def compute_fasta_stats(formats, input_file, seqtype, priority):
MIN_LENGTH='MIN_LENGTH'
MAX_LENGTH='MAX_LENGTH'
NUMSEQ='NUMSEQ'
TOTAL_LENGTH='TOTAL_LENGTH'
AVG_LENGTH='AVG_LENGTH'
stats = {
MIN_LENGTH: 0,
MAX_LENGTH: 0,
NUMSEQ : 0,
TOTAL_LENGTH: 0,
AVG_LENGTH : 0
}
""" min length """
_MAX = 1000000000000
stats[MAX_LENGTH] = -(_MAX)
stats[MIN_LENGTH]= _MAX
fastareader= FastaReader(input_file)
""" process one fasta sequence at a time """
lengths_str=""
for record in fastareader:
seqname = record.name
seq = record.sequence
length = len(seq)
stats[NUMSEQ] += 1
stats[AVG_LENGTH] = stats[AVG_LENGTH] + length
if stats[MIN_LENGTH] > length:
stats[MIN_LENGTH] = length
if stats[MAX_LENGTH] < length:
stats[MAX_LENGTH] = length
if stats[NUMSEQ] > 0 :
stats[AVG_LENGTH] = stats[AVG_LENGTH]/stats[NUMSEQ]
else:
stats[AVG_LENGTH] = 0
# printf("%s\tNumber of sequences in input file BEFORE QC (%s)\t%s\n" %(str(priority), opts.seqtype, str(stats[NUMSEQ][BEFORE])) )
# printf("%s\tNumber of sequences AFTER QC (%s)\t%s\n" %(str(priority + 5), opts.seqtype, str(stats[NUMSEQ][AFTER])))
printf(formats %(str(priority + 5), str(stats[NUMSEQ])))
printf("%s\t-min length\t%s\n" %(str(priority + 6), str(stats[MIN_LENGTH])) )
printf("%s\t-avg length\t%s\n" %( str(priority + 7), str(int(stats[AVG_LENGTH]))))
printf("%s\t-max length\t%s\n" %( str(priority + 8), str(stats[MAX_LENGTH])) )
printf("%s\t-total base pairs (bp)\t%s\n" %( str(priority + 9), str(int(stats[AVG_LENGTH]* stats[NUMSEQ])) ))
def create_gff_faa(tempfile, gfffile, faafile):
patt = re.compile(r'>(.*)_(\d+)_(\d+)_([+-])')
idpatt = re.compile(r'.*_(\d+_\d+)')
with open(gfffile, 'w') as gffout:
with open(faafile, 'w') as faaout:
fastareader = FastaReader(tempfile)
for fasta in fastareader:
res=patt.search(fasta.name)
if res:
#nameprint(res.group(1),res.group(2), res.group(3), res.group(4))
orfname=res.group(1)
start=res.group(2)
end=res.group(3)
strand=res.group(4)
res=idpatt.search(orfname)
id=''
if res:
id=res.group(1)
attr = "ID=" + id + ";partial=00"
fields=[orfname, 'FGS+', 'CDS', start, end, '0', strand, "0", attr]
fprintf(faaout,'>' + orfname + "\n" + fasta.sequence+"\n")
fprintf(gffout,'\t'.join(fields) +'\n')
def countNoOfSequencesInFile(file):
fastareader = FastaReader(file)
count = 0
for record in fastareader:
count += 1
return count
def create_splits(outputdir,
listfilename,
input_filename,
maxMBytes,
maxSize,
splitPrefix='split',
splitSuffix=''):
maxBytes = 1024 * 1024 * maxMBytes
if splitSuffix:
suffix = '.' + splitSuffix
else:
suffix = ''
try:
if path.exists(listfilename):
listfile = open(listfilename, 'r')
listfilenames = [x.strip() for x in listfile.readlines()]
remove_files(outputdir, listfilenames)
listfile.close()
except IOError:
print "Cannot read file " + listfilename + " !"
sys.exit(0)
try:
listfile = open(listfilename, 'w')
except IOError:
print "Cannot read file " + listfilename + " !"
