def mean_emoji(filename):
# works for up to 500bp reads
means = np.zeros(500)
seq_count = 0
for r in SeqIO.parse(filename, "fastq"):
index = 0
for s in r.letter_annotations["phred_quality"]:
means[index] += s
index = index + 1
seq_count = seq_count + 1
cleaned = np.trim_zeros(means)
means_fp = cleaned / seq_count
fake_seq = ''.join(["a"] * len(means_fp.round()))
record = SeqRecord(Seq(fake_seq),
id="test",
name="mean scores",
description="example with mean fastq socres",
letter_annotations={
'phred_quality': list(means_fp.round().astype(int))
})
print("".join([
emojify(fastq_emoji_map[s])
for s in QualityIO._get_sanger_quality_str(record)
]))
def get_vcf_qual(quality):
'''Map a quality value to an emoji'''
# Hack to do this quickly - use same trick as FASTQE and convert from value to a PHRED encoding then map
#TODO make this better
#
if quality == None:
bioemojify_qual = emojify(":question:")
else:
fake_seq = 'N'
record_qual = SeqRecord(Seq(fake_seq), id="test", name="lookup",
description="example",
letter_annotations={'phred_quality': [int(quality)]})
mapping_dict_qual_use = emaps.fastq_emoji_map_binned
original_qual = QualityIO._get_sanger_quality_str(record_qual)
#print(original_qual)
bioemojify_qual = "".join([emojify(mapping_dict_qual_use.get(s, ":heart_eyes:")) for s in original_qual])
return(bioemojify_qual)
def map_scores(sequence,
mapping_dict=emaps.fastq_emoji_map,
default_value=":heart_eyes:",
mapping_function=emojify,
spacer=" "):
'''
:param sequence:
:param mapping_dict:
:param default_value:
:param mapping_function:
:param spacer:
:return:
'''
mapped_values = spacer.join([
mapping_function(mapping_dict.get(s, default_value))
for s in QualityIO._get_sanger_quality_str(sequence)
])
return (mapped_values)
def convert_fastq(options):
'''Convert FASTQ file to emoji. If no FASTQ files are specified on the command line then
read from the standard input (stdin).
Arguments:
options: the command line options of the program
Result:
None
'''
if options.custom:
with open(options.custom) as f:
mapping_dict_use = ast.literal_eval(f.read())
else:
mapping_dict_use = local_seq_emoji_map
if options.custom_qual:
with open(options.custom_qual) as f:
mapping_dict_qual_use = ast.literal_eval(f.read())
elif options.bin:
mapping_dict_qual_use = emaps.fastq_emoji_map_binned
else:
mapping_dict_qual_use = emaps.fastq_emoji_map
if options.fastq_files:
for fastq_filename in options.fastq_files:
logging.info("Processing FASTA file from %s", fastq_filename)
try:
if fastq_filename.endswith(".gz"):
fastq_file = gzip.open(fastq_filename, 'rt')
else:
fastq_file = open(fastq_filename)
except IOError as exception:
exit_with_error(str(exception), EXIT_FILE_IO_ERROR)
else:
with fastq_file:
for seq in SeqIO.parse(fastq_file, "fastq"):
print(emojify(":arrow_forward:")+" "+seq.id)
#print(">"+seq.id)
original = seq.seq
bioemojify = "".join([emojify(mapping_dict_use.get(s,":heart_eyes:")) for s in original])
original_qual = QualityIO._get_sanger_quality_str(seq)
bioemojify_qual = "".join([emojify(mapping_dict_qual_use.get(s,":heart_eyes:")) for s in original_qual])
print(bioemojify+"\n"+bioemojify_qual)
# print(*zip([a for a in bioemojify if a != " "],[b for b in bioemojify_qual if b != " "]))
else:
logging.info("Processing FASTQ file from stdin")
#stats = FastaStats().from_file(sys.stdin, options.minlen)
if (binascii.hexlify(sys.stdin.buffer.peek(1)[:2]) == b'1f8b'):
# print("zipped")
stdin_file = gzip.open(sys.stdin.buffer, 'rt')
else:
stdin_file = sys.stdin
for seq in SeqIO.parse(stdin_file, "fastq"):
print(emojify(":arrow_forward:")+" "+seq.id)
#print(">"+seq.id)
original = seq.seq
bioemojify = "".join([emojify(mapping_dict_use.get(s,":heart_eyes:")) for s in original])
original_qual = QualityIO._get_sanger_quality_str(seq)
bioemojify_qual = "".join([emojify(mapping_dict_qual_use.get(s,":heart_eyes:")) for s in original_qual])
print(bioemojify+"\n"+bioemojify_qual)
def process_files(options):
'''Compute and print FastaStats for each input FASTA file specified on the
command line. If no FASTA files are specified on the command line then
read from the standard input (stdin).
