def print_flanking_regions_to_fasta(flanking_region_count_list, outfile, convert_counts=lambda x: x):
""" Given a (seq,count) list, make fasta file with the each seq present convert_counts(count) times. """
with open(outfile, "w") as OUTFILE:
for N, (seq, count) in enumerate(flanking_region_count_list):
seqname = "%s (%s reads)" % (N, count)
for _ in range(convert_counts(count)):
write_fasta_line(seqname, seq, OUTFILE)
def categorize_reads_print_to_files(readname_to_aln_list, UNALIGNED_FILE, CASSETTE_FILE, MULTIPLE_GENOMIC_FILE,
GENOMIC_UNIQUE_FILE, unaligned_as_fasta=True, multiple_to_write=-1,
input_collapsed_to_unique=False, no_warnings=False):
""" Decide the proper category for each read, write to appropriate output file; return category counts.
Categories: unaligned, cassette (one or more cassette alignments - print warning if multiple),
genomic-unique (single non-cassette alignment), multiple-genomic (multiple non-cassette alignments.
If input_collapsed_to_unique, for the purpose of category counts each read will be counted as N reads,
with N determined from readname using the fastx-collapser encoding.
In the output category counts, cassette-multiple is a special subcategory - anything in it is also counted in cassette.
Each read is printed to the appropriate outfile (all outfiles should be open file handles);
for multiple-genomic, multiple_to_write lines will be written; if unaligned_as_fasta, unaligned reads
will be written as fasta instead of SAM format (and so will multiple-genomic if multiple_to_write is 0).
"""
category_readcounts = {'unaligned':0, 'cassette':0, 'multiple-genomic':0, 'genomic-unique':0, 'cassette-multiple':0}
for readname,aln_list in sorted(readname_to_aln_list.items()):
readcount = 1 if not input_collapsed_to_unique else get_seq_count_from_collapsed_header(readname)
# if there's a single alignment, it's unaligned, cassette or genomic-unique
if len(aln_list) == 1:
aln = aln_list[0]
if not aln.aligned:
category_readcounts['unaligned'] += readcount
if unaligned_as_fasta: write_fasta_line(readname, aln.read.seq, UNALIGNED_FILE)
else: write_SAM_line_from_HTSeq_aln(aln, UNALIGNED_FILE)
elif is_cassette_chromosome(aln.iv.chrom):
category_readcounts['cassette'] += readcount
write_SAM_line_from_HTSeq_aln(aln, CASSETTE_FILE)
else:
category_readcounts['genomic-unique'] += readcount
write_SAM_line_from_HTSeq_aln(aln, GENOMIC_UNIQUE_FILE)
# if there are multiple alignments, it's cassette-multiple (weird!) or multiple-genomic
else:
assert all([aln.aligned for aln in aln_list]), "Shouldn't see multiple unaligned lines per read!"
# multiple-cassette - shouldn't really happen, but write to CASSETTE_FILE
# MAYBE-TODO come up with something better to do for multiple-cassette cases? If they ever happen.
if any([is_cassette_chromosome(aln.iv.chrom) for aln in aln_list]):
assert all([is_cassette_chromosome(aln.iv.chrom) for aln in aln_list]), "Mixed cassette/other!"
category_readcounts['cassette'] += readcount
if not no_warnings:
print "Warning: multiple cassette alignments! Printing all to cassette file.\n\t%s"%(aln_list)
category_readcounts['cassette-multiple'] += readcount
for aln in aln_list:
write_SAM_line_from_HTSeq_aln(aln, CASSETTE_FILE)
# multiple genomic alignments - how many get written depends on multiple_to_write;
# if it's 0, the outfile should be fasta, or else I guess it should be written as unaligned?
# (MAYBE-TODO writing single multiple as unaligned not implemented!)
else:
category_readcounts['multiple-genomic'] += readcount
if multiple_to_write == 0:
if unaligned_as_fasta:
write_fasta_line(readname, aln_list[0].read.seq, MULTIPLE_GENOMIC_FILE)
else:
raise Exception("Writing 0 multiple alignments in SAM format NOT IMPLEMENTED!")
else:
for aln in aln_list[:multiple_to_write]:
write_SAM_line_from_HTSeq_aln(aln, MULTIPLE_GENOMIC_FILE)
return category_readcounts
def _trim_prefix_single(seqname, seq, prefix_bases, TRIMMED_OUTFILE, WRONG_PREFIX_OUTFILE=None):
""" If prefix_bases is a prefix of seq, trim it off, print to TRIMMED_OUTFILE, return 1;
otherwise print to WRONG_PREFIX_OUTFILE if not None, return 0.
"""
if seq.upper().startswith(prefix_bases.upper()):
seq_trimmed = seq[len(prefix_bases):]
# some fastx_toolkit tools give errors on lowercase bases, so make everything uppercase
write_fasta_line(seqname, seq_trimmed.upper(), TRIMMED_OUTFILE)
return 1
else:
if WRONG_PREFIX_OUTFILE is not None:
# some fastx_toolkit tools give errors on lowercase bases, so make everything uppercase
write_fasta_line(seqname, seq.upper(), WRONG_PREFIX_OUTFILE)
return 0
def _trim_prefix_single(seqname,
seq,
prefix_bases,
TRIMMED_OUTFILE,
WRONG_PREFIX_OUTFILE=None):
""" If prefix_bases is a prefix of seq, trim it off, print to TRIMMED_OUTFILE, return 1;
otherwise print to WRONG_PREFIX_OUTFILE if not None, return 0.