sys.exit(0)
fragments = []
seq_beg_pattern = re.compile(">")
splitno = 0
currblocksize = 0
currblockbyteSize = 0
fastareader = FastaReader(input_filename)
# Read sequences from sorted sequence file and write them to block files
for name in fastareader:
fragments.append(fastareader.seqname)
fragments.append(fastareader.sequence)
if currblocksize >= maxSize - 1 or currblockbyteSize >= maxBytes:
splitfile = open(
outputdir + PATHDELIM + splitPrefix + str(splitno) + suffix,
'w')
fprintf(splitfile, "%s", '\n'.join(fragments))
fragments = []
splitfile.close()
# Add this block name to the blocklistfile
fprintf(listfile, "%s\n", splitPrefix + str(splitno) + suffix)
splitno += 1
currblocksize = 0
currblockbyteSize = 0
else:
currblocksize += 1
currblockbyteSize += len(fastareader.sequence)
if fragments:
splitfile = open(
outputdir + PATHDELIM + splitPrefix + str(splitno) + suffix, 'w')
fprintf(splitfile, "%s", '\n'.join(fragments))
splitfile.close()
fragments = []
fprintf(listfile, "%s\n", splitPrefix + str(splitno) + suffix)
splitno += 1
#Add this block name to the blocklistfile
currblocksize = 0
currblockbyteSize = 0
listfile.close()
return True
def main(argv, errorlogger=None, runstatslogger=None):
global parser
(opts, args) = parser.parse_args(argv)
if not valid_arguments(opts, args):
print(usage)
sys.exit(0)
min_length = 0
#inputfile = open(opts.input_fasta,'r')
outfile = open(opts.output_fasta, 'w')
outfilefna = open(opts.output_fna, 'w')
outfilefaa = open(opts.output_faa, 'w')
outfilegff = open(opts.output_gff, 'w')
logfile = open(opts.log_file, 'w')
lengthsfile = open(opts.lengths_file, 'w')
if opts.map_file:
mapfile = open(opts.map_file, 'w')
else:
mapfile = None
sample_name = opts.input_fasta
sample_name = re.sub(r'^.*/', '', sample_name, re.I)
sample_name = re.sub(r'^.*\\', '', sample_name, re.I)
sample_name = re.sub(r'\.fasta$', '', sample_name, re.I)
sample_name = re.sub(r'\.fna$', '', sample_name, re.I)
sample_name = re.sub(r'\.faa$', '', sample_name, re.I)
sample_name = re.sub(r'\.fas$', '', sample_name, re.I)
sample_name = re.sub(r'\.fa$', '', sample_name, re.I)
BEFORE = 'BEFORE'
AFTER = 'AFTER'
NUMSEQ = "#INFO\tNumber of sequences :"
NUMSEQ_SHORTER = "@INFO\tNumber of sequences shorter than minimum length of sequences"
AVG_LENGTH = "@INFO\tAverage length of sequences:"
MIN_LENGTH = "@INFO\tMinimum length of sequences:"
MAX_LENGTH = "@INFO\tMaximum length of sequences:"
_MAX = 1000000000000
stats = {
MIN_LENGTH: {
'BEFORE': _MAX,
'AFTER': _MAX
},
MAX_LENGTH: {
'BEFORE': 0,
'AFTER': 0
},
NUMSEQ: {
'BEFORE': 0,
'AFTER': 0
},
NUMSEQ_SHORTER: {
'BEFORE': 0,
'AFTER': 0
},
AVG_LENGTH: {
'BEFORE': 0,
'AFTER': 0
},
}
length_distribution = {}
length_cumulative_distribution = {}
for i in range(0, 31):
length_distribution[i] = 0
length_cumulative_distribution[i] = 0
seq_count = 0
allNames = dict()
outputStr = ""
outputLines = []
fastareader = FastaReader(opts.input_fasta)
""" process one fasta sequence at a time """
lengths_str = ""
for record in fastareader:
seqname = record.name
seq = record.sequence
length = len(seq)