Arguments:
options: the command line options of the program
Result:
None
'''
if options.fasta_files:
for fasta_filename in options.fasta_files:
logging.info(
"Processing FASTA file from {}".format(fasta_filename))
try:
fasta_file = open(fasta_filename)
except IOError as exception:
exit_with_error(str(exception), EXIT_FILE_IO_ERROR)
else:
with fasta_file:
stats = FastaStats().from_file(fasta_file, options.minlen)
#print(stats.pretty(fasta_filename))
if options.scale:
print_scale(emaps.all_qualities, options.bin)
#rewrite this
if options.bin:
logging.info("Binned calculations")
if options.max:
logging.info("Calculate max quality per position")
print(
stats.pretty(fasta_filename),
"max (binned)",
" ".join([
emojify(
emaps.fastq_emoji_map_binned.get(
s, ':heart_eyes:'))
for s in QualityIO._get_sanger_quality_str(
stats.quality_scores_maxs)
]),
sep='\t')
logging.info("Calculate mean quality per position")
print(stats.pretty(fasta_filename),
"mean (binned)",
" ".join([
emojify(
emaps.fastq_emoji_map_binned.get(
s, ':heart_eyes:'))
for s in QualityIO._get_sanger_quality_str(
stats.quality_scores_mean)
]),
sep='\t')
if options.min:
logging.info("Calculate min quality per position")
print(
stats.pretty(fasta_filename),
"min (binned)",
" ".join([
emojify(
emaps.fastq_emoji_map_binned.get(
s, ':heart_eyes:'))
for s in QualityIO._get_sanger_quality_str(
stats.quality_scores_mins)
]),
sep='\t')
else:
if options.max:
logging.info("Calculate max quality per position")
print(
stats.pretty(fasta_filename),
"max",
" ".join([
emojify(
emaps.fastq_emoji_map.get(
s, ':heart_eyes:'))
for s in QualityIO._get_sanger_quality_str(
stats.quality_scores_maxs)
]),
sep='\t')
logging.info("Calculate mean quality per position")
print(stats.pretty(fasta_filename),
"mean",
" ".join([
emojify(
emaps.fastq_emoji_map.get(
s, ':heart_eyes:'))
for s in QualityIO._get_sanger_quality_str(
stats.quality_scores_mean)
]),
sep='\t')
if options.min:
logging.info("Calculate min quality per position")
print(
stats.pretty(fasta_filename),
"min",
" ".join([
emojify(
emaps.fastq_emoji_map.get(
s, ':heart_eyes:'))
for s in QualityIO._get_sanger_quality_str(
stats.quality_scores_mins)
]),
sep='\t')
#print("MAX: "," ".join([s for s in QualityIO._get_sanger_quality_str(stats.quality_scores_maxs)]))
#print("MEAN: "," ".join([s for s in QualityIO._get_sanger_quality_str(stats.quality_scores_mean)]))
#print("MIN: "," ".join([s for s in QualityIO._get_sanger_quality_str(stats.quality_scores_mins)]))
else:
logging.info("Processing FASTA file from stdin")
stats = FastaStats().from_file(sys.stdin, options.minlen)
print(stats.pretty("stdin"))
return read
totreads = 0
passing_reads = 0
while True:
try:
read = R1.next()
read2 = R2.next()
totreads += 1
except StopIteration:
break
fil1 = filterSeq(read, 0.1, 10, 100)
fil2 = filterSeq(read2, 0.1, 10, 100)
if (fil1 != None) and (fil2 != None):
sys.stdout.write(fil1.id + "\t" + str(fil1.seq) + "\t" +
str(fil2.seq) + "\t" +
QualityIO._get_sanger_quality_str(fil1) + "\t" +
QualityIO._get_sanger_quality_str(fil2) + "\n")
passing_reads += 1
elif (fil1 != None):
SeqIO.write(fil1, out, "fastq")
elif (fil2 != None):
SeqIO.write(fil2, out, "fastq")
sys.stderr.write("\t" + str(passing_reads) + " out of " + str(totreads) +
" fragments passed the filtering" + "\n")
data = commands.getstatusoutput('date')
sys.stderr.write("2nd step: filtering out duplicated fragments at " + data[1] +
"\n")