"""
if seq.upper().startswith(prefix_bases.upper()):
seq_trimmed = seq[len(prefix_bases):]
# some fastx_toolkit tools give errors on lowercase bases, so make everything uppercase
write_fasta_line(seqname, seq_trimmed.upper(), TRIMMED_OUTFILE)
return 1
else:
if WRONG_PREFIX_OUTFILE is not None:
# some fastx_toolkit tools give errors on lowercase bases, so make everything uppercase
write_fasta_line(seqname, seq.upper(), WRONG_PREFIX_OUTFILE)
return 0
def main(args, options):
""" Run the main functionality of the module (see module docstring for more information), excluding testing.
The options argument should be generated by an optparse parser.
"""
try:
[infile] = args
except ValueError:
parser = define_option_parser()
parser.print_help()
sys.exit("Error: exactly one infile required!")
# MAYBE-TODO implement option with multiple infiles? Need to make sure they're the same fa/fq type etc...
### check inputs
adapter_options = '-a --adapter -b --anywhere -g --front'
if any([x in options.other_cutadapt_options for x in adapter_options.split()]):
sys.exit("Error: --other_cutadapt_options value shouldn't contain any adapter seq options (%s)"%adapter_options
+" - use -5/-3 options to specify adapters instead!")
### outfile and tmpfile names
infile_suffix = os.path.splitext(infile)[1]
outfile_suffix = '.fa'
#outfile_suffix = '.fa' if options.collapse_to_unique else infile_suffix
ends = "5' 3'".split()
outfiles = {end: options.outfile_basename + '_%s.fa'%end.replace("'","prime") for end in ends}
infofile = options.outfile_basename + '_info.txt'
wrong_start_file = options.outfile_basename + '_wrong-start.fa'
no_cassette_tmpfiles = {end: options.outfile_basename + '_no-cassette-tmpfile_%s.fa'%end.replace("'","prime") for end in ends}
no_cassette_file = options.outfile_basename + '_no-cassette.fa'
trimmed_tmpfile = trimmed_tmpfile_original = options.outfile_basename + '_trimmed-tmpfile.fa'
cutadapt_tmpfiles = {end: options.outfile_basename + '_cutadapt-tmpfile_%s.fa'%end.replace("'","prime") for end in ends}
cutadapt_tmpfiles_original = cutadapt_tmpfiles
with open(infofile,'w') as INFOFILE:
### write header data
write_header_data(INFOFILE,options)
INFOFILE.write('\n')
### 0. look at the infile; make sure it's readable, etc
# (check_readcount uses seq_count_and_lengths, which uses HTSeq and autodetects fa/fq format)
starting_readcount = check_readcount(infile, INFOFILE, bool(options.verbosity>1), "original input",
options.total_read_number_only, False)
### 1. Trim the first bases (from adapter)
# MAYBE-TODO I could do this with cutadapt again, instead of with my own trim_prefix function...
# Would that be faster, or better in any other way?
# MAYBE-TODO could also do it with a multiplexing barcode-splitting tool (like fastx_barcode_splitter.pl),
# since that's the eventual point of having those constant first bases there...
if options.first_bases_to_trim == 'NONE':
text = "### Not trimming first bases, since NONE was passed to -F option.\n"
if options.verbosity>0: print text
INFOFILE.write(text+'\n')
trimmed_tmpfile = infile
trimmed_readcount = starting_readcount
untrimmed_readcount = 0
else:
trim_prefix(options.first_bases_to_trim, infile, trimmed_tmpfile, wrong_start_file, INFOFILE, options.verbosity)
trimmed_readcount = check_readcount(trimmed_tmpfile, INFOFILE, bool(options.verbosity>1),
"first-base-trimming output", options.total_read_number_only, False)
untrimmed_readcount = check_readcount(wrong_start_file, None, False, True, False)
assert trimmed_readcount+untrimmed_readcount==starting_readcount,\
"Trimmed/untrimmed readcounts don't add up to starting readcount - check tmpfile!"\
+"(%s+%s != %s)"%(trimmed_readcount, untrimmed_readcount, starting_readcount)
### 2. run cutadapt to strip cassette sequence
# NOTE: this currently requires my version of cutadapt, cutadapt_mod (based on some older cutadapt version),
# to deal with too-long seqs correctly - LATER-TODO submit my modification as a patch to cutadapt to get it in the
# standard install! Or wait until the cutadapt maintainer does it (I submitted it as an issue)
# (see ~/experiments/basic_programs/cutadapt_modifications/).
if_running_cutadapt = True
if options.other_cutadapt_options == 'NONE':
if_running_cutadapt = False
text = "### Not running cutadapt, since NONE was passed to -A option.\n"
elif not (options.adapter_5prime or options.adapter_3prime):
if_running_cutadapt = False
text = "### Not running cutadapt, since empty sequences were passed to -5 and -3 options.\n"
# if not running it, just skip it
if not if_running_cutadapt:
if options.verbosity>0: print text
INFOFILE.write(text+'\n')
cutadapt_tmpfile = trimmed_tmpfile
cutadapt_readcount = {'all': trimmed_readcount}
no_cassette_readcount = 0
# otherwise run the 5' and 3' ends separately
else:
cutadapt_readcount = {}
for (end_type, adapter_seq) in [("5'", options.adapter_5prime), ("3'", options.adapter_3prime)]:
assert end_type in ends
# if the adapter sequence for that side is empty, skip
if not adapter_seq.replace('"','').replace("'",'').replace(' ',''): continue
cutadapt_tmpfile = cutadapt_tmpfiles[end_type]
full_cutadapt_options = '-a %s %s'%(adapter_seq, options.other_cutadapt_options)
for extra_seq_category in ('untrimmed', 'too-short', 'too-long'):
if not extra_seq_category in full_cutadapt_options:
full_cutadapt_options += ' --%s-output %s'%(extra_seq_category, no_cassette_tmpfiles[end_type])
command = "cutadapt_mod %s -o %s %s"%(full_cutadapt_options, cutadapt_tmpfile, trimmed_tmpfile)
run_command_print_info_output(command, INFOFILE, options.verbosity, shell=True,
program_name="cutadapt for %s"%end_type)
cutadapt_readcount[end_type] = check_readcount(cutadapt_tmpfile, INFOFILE, bool(options.verbosity>1),
"cutadapt output", options.total_read_number_only, False)
tmp_no_cassette_readcount = check_readcount(no_cassette_tmpfiles[end_type], None, False, True, False)
assert cutadapt_readcount[end_type] + tmp_no_cassette_readcount == trimmed_readcount,\
"%s cassette/no-cassette readcounts don't add up to trimmed readcount - check tmpfile!"\
+"(%s+%s != %s)"%(end_type, cutadapt_readcount[end_type], tmp_no_cassette_readcount, trimmed_readcount)
