module Fl2Stats
# -------------------------------------------------------------------------------- Main
def summary_stats
stats_file = File.open('fl2_results/summary_stats.txt', 'w')
total_seqs = 0
num1 = annotation_stats(stats_file)
num2 = testcode_stats(stats_file)
total_seqs = num1 + num2
stats_file.puts "\nInput sequences in your fasta: #{total_seqs}\n\n"
end
# ---------------------------------------------------------------------------------- Functions
def stats_my_db(db_name, array)
if (db_name !~ /^sp_/) && (db_name !~ /^tr_/)
array[1] += 1
elsif (db_name =~ /^sp_/)
array[2] += 1
elsif (db_name =~ /^tr_/)
array[3] += 1
end
return array
end
def annotation_stats(stats_file)
seqs_number = 0
array_of_all_accs = []
array_of_complete_accs = []
error_1_num = 0
seqs_longer_200 = 0
seqs_shorter_200 = 0
complete_longer_200 = 0
complete_shorter_200 = 0
seqs_longer_500 = 0
seqs_shorter_500 = 0
complete_longer_500 = 0
complete_shorter_500 = 0
complete = [0,0,0,0]
putative_complete = [0,0,0,0]
c_terminus = [0,0,0,0]
putative_c_terminus = [0,0,0,0]
n_terminus = [0,0,0,0]
putative_n_terminus = [0,0,0,0]
internal = [0,0,0,0]
cod_seq = [0,0,0,0]
File.open('fl2_results/annotations.txt').each do |line|
line.chomp!
(name,fasta_length,acc,db_name,status,kk1,kk2,kk3,kk4,kk5,msgs) = line.split("\t")
if (line !~ /^Query_id\t/)
seqs_number += 1
array_of_all_accs.push acc
# -------------------------------------------------------------------------
if (fasta_length.to_i >= 200)
seqs_longer_200 += 1
else
seqs_shorter_200 += 1
end
if (fasta_length.to_i >= 500)
seqs_longer_500 += 1
else
seqs_shorter_500 += 1
end
# -------------------------------------------------------------------------
if (msgs =~ /ERROR#1/)
error_1_num += 1
end
# -------------------------------------------------------------------------
if (status == 'Complete')
complete[0] += 1
array_of_complete_accs.push acc
complete = stats_my_db(db_name, complete)
if (fasta_length.to_i >= 200)
complete_longer_200 += 1
else
complete_shorter_200 += 1
end
if (fasta_length.to_i >= 500)
complete_longer_500 += 1
else
complete_shorter_500 += 1
end
elsif (status == 'Putative Complete')
putative_complete[0] += 1
putative_complete = stats_my_db(db_name, putative_complete)
elsif (status == 'C-terminus')
c_terminus[0] += 1
c_terminus = stats_my_db(db_name, c_terminus)
elsif (status == 'N-terminus')
n_terminus[0] += 1
n_terminus = stats_my_db(db_name, n_terminus)
elsif (status == 'Putative C-terminus')
putative_c_terminus[0] += 1
putative_c_terminus = stats_my_db(db_name, putative_c_terminus)
elsif (status == 'Putative N-terminus')
putative_n_terminus[0] += 1
putative_n_terminus = stats_my_db(db_name, putative_n_terminus)
elsif (status == 'Internal')
internal[0] += 1
internal = stats_my_db(db_name, internal)
elsif (status == 'Coding Seq')
cod_seq[0] += 1
cod_seq = stats_my_db(db_name, cod_seq)
end
# -------------------------------------------------------------------------
end
end
stats_file.puts "--- Annotation Summary ---"
stats_file.puts "\n------------------------------ Summary of sequences found by similarity -----"
stats_file.puts "\n\tSequences found: #{seqs_number}\t\t(>200: #{seqs_longer_200}, <200: #{seqs_shorter_200})\t(>500: #{seqs_longer_500}, <500: #{seqs_shorter_500})"
stats_file.puts "\tDifferent IDs: #{array_of_all_accs.uniq.count}"
stats_file.puts "\n\tsequences with sense and antisense hits error: #{error_1_num}"
stats_file.puts "\n------------------------------------------------- Full-Length Sequences -----"
