git clone https://github.com/Adamtaranto/RECONcile.git && cd RECONcile

awk '/^>/ {print $1;} ' Unclustered_candidate_TEs.fa | wc -l | sed 's/^ *//g' > denovo_names.txt  
awk '/^>/ {print $1;} ' Unclustered_candidate_TEs.fa | sed 's/>//g' | sed 's/^ *//g' >> temp_names.txt  

cat temp_names.txt | sort >> denovo_names.txt  
rm temp_names.txt  

blastn -subject Unclustered_candidate_TEs.fa -query Unclustered_candidate_TEs.fa \  
-out denovo_all_v_all.tab -evalue 0.001 -outfmt 6 -task blastn -max_target_seqs 1000  

awk '{if ($1 != $2 && $12 >= 100) print;}' denovo_all_v_all.tab > filtered_hits.tab  

./blast2MSP.pl filtered_hits.tab > MSP_denovo.out  

./RECON-1.08/scripts/recon.pl denovo_names.txt MSP_denovo.out 1  

awk '!/^#/ {print;}' eles | sed 's/\( \)*/\1/g' | cut -d' ' -f 2- > Clean_Eles.txt  

./RECON_cluster.py -i Unclustered_candidate_TEs.fa -e Clean_Eles.txt -d output_clusters  

mkdir mafftaligns  
for i in $(find output_clusters -name '*.fa' | sort);do  
base=$(basename $i)  
name="${base%.*}"  
mafft $i > 'mafftaligns/'$name'.aln'  
done  

mkdir consensus_fasta  
for i in $(find mafftaligns -name '*.aln' | sort);do  
base=$(basename $i)  
name="${base%.*}"  
cons -sequence $i -identity 0 -snucleotide1 -supper1 -name $name'_consensus' \  
-outseq 'consensus_fasta2/'$name'_consensus.fa' -auto  
done  

rm RECON_consensus.fa  
touch RECON_consensus.fa  
for x in $(find consensus_fasta -name '*.fa' | sort);do  
tr [:lower:] [:upper:] < $x >> RECON_consensus.fa  
done  

Usage: RECONcile [-h] -i INFASTA [-e ELES] [-d OUTDIR]

Extracts and orients TE frags belonging to RECON clusters.

Optional arguments:
  -h, --help        Show this help message and exit
  -i, --inFasta     Multi fasta containing all TE sequences.
  -e, --eles        Space delimited 'ele' file from RECON.
  -d, --outDir      Directory for new cluster files to be written to.