# make an actual no_cassette_file based on the overlap of the two no_cassette_tmpfiles!
text = "### Merging the 5' and 3' cutadapt untrimmed outputs to get single no-cassette file.\n"
if options.verbosity>0: print text
INFOFILE.write(text+'\n')
no_cassette_seqs = []
for no_cassette_tmpfile in no_cassette_tmpfiles.values():
try: no_cassette_seqs.append(dict(parse_fasta(no_cassette_tmpfile)))
except IOError: pass
# the real no-cassette seqs are the intersection of the seq headers from both no_cassette_tmpfile sets
overlapping_no_cassette_headers = set.intersection(*[set(d.keys()) for d in no_cassette_seqs])
no_cassette_readcount = len(overlapping_no_cassette_headers)
with open(no_cassette_file,'w') as NO_CASSETTE_FILE:
for header in sorted(overlapping_no_cassette_headers):
# some fastx_toolkit tools give errors on lowercase bases, so make everything uppercase
write_fasta_line(header, no_cassette_seqs[0][header].upper(), NO_CASSETTE_FILE)
assert no_cassette_readcount + sum(cutadapt_readcount.values()) == trimmed_readcount,\
"Final cassette/no-cassette readcounts don't add up to trimmed readcount - check tmpfile!"\
+"(%s+%s != %s)"%(sum(cutadapt_readcount.values()), no_cassette_readcount, trimmed_readcount)
# remove the original no_cassette_tmpfiles
for tmpfile in no_cassette_tmpfiles.values():
if os.path.exists(tmpfile): os.remove(tmpfile)
### 3. run fastx_collapser to collapse the sequences to unique
if not options.collapse_to_unique:
text = "### Not running fastx_collapser, since -C option was not used.\n"
if options.verbosity>0: print text
INFOFILE.write(text+'\n')
for (end_type,cutadapt_tmpfile) in cutadapt_tmpfiles.items():
if os.path.exists(cutadapt_tmpfile): os.rename(cutadapt_tmpfile, outfiles[end_type])
collapsed_readcount = cutadapt_readcount
# Note for fastx_collapser, but also for the others - NONE is necessary here, can't just use '', because
# fastx_collapser works fine with no options, so '' is a sensible input and can't be used to turn it off.
else:
collapsed_readcount, uncollapsed_readcount = {}, {}
for (end_type,cutadapt_tmpfile) in cutadapt_tmpfiles.items():
outfile = outfiles[end_type]
# if there is no file for that end, skip
if not os.path.exists(cutadapt_tmpfile): continue
command = "fastx_collapser -v %s -i %s -o %s"%(FASTQ_ENCODINGS_FASTX_TOOLKIT[options.fastq_encoding],
cutadapt_tmpfile, outfile)
run_command_print_info_output(command, INFOFILE, options.verbosity, shell=True,
program_name="fastx_collapser for %s"%end_type)
INFOFILE.write('\n')
collapsed_readcount[end_type] = check_readcount(outfile,INFOFILE,bool(options.verbosity>1),
"fastx_collapser output", options.total_read_number_only, input_collapsed_to_unique=False)
# make sure uncollapsed readcount is the same as before collapsing
uncollapsed_readcount[end_type] = check_readcount(outfile, None, False, "", True, input_collapsed_to_unique=True)
if not uncollapsed_readcount[end_type] == cutadapt_readcount[end_type]:
text = "ERROR: the uncollapsed read-count after fastx_collapser isn't the same as the before-collapser count! Collapsing went wrong somehow, or the way fastx_collapser works changed since this program was written?\n"
else:
text = "(checked that all the reads are still there if you uncollapse the numbers using header info)\n"
if options.verbosity>1: print text
INFOFILE.write(text+'\n')
# also run fastx_collapser on wrong_start_file and no_cassette_file
text = "### Running fastx_collapser on the \"bad\" output files. Not printing the output to info file.\n"
if options.verbosity: print text
INFOFILE.write(text+'\n')
extra_collapsed_readcounts = {}
for extra_file in (wrong_start_file, no_cassette_file):
command = "fastx_collapser -v %s -i %s -o tmp.fa"%(FASTQ_ENCODINGS_FASTX_TOOLKIT[options.fastq_encoding],
extra_file)
retcode = run_command_print_info_output(command, None, options.verbosity-1, shell=True)