stats_file.puts "\tComplete Seqs: #{complete[0]} ("+ '%.3f' % (complete[0].to_f/seqs_number.to_f*100) +" %)\t\t(>200: #{complete_longer_200}, <200: #{complete_shorter_200})\t(>500: #{complete_longer_500}, <500: #{complete_shorter_500})"
stats_file.puts "\tDifferent IDs: #{array_of_complete_accs.uniq.count} ("+ '%.3f' % (array_of_complete_accs.uniq.count.to_f/seqs_number.to_f*100) +" %)"
stats_file.puts "\n\t\tuser_db: #{complete[1]}\n\t\tsp: #{complete[2]}\n\t\ttr: #{complete[3]}"
stats_file.puts "-----------------------------------------------------------------------------"
stats_file.puts "\n\tputative completes: #{putative_complete[0]}\n\t\tuser_db: #{putative_complete[1]}\n\t\tsp: #{putative_complete[2]}\n\t\ttr: #{putative_complete[3]}"
stats_file.puts "\n\tn-terminus: #{n_terminus[0]}\n\t\tuser_db: #{n_terminus[1]}\n\t\tsp: #{n_terminus[2]}\n\t\ttr: #{n_terminus[3]}"
stats_file.puts "\n\tputative_n_terminus: #{putative_n_terminus[0]}\n\t\tuser_db: #{putative_n_terminus[1]}\n\t\tsp: #{putative_n_terminus[2]}\n\t\ttr: #{putative_n_terminus[3]}"
stats_file.puts "\n\tc-terminus: #{c_terminus[0]}\n\t\tuser_db: #{c_terminus[1]}\n\t\tsp: #{c_terminus[2]}\n\t\ttr: #{c_terminus[3]}"
stats_file.puts "\n\tputative_c_terminus: #{putative_c_terminus[0]}\n\t\tuser_db: #{putative_c_terminus[1]}\n\t\tsp: #{putative_c_terminus[2]}\n\t\ttr: #{putative_c_terminus[3]}"
stats_file.puts "\n\tinternal: #{internal[0]}\n\t\tuser_db: #{internal[1]}\n\t\tsp: #{internal[2]}\n\t\ttr: #{internal[3]}"
stats_file.puts "\n\tcoding sequences with unknown status: #{cod_seq[0]}\n\t\tuser_db: #{cod_seq[1]}\n\t\tsp: #{cod_seq[2]}\n\t\ttr: #{cod_seq[3]}"
return seqs_number
end
def testcode_stats(stats_file)
seqs_number = 0
coding = 0
putative_coding = 0
unknown = 0
coding_longer_200 = 0
coding_shorter_200 = 0
unknown_longer_200 = 0
unknown_shorter_200 = 0
coding_longer_500 = 0
coding_shorter_500 = 0
unknown_longer_500 = 0
unknown_shorter_500 = 0
File.open('fl2_results/tcode_result.txt').each do |line|
line.chomp!
(name,fasta_length,acc,db_name,status) = line.split("\t")
if (line !~ /^Query_id\t/)
seqs_number += 1
if (status == 'coding')
coding += 1
if (fasta_length.to_i >= 200)
coding_longer_200 += 1
coding_longer_500 += 1
else
coding_shorter_200 += 1
coding_shorter_500 += 1
end
elsif (status == 'putative_coding')
putative_coding += 1
elsif (status == 'unknown')
unknown += 1
if (fasta_length.to_i >= 200)
unknown_longer_200 += 1
unknown_longer_500 += 1
else
unknown_shorter_200 += 1
unknown_shorter_500 += 1
end
end
end
end
stats_file.puts "\n--------------------------- Test Code Summary\n\n\ttotal seqs: #{seqs_number}"
stats_file.puts "\n\tcoding sequences: #{coding}"
stats_file.puts "\t\tlonger than 200 bp: #{coding_longer_200}"
stats_file.puts "\t\tshorter than 200 bp: #{coding_shorter_200}"
stats_file.puts "\t\tlonger than 500 bp: #{coding_longer_500}"
stats_file.puts "\t\tshorter than 500 bp: #{coding_shorter_500}"
stats_file.puts "\n\tputative coding sequences: #{putative_coding}\n"
stats_file.puts "\n\tunknown: #{unknown} ("+ '%.3f' % (unknown.to_f/seqs_number.to_f*100) +" %)"
stats_file.puts "\t\tlonger than 200 bp: #{unknown_longer_200}"
stats_file.puts "\t\tshorter than 200 bp: #{unknown_shorter_200}"
stats_file.puts "\t\tlonger than 500 bp: #{unknown_longer_500}"
stats_file.puts "\t\tshorter than 500 bp: #{unknown_shorter_500}"
stats_file.puts "\n\tUnknown sequences have a bad test code score or haven't got an ORF longer than 200 nt"
stats_file.puts "---------------------------------------------"
return seqs_number
end
end