index = int(len(seq) / 50)
if index >= 30:
index = 30
length_distribution[index] += 1
if length < stats[MIN_LENGTH][BEFORE]:
stats[MIN_LENGTH][BEFORE] = length
if length > stats[MAX_LENGTH][BEFORE]:
stats[MAX_LENGTH][BEFORE] = length
if length < MIN_LENGTH:
stats[NUMSEQ_SHORTER][BEFORE] += 1
stats[AVG_LENGTH][BEFORE] = stats[AVG_LENGTH][BEFORE] + length
seqvalue = filter_sequence(seq)
stats[NUMSEQ][BEFORE] += 1
seqlen = len(seqvalue)
if seqlen >= min_length:
if len(lengths_str) > 100:
fprintf(lengthsfile, "%s\n", lengths_str)
lengths_str = str(seqlen)
else:
lengths_str += '\t' + str(seqlen)
stats[NUMSEQ][AFTER] += 1
stats[AVG_LENGTH][AFTER] = stats[AVG_LENGTH][AFTER] + seqlen
if mapfile == None:
fprintf(outfile, "%s\n", seqname)
else:
contigID = sample_name + '_' + str(seq_count)
orfID = sample_name + '_' + str(seq_count) + "_0"
fprintf(outfile, ">%s\n", contigID)
fprintf(outfilefna, ">%s\n", orfID)
fprintf(outfilefaa, ">%s\n", orfID)
gffString = sample_name + '_' + str(seq_count)
gffString += "\t" + "AMINO_ACID_SEQ"
gffString += "\t" + "CDS"
gffString += "\t" + "0"
gffString += "\t" + str(3 * seqlen)
gffString += "\t" + "0"
gffString += "\t" + "+"
gffString += "\t" + "0"
gffString += "\t" + "ID=" + orfID + ";"
gffString += "locus_tag=" + orfID + ";"
gffString += "partial=00;"
gffString += "orf_length=" + str(seqlen) + ";"
gffString += "contig_length=" + str(3 * seqlen)
fprintf(outfilegff, "%s\n", gffString)
key = re.sub(r'^>', '', seqname)
fprintf(
mapfile, "%s\n", sample_name + '_' + str(seq_count) +
'\t' + key + '\t' + str(seqlen))
seq_count += 1
fprintf(outfile, "%s\n", "DUMMY CONTIGS FOR AMINO ACID SEQUENCES")
fprintf(outfilefna, "%s\n", "DUMMY ORFS FOR AMINO ACID SEQUENCES")
fprintf(outfilefaa, "%s\n", seqvalue)
if seqlen < stats[MIN_LENGTH][AFTER]:
stats[MIN_LENGTH][AFTER] = seqlen
if seqlen > stats[MAX_LENGTH][AFTER]:
stats[MAX_LENGTH][AFTER] = seqlen
fprintf(lengthsfile, "%s\n", lengths_str)
if stats[NUMSEQ][BEFORE] > 0:
stats[AVG_LENGTH][
BEFORE] = stats[AVG_LENGTH][BEFORE] / stats[NUMSEQ][BEFORE]
else:
stats[AVG_LENGTH][BEFORE] = 0
if stats[NUMSEQ][AFTER] > 0:
stats[AVG_LENGTH][
AFTER] = stats[AVG_LENGTH][AFTER] / stats[NUMSEQ][AFTER]
else:
stats[AVG_LENGTH][AFTER] = 0
lengthsfile.close()
outfile.close()
outfilefna.close()
outfilefaa.close()
outfilegff.close()
#inputfile.close()
if mapfile != None:
mapfile.close()
""" min length """
if stats[MIN_LENGTH][BEFORE] == _MAX:
stats[MIN_LENGTH][BEFORE] = 0
if stats[MIN_LENGTH][AFTER] == _MAX:
stats[MIN_LENGTH][AFTER] = 0
fprintf(logfile, "@INFO\tBEFORE\tAFTER\n")
fprintf(
logfile, "%s\n", NUMSEQ + '\t' + str(stats[NUMSEQ][BEFORE]) + '\t' +
str(stats[NUMSEQ][AFTER]))
fprintf(
logfile, "%s\n",
NUMSEQ_SHORTER + '\t' + str(stats[NUMSEQ_SHORTER][BEFORE]) + '\t' +
str(stats[NUMSEQ_SHORTER][AFTER]))
fprintf(
logfile, "%s\n", AVG_LENGTH + '\t' + str(stats[AVG_LENGTH][BEFORE]) +
'\t' + str(stats[AVG_LENGTH][AFTER]))
fprintf(
logfile, "%s\n", MIN_LENGTH + '\t' + str(stats[MIN_LENGTH][BEFORE]) +
'\t' + str(stats[MIN_LENGTH][AFTER]))
fprintf(
logfile, "%s\n", MAX_LENGTH + '\t' + str(stats[MAX_LENGTH][BEFORE]) +