# note: actually fastx_collapser doesn't give proper retcodes, so just check if outfile exists
# (also it chokes on empty files, AND on lowercase bases! That's a bit ridiculous...)
# it also apparently sometimes changes the order of the sequences for no good reason! ARGH.
if retcode in (0, None) and os.path.exists('tmp.fa'):
os.remove(extra_file)
os.rename('tmp.fa', extra_file)
extra_collapsed_readcounts[extra_file] = check_readcount(extra_file, None, False, "", True,
input_collapsed_to_unique=False)
### Final readcount check
final_output = ["### Final read count info for %s (main output files %s)\n"%(infile, ', '.join(outfiles))]
final_output.append("# starting total read count:\t%s\n"%starting_readcount)
if not options.first_bases_to_trim == 'NONE':
final_output.append('# "good" read count after start trimming (%% of total):\t%s\n'%
value_and_percentages(trimmed_readcount, [starting_readcount]))
final_output.append('# "bad" read count (wrong-start) (%% of total):\t%s\n'%
value_and_percentages(untrimmed_readcount, [starting_readcount]))
if if_running_cutadapt:
for end_type in cutadapt_readcount.keys():
final_output.append('# "good" %s read count after cassette stripping (%% of total, %% of trimmed):\t%s\n'%
(end_type, value_and_percentages(cutadapt_readcount[end_type], [starting_readcount, trimmed_readcount])))
final_output.append('# "bad" read count (no-cassette) (%% of total, %% of trimmed):\t%s\n'%
value_and_percentages(no_cassette_readcount, [starting_readcount, trimmed_readcount]))
for end_type in cutadapt_readcount.keys():
final_output.append('## final "good" %s reads (in main output file) (%% of total):\t%s\n'%(end_type,
value_and_percentages(cutadapt_readcount[end_type], [starting_readcount])))
final_output.append('## final "bad" reads (in _wrong-start and/or _no-cassette files) (%% of total):\t%s\n'%
value_and_percentages(starting_readcount-sum(cutadapt_readcount.values()), [starting_readcount]))
if options.collapse_to_unique:
for end_type in cutadapt_readcount.keys():
final_output.append('# "good" %s unique sequence count after collapsing reads to unique sequences '%end_type
+'(%% of read count):\t%s\n'%value_and_percentages(collapsed_readcount[end_type],
[cutadapt_readcount[end_type]]))
if not options.first_bases_to_trim == 'NONE':
final_output.append('# wrong-start unique sequence count after collapsing (%% of read count):\t%s\n'
%value_and_percentages(extra_collapsed_readcounts[wrong_start_file], [untrimmed_readcount]))
if if_running_cutadapt:
final_output.append('# no-cassette unique sequence count after collapsing (%% of read count):\t%s\n'
%value_and_percentages(extra_collapsed_readcounts[no_cassette_file], [no_cassette_readcount]))
for line in final_output:
INFOFILE.write(line)
if options.verbosity>0: print line,
### Remove tmpfiles
# need to use the tmpfile*_original names here because I do "trimmed_tmpfile = infile" etc if skipping steps,
# and I don't want to remove the infile!
if not options.keep_tmpfiles:
for tmpfile in [trimmed_tmpfile_original] + cutadapt_tmpfiles_original.values():
if os.path.exists(tmpfile): os.remove(tmpfile)
def main(args, options):
""" Run the main functionality of the module (see module docstring for more information), excluding testing.
The options argument should be generated by an optparse parser.
"""
try:
[infile] = args
# TODO multiple infiles would be nice!
except ValueError:
parser = define_option_parser()
parser.print_help()
sys.exit("Error: exactly one infile required!")
# MAYBE-TODO implement option with multiple infiles? Need to make sure they're the same fa/fq type etc...
### check inputs
adapter_options = '-a --adapter -b --anywhere -g --front'
if any(
[x in options.other_cutadapt_options
for x in adapter_options.split()]):
sys.exit(
"Error: --other_cutadapt_options value shouldn't contain any adapter seq options (%s)"
% adapter_options +
" - use -5/-3 options to specify adapters instead!")
### outfile and tmpfile names
# outfile suffix is always fa because we always discard quality info right now, even when not forced to do that by collapsing to unique! MAYBE-TODO change that?
#infile_suffix = os.path.splitext(infile)[1]
#outfile_suffix = '.fa' if options.collapse_to_unique else infile_suffix
outfile_suffix = '.fa'
infofile = options.outfile_basename + '_info.txt'
wrong_start_file = options.outfile_basename + '_wrong-start.fa'
no_cassette_file = options.outfile_basename + '_no-cassette.fa'
trimmed_tmpfile = trimmed_tmpfile_original = options.outfile_basename + '_trimmed-tmpfile.fa'
# outfiles and tmpfiles should be split by end ONLY if cutadapt is being run!
if options.other_cutadapt_options == 'NONE' or not (
options.adapter_5prime or options.adapter_3prime):
outfiles = {'': options.outfile_basename + '.fa'}
no_cassette_tmpfiles = {
'': options.outfile_basename + '_no-cassette-tmpfile.fa'
}
cutadapt_tmpfiles = {
'': options.outfile_basename + '_cutadapt-tmpfile.fa'
}
cutadapt_tmpfiles_original = dict(cutadapt_tmpfiles)
else:
ends = "5' 3'".split()
outfiles = {
end:
options.outfile_basename + '_%s.fa' % end.replace("'", "prime")
for end in ends
}
no_cassette_tmpfiles = {
end: options.outfile_basename +
'_no-cassette-tmpfile_%s.fa' % end.replace("'", "prime")
for end in ends
}
cutadapt_tmpfiles = {
end: options.outfile_basename +
'_cutadapt-tmpfile_%s.fa' % end.replace("'", "prime")
for end in ends
}
cutadapt_tmpfiles_original = dict(cutadapt_tmpfiles)
with open(infofile, 'w') as INFOFILE:
### write header data
write_header_data(INFOFILE, options)
INFOFILE.write('\n')
### 0. look at the infile; make sure it's readable, etc
# (check_readcount uses seq_count_and_lengths, which uses HTSeq and autodetects fa/fq format)
starting_readcount = check_readcount(infile, INFOFILE,
bool(options.verbosity > 1),
"original input",
options.total_read_number_only,
False)
