam \
-s ./rad_alignment/A12R013.sam \
-s ./rad_alignment/A12R015.sam \
-s ./rad_alignment/A12R016.sam \
-s ./rad_alignment/A12R020.sam \
-s ./rad_alignment/A12R021.sam \
-s ./rad_alignment/A12R022.sam \
-s ./rad_alignment/A12R023.sam \
-s ./rad_alignment/A12R024.sam \
-s ./rad_alignment/A12R026.sam \
-s ./rad_alignment/A12R027.sam \
-s ./rad_alignment/A12R028.sam \
-s ./rad_alignment/A12R030.sam \
-s ./rad_alignment/A12R031.sam \
-s ./rad_alignment/A12R032.sam \
-s ./rad_alignment/A12R033.sam \
-s ./rad_alignment/CS16.sam \
-s ./rad_alignment/CS17.sam \
-s ./rad_alignment/CS18.sam \
-s ./rad_alignment/CS20.sam \
-s ./rad_alignment/CS21.sam \
-s ./rad_alignment/CS22.sam \
-s ./rad_alignment/CS23.sam \
-s ./rad_alignment/CS24.sam \
-s ./rad_alignment/CS25.sam \
-s ./rad_alignment/CS26.sam \
-s ./rad_alignment/CS27.sam \
-s ./rad_alignment/CS28.sam \
-s ./rad_alignment/CS29.sam \
-s ./rad_alignment/CS30.sam 

# Run the stacks genotype correction module

rxstacks -b 1 -P $src/stacks -o ./stacks_cor  --prune_haplo  \
  --lnl_lim -10.0 -t 8 --verbose --lnl_dist

cstacks -b 1 -p 15 -o ./stacks_cor \
-s ./stacks_cor/A12G002 \
-s ./stacks_cor/A12G003 \
-s ./stacks_cor/A12G009 \
-s ./stacks_cor/A12G010 \
-s ./stacks_cor/A12G011 \
-s ./stacks_cor/A12G012 \
-s ./stacks_cor/A12G013 \
-s ./stacks_cor/A12G014 \
-s ./stacks_cor/A12G015 \
-s ./stacks_cor/A12G016 \
-s ./stacks_cor/A12G017 \
-s ./stacks_cor/A12G018 \
-s ./stacks_cor/A12G019 \
-s ./stacks_cor/A12G022 \
-s ./stacks_cor/A12G023 \
-s ./stacks_cor/A12R012 \
-s ./stacks_cor/A12R013 \
-s ./stacks_cor/A12R015 \
-s ./stacks_cor/A12R016 \
-s ./stacks_cor/A12R020 \
-s ./stacks_cor/A12R021 \
-s ./stacks_cor/A12R022 \
-s ./stacks_cor/A12R023 \
-s ./stacks_cor/A12R024 \
-s ./stacks_cor/A12R026 \
-s ./stacks_cor/A12R027 \
-s ./stacks_cor/A12R028 \
-s ./stacks_cor/A12R030 \
-s ./stacks_cor/A12R031 \
-s ./stacks_cor/A12R032 \
-s ./stacks_cor/A12R033 \
-s ./stacks_cor/CS16 \
-s ./stacks_cor/CS17 \
-s ./stacks_cor/CS18 \
-s ./stacks_cor/CS20 \
-s ./stacks_cor/CS21 \
-s ./stacks_cor/CS22 \
-s ./stacks_cor/CS23 \
-s ./stacks_cor/CS24 \
-s ./stacks_cor/CS25 \
-s ./stacks_cor/CS26 \
-s ./stacks_cor/CS27 \
-s ./stacks_cor/CS28 \
-s ./stacks_cor/CS29 \
-s ./stacks_cor/CS30 
while read f; do
     sstacks -p 60 -b 1 -c ./stacks_cor/batch_1 \
     -s ./stacks_cor/${f} \
    -o ./stacks_cor/ &>> ./stacks_cor/Log
done < files

# Consider all samples as a single population

populations -b 1 -P ./stacks_cor -M ./popmap -t 20 -r 0.5 -m 5 --fstats \
  --write_single_snp --phylip --structure --log_fst_comp --vcf --genepop


# Now to run the structure analysis using runStructure.py

wget "http://genome.smcm.edu/emersonLab/runStructure.py"
grep -v "#" $src/stacks_cor/batch_1.structure.str $src/structure_input.str
./runStructure.py -i $src/structure_input.str -o $src/structure -p 10 -b 100000 \
  -m 1000000 -x 40 -k 40 -n 60