'\t' + str(stats[MAX_LENGTH][AFTER]))
fprintf(logfile, "@INFO\tLOW\tHIGH\tFREQUENCY\tCUMULATIVE_FREQUENCY\n")
# fprintf(logfile, "# ---\t-----\t--------\t---------\t----------\n");
i = 30
length_cumulative_distribution[i] = length_cumulative_distribution[i]
i -= 1
while i >= 0:
length_cumulative_distribution[i] = length_cumulative_distribution[
i + 1] + length_distribution[i]
i -= 1
for i in range(0, 31):
fprintf(logfile, " %s\n", str(i*50) + '\t' + str((i+1)*50) + '\t' +\
str(length_distribution[i]) +'\t' + str(length_cumulative_distribution[i]) )
logfile.close()
seqtype = 'amino'
"""priority is used to sort the output to print in the right order"""
priority = 2000
if runstatslogger != None:
runstatslogger.write(
"%s\tSequences BEFORE Filtering (%s)\t%s\n" %
(str(priority), seqtype, str(stats[NUMSEQ][BEFORE])))
runstatslogger.write(
"%s\tmin length\t%s\n" %
(str(priority + 1), str(stats[MIN_LENGTH][BEFORE])))
runstatslogger.write(
"%s\tavg length\t%s\n" %
(str(priority + 2), str(int(stats[AVG_LENGTH][BEFORE]))))
runstatslogger.write(
"%s\tmax length\t%s\n" %
(str(priority + 3), str(stats[MAX_LENGTH][BEFORE])))
runstatslogger.write(
"%s\ttot length\t%s\n" %
(str(priority + 4),
str(int(stats[AVG_LENGTH][BEFORE] * stats[NUMSEQ][BEFORE]))))
runstatslogger.write(
"%s\tSequences AFTER Filtering (%s)\t%s\n" %
(str(priority + 5), seqtype, str(stats[NUMSEQ][AFTER])))
runstatslogger.write(
"%s\tmin length\t%s\n" %
(str(priority + 6), str(stats[MIN_LENGTH][AFTER])))
runstatslogger.write(
"%s\tavg length\t%s\n" %
(str(priority + 7), str(int(stats[AVG_LENGTH][AFTER]))))
runstatslogger.write(
"%s\tmax length\t%s\n" %
(str(priority + 8), str(stats[MAX_LENGTH][AFTER])))
runstatslogger.write(
"%s\ttot length\t%s\n" %
(str(priority + 9),
str(int(stats[AVG_LENGTH][AFTER] * stats[NUMSEQ][AFTER]))))
def main(argv, errorlogger=None, runstatslogger=None):
global parser
global errorcode
(opts, args) = parser.parse_args(argv)
if not valid_arguments(opts, args):
print(usage)
sys.exit(0)
min_length = opts.min_length
outfile = open(opts.output_fasta + '.tmp', 'w')
logfile = open(opts.log_file, 'w')
lengthsfile = open(opts.lengths_file + '.tmp', 'w')
if opts.map_file:
mapfile = open(opts.map_file, 'w')
else:
mapfile = None
if opts.seqtype == 'nucleotide':
errorcode = 1
else:
errorcode = 3
sample_name = opts.input_fasta
sample_name = re.sub(r'^.*/', '', sample_name, re.I)
sample_name = re.sub(r'^.*\\', '', sample_name, re.I)
sample_name = re.sub(r'\.fasta$', '', sample_name, re.I)
sample_name = re.sub(r'\.fna$', '', sample_name, re.I)
sample_name = re.sub(r'\.faa$', '', sample_name, re.I)
sample_name = re.sub(r'\.fas$', '', sample_name, re.I)
sample_name = re.sub(r'\.fa$', '', sample_name, re.I)
BEFORE = 'BEFORE'
AFTER = 'AFTER'
NUMSEQ = "#INFO\tNumber of sequences :"
NUMSEQ_SHORTER = "@INFO\tNumber of sequences shorter than minimum length of sequences"
AVG_LENGTH = "@INFO\tAverage length of sequences:"
MIN_LENGTH = "@INFO\tMinimum length of sequences:"
MAX_LENGTH = "@INFO\tMaximum length of sequences:"
_MAX = 1000000000000