### 1. Trim the first bases (from adapter)
# MAYBE-TODO I could do this with cutadapt again, instead of with my own trim_prefix function...
# Would that be faster, or better in any other way?
# MAYBE-TODO could also do it with a multiplexing barcode-splitting tool (like fastx_barcode_splitter.pl),
# since that's the eventual point of having those constant first bases there...
if options.first_bases_to_trim == 'NONE':
text = "### Not trimming first bases, since NONE was passed to -F option.\n"
if options.verbosity > 0: print text
INFOFILE.write(text + '\n')
trimmed_tmpfile = infile
trimmed_readcount = starting_readcount
untrimmed_readcount = 0
else:
trim_prefix(options.first_bases_to_trim, infile, trimmed_tmpfile,
wrong_start_file, INFOFILE, options.verbosity)
trimmed_readcount = check_readcount(trimmed_tmpfile, INFOFILE,
bool(options.verbosity > 1),
"first-base-trimming output",
options.total_read_number_only,
False)
untrimmed_readcount = check_readcount(wrong_start_file, None,
False, True, False)
assert trimmed_readcount+untrimmed_readcount==starting_readcount,\
"Trimmed/untrimmed readcounts don't add up to starting readcount - check tmpfile!"\
+"(%s+%s != %s)"%(trimmed_readcount, untrimmed_readcount, starting_readcount)
### 2. run cutadapt to strip cassette sequence
# NOTE: this currently requires my version of cutadapt, cutadapt_mod (based on some older cutadapt version),
# to deal with too-long seqs correctly - LATER-TODO submit my modification as a patch to cutadapt to get it in the
# standard install! Or wait until the cutadapt maintainer does it (I submitted it as an issue)
# (see ~/experiments/basic_programs/cutadapt_modifications/).
if_running_cutadapt = True
if options.other_cutadapt_options == 'NONE':
if_running_cutadapt = False
text = "### Not running cutadapt, since NONE was passed to -A option.\n"
elif not (options.adapter_5prime or options.adapter_3prime):
if_running_cutadapt = False
text = "### Not running cutadapt, since empty sequences were passed to -5 and -3 options.\n"
# if not running it, just skip it
if not if_running_cutadapt:
if options.verbosity > 0: print text
INFOFILE.write(text + '\n')
cutadapt_tmpfiles[''] = trimmed_tmpfile
cutadapt_readcount = {'all': trimmed_readcount}
no_cassette_readcount = 0
# otherwise run the 5' and 3' ends separately
else:
cutadapt_readcount = {}
for (end_type, adapter_seqs) in [("5'", options.adapter_5prime),
("3'", options.adapter_3prime)]:
assert end_type in ends
# if the adapter sequence for that side is empty, skip
adapter_seqs = adapter_seqs.replace('"', '').replace(
"'", '').replace(' ', '')
if not adapter_seqs: continue
cutadapt_tmpfile = cutadapt_tmpfiles[end_type]
all_adapter_options = ' '.join(
['-a %s' % seq for seq in adapter_seqs.split(',')])
full_cutadapt_options = all_adapter_options + ' ' + options.other_cutadapt_options
for extra_seq_category in ('untrimmed', 'too-short',
'too-long'):
if not extra_seq_category in full_cutadapt_options:
full_cutadapt_options += ' --%s-output %s' % (
extra_seq_category, no_cassette_tmpfiles[end_type])
command = "cutadapt_mod %s -o %s %s" % (
full_cutadapt_options, cutadapt_tmpfile, trimmed_tmpfile)
run_command_print_info_output(command,
INFOFILE,
options.verbosity,
shell=True,
program_name="cutadapt for %s" %
end_type)
cutadapt_readcount[end_type] = check_readcount(
cutadapt_tmpfile, INFOFILE, bool(options.verbosity > 1),
"cutadapt output", options.total_read_number_only, False)
tmp_no_cassette_readcount = check_readcount(
no_cassette_tmpfiles[end_type], None, False, True, False)
assert cutadapt_readcount[end_type] + tmp_no_cassette_readcount == trimmed_readcount,\
"%s cassette/no-cassette readcounts don't add up to trimmed readcount - check tmpfile!"\
+"(%s+%s != %s)"%(end_type, cutadapt_readcount[end_type], tmp_no_cassette_readcount, trimmed_readcount)
