diff --git a/consensus_on_all_clusters.sh b/consensus_on_all_clusters.sh index b03fb939fb90b4f7f07ac7e4bb8fd694aeb3a8ac..5e5c4f4e8021eb41345cf504bb9d941e34f0069a 100755 --- a/consensus_on_all_clusters.sh +++ b/consensus_on_all_clusters.sh @@ -13,7 +13,7 @@ consensus_dir=$tests_dir/consensus_100k consensus_script="reads_consensus_class.py" start_primer="GTTCTACAGTCCGACGATCC" stop_primer="TTGGCACCCGAGAATTCCAC" -kmer_size="21" +kmer_size="15" #for file in "$clusters_dir"/*.fasta; do # cluster_name=$(basename -- "$file") @@ -31,18 +31,19 @@ sort $tests_dir/ref_sequences.txt > $tests_dir/sorted_ref_sequences.txt sort $tests_dir/consensus_sequences.txt > $tests_dir/sorted_consensus_sequences.txt -comm -12 $tests_dir/sorted_ref_sequences.txt $tests_dir/sorted_consensus_sequences.txt > $consensus_dir/correct_consensus.txt +comm -12 $tests_dir/sorted_ref_sequences.txt $tests_dir/sorted_consensus_sequences.txt > $consensus_dir/correct_consensus.txt # get the common sequences between ref and consensuses +num_consensuses=$(wc -l < $tests_dir/consensus_sequences.txt) num_common_sequences=$(wc -l < $consensus_dir/correct_consensus.txt) num_total_ref=$(wc -l < $tests_dir/ref_sequences.txt) rm $tests_dir/ref_sequences.txt $tests_dir/consensus_sequences.txt $tests_dir/sorted_ref_sequences.txt $tests_dir/sorted_consensus_sequences.txt -echo "number of correct consensuses found : $num_common_sequences out of a total of $num_total_ref referrences" +echo "consensuses found : $num_consensuses ; correct consensuses found : $num_common_sequences out of a total of $num_total_ref referrences" #-------------- Exit --------------# -echo "___END !___" +echo "______________ END ! ______________" exit 0