stats = {
MIN_LENGTH: {
'BEFORE': _MAX,
'AFTER': _MAX
},
MAX_LENGTH: {
'BEFORE': 0,
'AFTER': 0
},
NUMSEQ: {
'BEFORE': 0,
'AFTER': 0
},
NUMSEQ_SHORTER: {
'BEFORE': 0,
'AFTER': 0
},
AVG_LENGTH: {
'BEFORE': 0,
'AFTER': 0
},
}
length_distribution = {}
length_cumulative_distribution = {}
for i in range(0, 31):
length_distribution[i] = 0
length_cumulative_distribution[i] = 0
seq_count = 0
allNames = dict()
outputStr = ""
outputLines = []
print(opts.input_fasta)
fastareader = FastaReader(opts.input_fasta)
""" process one fasta sequence at a time """
lengths_str = ""
for record in fastareader:
seqname = record.name
seq = record.sequence
length = len(seq)
index = int(len(seq) / 50)
if index >= 30:
index = 30
length_distribution[index] += 1
if length < stats[MIN_LENGTH][BEFORE]:
stats[MIN_LENGTH][BEFORE] = length
if length > stats[MAX_LENGTH][BEFORE]:
stats[MAX_LENGTH][BEFORE] = length
if length < min_length:
stats[NUMSEQ_SHORTER][BEFORE] += 1
stats[AVG_LENGTH][BEFORE] = stats[AVG_LENGTH][BEFORE] + length
#stopped the filtering process seqvalue = filter_sequence(seq)
seqvalue = seq.upper()
stats[NUMSEQ][BEFORE] += 1
seqlen = len(seqvalue)
if seqlen >= min_length:
if len(lengths_str) > 100:
fprintf(lengthsfile, "%s\n", lengths_str)
lengths_str = str(seqlen)
else:
lengths_str += '\t' + str(seqlen)
stats[NUMSEQ][AFTER] += 1
stats[AVG_LENGTH][AFTER] = stats[AVG_LENGTH][AFTER] + seqlen
if mapfile == None:
fprintf(outfile, "%s\n", seqname)
else:
fprintf(outfile, ">%s\n", sample_name + '_' + str(seq_count))
key = re.sub(r'^>', '', seqname)
fprintf(
mapfile, "%s\n", sample_name + '_' + str(seq_count) +
'\t' + key + '\t' + str(seqlen))
seq_count += 1
fprintf(outfile, "%s\n", seqvalue)
if seqlen < stats[MIN_LENGTH][AFTER]:
stats[MIN_LENGTH][AFTER] = seqlen
if seqlen > stats[MAX_LENGTH][AFTER]:
stats[MAX_LENGTH][AFTER] = seqlen
fprintf(lengthsfile, "%s\n", lengths_str)
if stats[NUMSEQ][BEFORE] > 0:
stats[AVG_LENGTH][
BEFORE] = stats[AVG_LENGTH][BEFORE] / stats[NUMSEQ][BEFORE]
else:
stats[AVG_LENGTH][BEFORE] = 0
if stats[NUMSEQ][AFTER] > 0:
stats[AVG_LENGTH][
AFTER] = stats[AVG_LENGTH][AFTER] / stats[NUMSEQ][AFTER]
else:
stats[AVG_LENGTH][AFTER] = 0
lengthsfile.close()
outfile.close()
rename(opts.output_fasta + ".tmp", opts.output_fasta)
rename(opts.lengths_file + ".tmp", opts.lengths_file)
#inputfile.close()
if mapfile != None:
mapfile.close()
""" min length """
if stats[MIN_LENGTH][BEFORE] == _MAX:
stats[MIN_LENGTH][BEFORE] = 0
if stats[MIN_LENGTH][AFTER] == _MAX:
stats[MIN_LENGTH][AFTER] = 0
fprintf(logfile, "@INFO\tBEFORE\tAFTER\n")
fprintf(
logfile, "%s\n", NUMSEQ + '\t' + str(stats[NUMSEQ][BEFORE]) + '\t' +
str(stats[NUMSEQ][AFTER]))
fprintf(
logfile, "%s\n",
NUMSEQ_SHORTER + '\t' + str(stats[NUMSEQ_SHORTER][BEFORE]) + '\t' +
str(stats[NUMSEQ_SHORTER][AFTER]))
fprintf(
logfile, "%s\n", AVG_LENGTH + '\t' + str(stats[AVG_LENGTH][BEFORE]) +
'\t' + str(stats[AVG_LENGTH][AFTER]))
fprintf(
logfile, "%s\n", MIN_LENGTH + '\t' + str(stats[MIN_LENGTH][BEFORE]) +
'\t' + str(stats[MIN_LENGTH][AFTER]))
fprintf(
logfile, "%s\n", MAX_LENGTH + '\t' + str(stats[MAX_LENGTH][BEFORE]) +