# make an actual no_cassette_file based on the overlap of the two no_cassette_tmpfiles!
text = "### Merging the 5' and 3' cutadapt untrimmed outputs to get single no-cassette file.\n"
if options.verbosity > 0: print text
INFOFILE.write(text + '\n')
no_cassette_seqs = []
for no_cassette_tmpfile in no_cassette_tmpfiles.values():
try:
no_cassette_seqs.append(
dict(parse_fasta(no_cassette_tmpfile)))
except IOError:
pass
# the real no-cassette seqs are the intersection of the seq headers from both no_cassette_tmpfile sets
overlapping_no_cassette_headers = set.intersection(
*[set(d.keys()) for d in no_cassette_seqs])
no_cassette_readcount = len(overlapping_no_cassette_headers)
with open(no_cassette_file, 'w') as NO_CASSETTE_FILE:
for header in sorted(overlapping_no_cassette_headers):
# some fastx_toolkit tools give errors on lowercase bases, so make everything uppercase
write_fasta_line(header,
no_cassette_seqs[0][header].upper(),
NO_CASSETTE_FILE)
assert no_cassette_readcount + sum(cutadapt_readcount.values()) == trimmed_readcount,\
"Final cassette/no-cassette readcounts don't add up to trimmed readcount - check tmpfile!"\
+"(%s+%s != %s)"%(sum(cutadapt_readcount.values()), no_cassette_readcount, trimmed_readcount)
# remove the original no_cassette_tmpfiles
for tmpfile in no_cassette_tmpfiles.values():
if os.path.exists(tmpfile): os.remove(tmpfile)
### 3. run fastx_collapser to collapse the sequences to unique
if not options.collapse_to_unique:
text = "### Not running fastx_collapser, since -C option was not used.\n"
if options.verbosity > 0: print text
INFOFILE.write(text + '\n')
for (end_type, cutadapt_tmpfile) in cutadapt_tmpfiles.items():
if os.path.exists(cutadapt_tmpfile):
os.rename(cutadapt_tmpfile, outfiles[end_type])
collapsed_readcount = cutadapt_readcount
# Note for fastx_collapser, but also for the others - NONE is necessary here, can't just use '', because
# fastx_collapser works fine with no options, so '' is a sensible input and can't be used to turn it off.
else:
collapsed_readcount, uncollapsed_readcount = {}, {}
for (end_type, cutadapt_tmpfile) in cutadapt_tmpfiles.items():
outfile = outfiles[end_type]
# if there is no file for that end, skip
if not os.path.exists(cutadapt_tmpfile): continue
command = "fastx_collapser -v %s -i %s -o %s" % (
FASTQ_ENCODINGS_FASTX_TOOLKIT[options.fastq_encoding],
cutadapt_tmpfile, outfile)
run_command_print_info_output(
command,
INFOFILE,
options.verbosity,
shell=True,
program_name="fastx_collapser for %s" % end_type)
INFOFILE.write('\n')
collapsed_readcount[end_type] = check_readcount(
outfile,
INFOFILE,
bool(options.verbosity > 1),
"fastx_collapser output",
options.total_read_number_only,
input_collapsed_to_unique=False)
# make sure uncollapsed readcount is the same as before collapsing
uncollapsed_readcount[end_type] = check_readcount(
outfile,
None,
False,
"",
True,
input_collapsed_to_unique=True)
if not uncollapsed_readcount[end_type] == cutadapt_readcount[
end_type]:
text = "ERROR: the uncollapsed read-count after fastx_collapser isn't the same as the before-collapser count! Collapsing went wrong somehow, or the way fastx_collapser works changed since this program was written?\n"
else:
text = "(checked that all the reads are still there if you uncollapse the numbers using header info)\n"
if options.verbosity > 1: print text
INFOFILE.write(text + '\n')
# also run fastx_collapser on wrong_start_file and no_cassette_file
text = "### Running fastx_collapser on the \"bad\" output files. Not printing the output to info file.\n"
if options.verbosity: print text
INFOFILE.write(text + '\n')
extra_collapsed_readcounts = {}
for extra_file in (wrong_start_file, no_cassette_file):
command = "fastx_collapser -v %s -i %s -o tmp.fa" % (
FASTQ_ENCODINGS_FASTX_TOOLKIT[options.fastq_encoding],
extra_file)
retcode = run_command_print_info_output(command,
None,
options.verbosity - 1,
shell=True)
# note: actually fastx_collapser doesn't give proper retcodes, so just check if outfile exists
# (also it chokes on empty files, AND on lowercase bases! That's a bit ridiculous...)
# it also apparently sometimes changes the order of the sequences for no good reason! ARGH.
if retcode in (0, None) and os.path.exists('tmp.fa'):
os.remove(extra_file)
os.rename('tmp.fa', extra_file)
extra_collapsed_readcounts[extra_file] = check_readcount(
extra_file,
None,
False,
"",
True,
input_collapsed_to_unique=False)
### Final readcount check
final_output = [
"### Final read count info for %s (main output files %s)\n" %
(infile, ', '.join(outfiles))
]
final_output.append("# starting total read count:\t%s\n" %
starting_readcount)
if not options.first_bases_to_trim == 'NONE':
final_output.append(
'# "good" read count after start trimming (%% of total):\t%s\n'
%
value_and_percentages(trimmed_readcount, [starting_readcount]))
final_output.append(
'# "bad" read count (wrong-start) (%% of total):\t%s\n' %
value_and_percentages(untrimmed_readcount,
[starting_readcount]))
if if_running_cutadapt:
for end_type in cutadapt_readcount.keys():
final_output.append(
'# "good" %s read count after cassette stripping (%% of total, %% of trimmed):\t%s\n'
% (end_type,
value_and_percentages(
cutadapt_readcount[end_type],
[starting_readcount, trimmed_readcount])))
final_output.append(
'# "bad" read count (no-cassette) (%% of total, %% of trimmed):\t%s\n'
%
value_and_percentages(no_cassette_readcount,
[starting_readcount, trimmed_readcount]))
for end_type in cutadapt_readcount.keys():
final_output.append(
'## final "good" %s reads (in main output file) (%% of total):\t%s\n'
% (end_type,
value_and_percentages(cutadapt_readcount[end_type],
[starting_readcount])))
final_output.append(
'## final "bad" reads (in _wrong-start and/or _no-cassette files) (%% of total):\t%s\n'
% value_and_percentages(
starting_readcount - sum(cutadapt_readcount.values()),
[starting_readcount]))
if options.collapse_to_unique:
for end_type in cutadapt_readcount.keys():
final_output.append(
'# "good" %s unique sequence count after collapsing reads to unique sequences '
% end_type + '(%% of read count):\t%s\n' %
value_and_percentages(collapsed_readcount[end_type],
[cutadapt_readcount[end_type]]))
if not options.first_bases_to_trim == 'NONE':
final_output.append(
'# wrong-start unique sequence count after collapsing (%% of read count):\t%s\n'
% value_and_percentages(
extra_collapsed_readcounts[wrong_start_file],
[untrimmed_readcount]))
if if_running_cutadapt:
final_output.append(
'# no-cassette unique sequence count after collapsing (%% of read count):\t%s\n'
% value_and_percentages(
extra_collapsed_readcounts[no_cassette_file],
[no_cassette_readcount]))
for line in final_output:
INFOFILE.write(line)
