if len(args) != 1:
usage()
sys.exit(2)
basename = goby.Alignments.get_basename(args[0])
print "Compact Alignment basename =", basename
alignment_reader = AlignmentReader(basename, verbose)
header = alignment_reader.header
tmh_reader = TooManyHitsReader(basename, verbose)
tmh = tmh_reader.tmh
entries_filesize = os.stat(basename + ".entries")[stat.ST_SIZE]
print "Info from header:"
print "Sorted:", header.sorted
print "Indexed: ", header.indexed
print "Number of target sequences = %s" % commify(header.number_of_targets)
# target length stats
target_length = len(header.target_length)
if target_length > 0:
min_target_length = min(header.target_length)
max_target_length = max(header.target_length)
mean_target_length = sum(header.target_length) / float(target_length)
else:
min_target_length = 0
max_target_length = 0
mean_target_length = 0
print "Number of target length entries = %s" % commify(target_length)
print "Min target length = %s" % commify(min_target_length)
print "Max target length = %s" % commify(max_target_length)
number_of_identifiers += 1
if entry.HasField("description"):
number_of_descriptions += 1
if entry.HasField("sequence"):
number_of_sequences += 1
if entry.HasField("sequence_pair"):
number_of_sequences_pairs += 1
if entry.HasField("quality_scores"):
number_of_quality_scores += 1
if entry.HasField("quality_scores_pair"):
number_of_quality_score_pairs += 1
min_read_length = min(min_read_length, read_length)
max_read_length = max(max_read_length, read_length)
print "Average bytes per entry: %s" % commify(filesize / float(number_of_entries))
print "Average bytes per base: %s" % commify(filesize / float(total_read_length))
print "Has identifiers = %s (%s)" % (number_of_identifiers > 0, commify(number_of_identifiers))
print "Has descriptions = %s (%s)" % (number_of_descriptions > 0, commify(number_of_descriptions))
print "Has sequences = %s (%s)" % (number_of_sequences > 0, commify(number_of_sequences))
print "Has sequence pairs = %s (%s)" % (number_of_sequence_pairs > 0, commify(number_of_sequence_pairs))
print "Has quality scores = %s (%s)" % (number_of_quality_scores > 0, commify(number_of_quality_scores))
print "Has quality score pairs = %s (%s)" % (number_of_quality_score_pairs > 0, commify(number_of_quality_score_pairs))
print "Number of entries = %s" % commify(number_of_entries)
print "Min read length = %s" % commify(min_read_length)
print "Max read length = %s" % commify(max_read_length)
print "Avg read length = %s" % commify(total_read_length / float(number_of_entries))
print "Avg read pair length = %s" % commify(total_read_length_pair / float(number_of_entries))
if __name__ == "__main__":
main()
number_of_identifiers += 1
if entry.HasField("description"):
number_of_descriptions += 1
if entry.HasField("sequence"):
number_of_sequences += 1
if entry.HasField("sequence_pair"):
number_of_sequences_pairs += 1
if entry.HasField("quality_scores"):
number_of_quality_scores += 1
if entry.HasField("quality_scores_pair"):
number_of_quality_score_pairs += 1
min_read_length = min(min_read_length, read_length)
max_read_length = max(max_read_length, read_length)
print "Average bytes per entry: %s" % commify(
filesize / float(number_of_entries))
print "Average bytes per base: %s" % commify(
filesize / float(total_read_length))
print "Has identifiers = %s (%s)" % (number_of_identifiers > 0,
commify(number_of_identifiers))
print "Has descriptions = %s (%s)" % (number_of_descriptions > 0,
commify(number_of_descriptions))
print "Has sequences = %s (%s)" % (number_of_sequences > 0,
commify(number_of_sequences))
print "Has sequence pairs = %s (%s)" % (number_of_sequence_pairs > 0,
commify(number_of_sequence_pairs))
print "Has quality scores = %s (%s)" % (number_of_quality_scores > 0,
commify(number_of_quality_scores))
print "Has quality score pairs = %s (%s)" % (
number_of_quality_score_pairs > 0,
commify(number_of_quality_score_pairs))