'\t' + str(stats[MAX_LENGTH][AFTER]))
fprintf(logfile, "@INFO\tLOW\tHIGH\tFREQUENCY\tCUMULATIVE_FREQUENCY\n")
# fprintf(logfile, "# ---\t-----\t--------\t---------\t----------\n");
i = 30
length_cumulative_distribution[i] = length_cumulative_distribution[i]
i -= 1
while i >= 0:
length_cumulative_distribution[i] = length_cumulative_distribution[
i + 1] + length_distribution[i]
i -= 1
for i in range(0, 31):
fprintf(logfile, " %s\n", str(i*50) + '\t' + str((i+1)*50) + '\t' +\
str(length_distribution[i]) +'\t' + str(length_cumulative_distribution[i]) )
logfile.close()
if opts.seqtype == 'nucleotide':
priority = 1000
else:
priority = 2000
if runstatslogger != None:
if opts.seqtype == 'nucleotide':
runstatslogger.write(
"%s\tNumber of sequences in input file BEFORE QC (%s)\t%s\n" %
(str(priority), opts.seqtype, str(stats[NUMSEQ][BEFORE])))
runstatslogger.write(
"%s\t-min length\t%s\n" %
(str(priority + 1), str(stats[MIN_LENGTH][BEFORE])))
runstatslogger.write(
"%s\t-avg length\t%s\n" %
(str(priority + 2), str(int(stats[AVG_LENGTH][BEFORE]))))
runstatslogger.write(
"%s\t-max length\t%s\n" %
(str(priority + 3), str(stats[MAX_LENGTH][BEFORE])))
runstatslogger.write(
"%s\t-total base pairs (bp)\t%s\n" %
(str(priority + 4),
str(int(stats[AVG_LENGTH][BEFORE] * stats[NUMSEQ][BEFORE]))))
runstatslogger.write(
"%s\tNumber of sequences AFTER QC (%s)\t%s\n" %
(str(priority + 5), opts.seqtype, str(stats[NUMSEQ][AFTER])))
runstatslogger.write(
"%s\t-min length\t%s\n" %
(str(priority + 6), str(stats[MIN_LENGTH][AFTER])))
runstatslogger.write(
"%s\t-avg length\t%s\n" %
(str(priority + 7), str(int(stats[AVG_LENGTH][AFTER]))))
runstatslogger.write(
"%s\t-max length\t%s\n" %
(str(priority + 8), str(stats[MAX_LENGTH][AFTER])))
runstatslogger.write(
"%s\t-total base pairs (bp)\t%s\n" %
(str(priority + 9),
str(int(stats[AVG_LENGTH][AFTER] * stats[NUMSEQ][AFTER]))))
else:
runstatslogger.write(
"%s\tNumber of translated ORFs BEFORE QC (%s)\t%s\n" %
(str(priority), opts.seqtype, str(stats[NUMSEQ][BEFORE])))
runstatslogger.write(
"%s\t-min length\t%s\n" %
(str(priority + 1), str(stats[MIN_LENGTH][BEFORE])))
runstatslogger.write(
"%s\t-avg length\t%s\n" %
(str(priority + 2), str(int(stats[AVG_LENGTH][BEFORE]))))
runstatslogger.write(
"%s\t-max length\t%s\n" %
(str(priority + 3), str(stats[MAX_LENGTH][BEFORE])))
runstatslogger.write(
"%s\t-total base pairs (bp)\t%s\n" %
(str(priority + 4),
str(int(stats[AVG_LENGTH][BEFORE] * stats[NUMSEQ][BEFORE]))))
runstatslogger.write(
"%s\tNumber of tranlated ORFs AFTER QC (%s)\t%s\n" %
(str(priority + 5), opts.seqtype, str(stats[NUMSEQ][AFTER])))
runstatslogger.write(
"%s\t-min length\t%s\n" %
(str(priority + 6), str(stats[MIN_LENGTH][AFTER])))
runstatslogger.write(
"%s\t-avg length\t%s\n" %
(str(priority + 7), str(int(stats[AVG_LENGTH][AFTER]))))
runstatslogger.write(
"%s\t-max length\t%s\n" %
(str(priority + 8), str(stats[MAX_LENGTH][AFTER])))
runstatslogger.write(
"%s\t-total base pairs (bp)\t%s\n" %
(str(priority + 9),
str(int(stats[AVG_LENGTH][AFTER] * stats[NUMSEQ][AFTER]))))