if options.verbosity > 0: print line,
### Remove tmpfiles
# need to use the tmpfile*_original names here because I do "trimmed_tmpfile = infile" etc if skipping steps,
# and I don't want to remove the infile!
if not options.keep_tmpfiles:
for tmpfile in [trimmed_tmpfile_original
] + cutadapt_tmpfiles_original.values():
if os.path.exists(tmpfile): os.remove(tmpfile)
def categorize_reads_print_to_files(readname,
aln_list,
category_readcounts,
UNALIGNED_FILE,
CASSETTE_FILE,
MULTIPLE_GENOMIC_FILE,
GENOMIC_UNIQUE_FILE,
unaligned_as_fasta=False,
multiple_to_write=-1,
input_collapsed_to_unique=False,
no_multi_cassette_warnings=False):
""" Decide the proper category for the read, write to appropriate output file; adjust category counts.
Categories: unaligned, cassette (one or more cassette alignments - print warning if multiple),
genomic-unique (single non-cassette alignment), multiple-genomic (multiple non-cassette alignments).
The reads will be categorized, and printed to the appropriate file (all the uppercase arguments should be open file objects;
they can all be the SAME file object if desired.)
If input_collapsed_to_unique, for the purpose of category counts each read will be counted as N reads,
with N determined from readname using the fastx-collapser encoding.
In the output category counts, cassette-multiple is a special subcategory - anything in it is also counted in cassette.
The read is printed to the appropriate outfile (all outfiles should be open file handles);
for multiple-genomic, only N=multiple_to_write lines will be written; if N=0, one line will be written that treats
the read as unaligned, but with XM:i:M optional tag field added, where M is the number of multiple alignments.
If unaligned_as_fasta, unaligned reads will be written as fasta instead of SAM format,
and so will multiple if multiple_to_write is 0.
"""
readcount = 1 if not input_collapsed_to_unique else get_seq_count_from_collapsed_header(
readname)
# if there's a single alignment, it's unaligned, cassette or genomic-unique
if len(aln_list) == 1:
aln = aln_list[0]
if not aln.aligned:
category = 'unaligned'
if unaligned_as_fasta:
write_fasta_line(readname, aln.read.seq, UNALIGNED_FILE)
else:
write_SAM_line_from_HTSeq_aln(aln, UNALIGNED_FILE)
elif is_cassette_chromosome(aln.iv.chrom):
category = 'cassette'
write_SAM_line_from_HTSeq_aln(aln, CASSETTE_FILE)
else:
category = 'genomic-unique'
write_SAM_line_from_HTSeq_aln(aln, GENOMIC_UNIQUE_FILE)
# if there are multiple alignments, it's cassette-multiple (weird!) or multiple-genomic
else:
assert all([aln.aligned for aln in aln_list
]), "Shouldn't see multiple unaligned lines per read!"
# multiple-cassette - shouldn't really happen, but write to CASSETTE_FILE
# MAYBE-TODO come up with something better to do for multiple-cassette cases? If they ever happen.
# (NOTE: sometimes they happen because I'm actually aligning to multiple cassettes - then they're fine.)
if any([is_cassette_chromosome(aln.iv.chrom) for aln in aln_list]):
assert all([
is_cassette_chromosome(aln.iv.chrom) for aln in aln_list
]), "Mixed cassette/other!"
if not no_multi_cassette_warnings:
print(
"Warning: multiple cassette alignments! Printing only one to cassette file. Seq %s, "
% aln_list[0].read.seq,
"first 3 positions %s" % ', '.join([
"%s %s %s" % (a.iv.chrom, a.iv.strand, a.iv.start)
for a in aln_list[:3]
]))
category = 'cassette-multiple'
else:
category = 'cassette'
# first position alphabetically is chosen - MAYBE-TODO add other choice options?
aln_to_print = sorted(
aln_list,
key=lambda a:
(a.iv.chrom, a.iv.strand, a.iv.start, a.iv.end))[0]
# just add _and_others to the chromosome - MAYBE-TODO add something more informative, like list of names?
# but that would be tricky, need to strip matching prefixes from them,
# what about multiple alignments to SAME chromosome, etc.
aln_to_print.iv.chrom = aln_to_print.iv.chrom + '_and_others'
write_SAM_line_from_HTSeq_aln(aln_to_print, CASSETTE_FILE)
# multiple genomic alignments:
# - if multiple_to_write=0, treat multiple as unaligned - if unaligned_as_fasta, print fasta line,
# else single unaligned SAM line, with XM:i:M optional tag field added, where M is the number of multiple alignments.
# - if multiple_to_write>0, print that many normal SAM lines for N alignments
# MAYBE-TODO add an option to write multiple as unaligned to the main SAM file AND full multiple lines to another file?
else:
category = 'multiple-genomic'
if multiple_to_write == 0:
if unaligned_as_fasta:
write_fasta_line(readname, aln_list[0].read.seq,
MULTIPLE_GENOMIC_FILE)
else:
aln = aln_list[0]
MULTIPLE_GENOMIC_FILE.write(
'%s\t4\t*\t0\t0\t*\t*\t0\t0\t%s\t%s\tXM:i:%s\n' %
(aln.read.name, aln.read.seq, aln.read.qualstr,
len(aln_list)))
else:
for aln in aln_list[:multiple_to_write]:
write_SAM_line_from_HTSeq_aln(aln, MULTIPLE_GENOMIC_FILE)
category_readcounts[category] += readcount
return category
def categorize_reads_print_to_files(readname, aln_list, category_readcounts, UNALIGNED_FILE, CASSETTE_FILE,
MULTIPLE_GENOMIC_FILE, GENOMIC_UNIQUE_FILE, unaligned_as_fasta=False, multiple_to_write=-1,
input_collapsed_to_unique=False, no_multi_cassette_warnings=False):
""" Decide the proper category for the read, write to appropriate output file; adjust category counts.
Categories: unaligned, cassette (one or more cassette alignments - print warning if multiple),
genomic-unique (single non-cassette alignment), multiple-genomic (multiple non-cassette alignments).
The reads will be categorized, and printed to the appropriate file (all the uppercase arguments should be open file objects;
they can all be the SAME file object if desired.)
If input_collapsed_to_unique, for the purpose of category counts each read will be counted as N reads,
with N determined from readname using the fastx-collapser encoding.
In the output category counts, cassette-multiple is a special subcategory - anything in it is also counted in cassette.
The read is printed to the appropriate outfile (all outfiles should be open file handles);
for multiple-genomic, only N=multiple_to_write lines will be written; if N=0, one line will be written that treats
the read as unaligned, but with XM:i:M optional tag field added, where M is the number of multiple alignments.
If unaligned_as_fasta, unaligned reads will be written as fasta instead of SAM format,
and so will multiple if multiple_to_write is 0.
"""
readcount = 1 if not input_collapsed_to_unique else get_seq_count_from_collapsed_header(readname)
# if there's a single alignment, it's unaligned, cassette or genomic-unique
if len(aln_list) == 1:
aln = aln_list[0]
if not aln.aligned:
category = 'unaligned'
if unaligned_as_fasta: write_fasta_line(readname, aln.read.seq, UNALIGNED_FILE)
else: write_SAM_line_from_HTSeq_aln(aln, UNALIGNED_FILE)
elif is_cassette_chromosome(aln.iv.chrom):
category = 'cassette'
write_SAM_line_from_HTSeq_aln(aln, CASSETTE_FILE)
else:
category = 'genomic-unique'
write_SAM_line_from_HTSeq_aln(aln, GENOMIC_UNIQUE_FILE)
# if there are multiple alignments, it's cassette-multiple (weird!) or multiple-genomic
else:
assert all([aln.aligned for aln in aln_list]), "Shouldn't see multiple unaligned lines per read!"
# multiple-cassette - shouldn't really happen, but write to CASSETTE_FILE
# MAYBE-TODO come up with something better to do for multiple-cassette cases? If they ever happen.
# (NOTE: sometimes they happen because I'm actually aligning to multiple cassettes - then they're fine.)
if any([is_cassette_chromosome(aln.iv.chrom) for aln in aln_list]):
assert all([is_cassette_chromosome(aln.iv.chrom) for aln in aln_list]), "Mixed cassette/other!"
if not no_multi_cassette_warnings:
print ("Warning: multiple cassette alignments! Printing only one to cassette file. Seq %s, "%aln_list[0].read.seq,
"first 3 positions %s"%', '.join(["%s %s %s"%(a.iv.chrom, a.iv.strand, a.iv.start) for a in aln_list[:3]]))
category = 'cassette-multiple'
else:
category = 'cassette'
# first position alphabetically is chosen - MAYBE-TODO add other choice options?
aln_to_print = sorted(aln_list, key=lambda a: (a.iv.chrom, a.iv.strand, a.iv.start, a.iv.end))[0]
# just add _and_others to the chromosome - MAYBE-TODO add something more informative, like list of names?
# but that would be tricky, need to strip matching prefixes from them,
# what about multiple alignments to SAME chromosome, etc.
aln_to_print.iv.chrom = aln_to_print.iv.chrom + '_and_others'
write_SAM_line_from_HTSeq_aln(aln_to_print, CASSETTE_FILE)
# multiple genomic alignments:
# - if multiple_to_write=0, treat multiple as unaligned - if unaligned_as_fasta, print fasta line,
# else single unaligned SAM line, with XM:i:M optional tag field added, where M is the number of multiple alignments.
# - if multiple_to_write>0, print that many normal SAM lines for N alignments
# MAYBE-TODO add an option to write multiple as unaligned to the main SAM file AND full multiple lines to another file?
else:
category = 'multiple-genomic'
if multiple_to_write == 0:
if unaligned_as_fasta:
write_fasta_line(readname, aln_list[0].read.seq, MULTIPLE_GENOMIC_FILE)
else:
aln = aln_list[0]
MULTIPLE_GENOMIC_FILE.write('%s\t4\t*\t0\t0\t*\t*\t0\t0\t%s\t%s\tXM:i:%s\n'%(aln.read.name, aln.read.seq,
aln.read.qualstr, len(aln_list)))
else:
for aln in aln_list[:multiple_to_write]:
write_SAM_line_from_HTSeq_aln(aln, MULTIPLE_GENOMIC_FILE)
category_readcounts[category] += readcount
return category
