def write_good_collapsed_isoforms(in_abundance_filename, in_gff_filename, in_rep_filename,
out_abundance_filename, out_gff_filename, out_rep_filename,
good):
"""Write good collapsed isoforms."""
in_suffix = parse_ds_filename(in_rep_filename)[1]
out_suffix = parse_ds_filename(out_rep_filename)[1]
if in_suffix != out_suffix:
raise ValueError("Format of input %s and output %s must match." %
(in_rep_filename, out_rep_filename))
if in_suffix not in ("fasta", "fastq"):
raise ValueError("Format of input %s and output %s must be either FASTA or FASTQ." %
(in_rep_filename, out_rep_filename))
# then read gff, and write good gff record.
with CollapseGffWriter(out_gff_filename) as gff_writer:
for r in CollapseGffReader(in_gff_filename):
if r.seqid in good:
gff_writer.writeRecord(r)
# next read rep fasta/fastq, and write good rep fasta/fastq record.
rep_reader = FastaReader(in_rep_filename) if in_suffix == "fasta" \
else FastqReader(in_rep_filename)
rep_writer = FastaWriter(out_rep_filename) if in_suffix == "fasta" \
else FastqWriter(out_rep_filename)
for r in rep_reader:
# r.name e.g., PB.1.1|PB.1.1:10712-11643(+)|i0_HQ_sample18ba5d|c1543/f8p1/465
if r.name.split('|')[0] in good:
rep_writer.writeRecord(r)
# finally write abundance info of good records.
with AbundanceReader(in_abundance_filename) as a_reader, \
AbundanceWriter(out_abundance_filename, comments=a_reader.comments) as a_writer:
for r in a_reader:
if r.pbid in good:
a_writer.writeRecord(r)
def __init__(self, isoform_filename, sam_filename, output_prefix,
min_aln_coverage, min_aln_identity, min_flnc_coverage,
max_fuzzy_junction, allow_extra_5exon, skip_5_exon_alt):
"""
Parameters:
isoform_filename -- input file containing isoforms, as fastq|fasta|contigset
sam_filename -- input sam file produced by mapping fastq_filename to reference and sorted.
#collapsed_isoform_filename -- file to output collapsed isoforms as fasta|fastq|contigset
min_aln_coverage -- min coverage over reference to collapse a group of isoforms
min_aln_identity -- min identity aligning to reference to collapse a group of isoforms
min_flnc_coverage -- min supportive flnc reads to not ignore an isoform
Must be 1 when collapsing consensus isoforms, which is the case in production isoseq.
Can be >= 1 only when directly collapsing FLNC reads.
max_fuzzy_junction -- max edit distance between fuzzy-matching exons
allow_extra_5exon -- whether or not to allow shorter 5' exons
skip_5_exon_alt -- whether or not to skip alternative 5' exons
"""
self.suffix = parse_ds_filename(isoform_filename)[1]
super(CollapseIsoformsRunner, self).__init__(prefix=output_prefix,
allow_extra_5exon=allow_extra_5exon)
self.isoform_filename = isoform_filename # input, uncollapsed fa|fq|ds
self.sam_filename = sam_filename # input, sorted, gmap sam
#self.collapsed_isoform_filename = collapsed_isoform_filename # output, collapsed, fa|fq|ds
self.min_aln_coverage = float(min_aln_coverage)
self.min_aln_identity = float(min_aln_identity)
self.min_flnc_coverage = int(min_flnc_coverage)
self.max_fuzzy_junction = int(max_fuzzy_junction)
self.allow_extra_5exon = bool(allow_extra_5exon)
self.skip_5_exon_alt = bool(skip_5_exon_alt)
def __init__(self, isoform_filename, sam_filename, output_prefix,
min_aln_coverage, min_aln_identity, min_flnc_coverage,
max_fuzzy_junction, allow_extra_5exon, skip_5_exon_alt):
"""
Parameters:
isoform_filename -- input file containing isoforms, as fastq|fasta|contigset
sam_filename -- input sam file produced by mapping fastq_filename to reference and sorted.
#collapsed_isoform_filename -- file to output collapsed isoforms as fasta|fastq|contigset
min_aln_coverage -- min coverage over reference to collapse a group of isoforms
min_aln_identity -- min identity aligning to reference to collapse a group of isoforms
min_flnc_coverage -- min supportive flnc reads to not ignore an isoform
Must be 1 when collapsing consensus isoforms, which is the case in production isoseq.
Can be >= 1 only when directly collapsing FLNC reads.
max_fuzzy_junction -- max edit distance between fuzzy-matching exons
allow_extra_5exon -- whether or not to allow shorter 5' exons
skip_5_exon_alt -- whether or not to skip alternative 5' exons
"""
self.suffix = parse_ds_filename(isoform_filename)[1]
super(CollapseIsoformsRunner,
self).__init__(prefix=output_prefix,
allow_extra_5exon=allow_extra_5exon)
self.isoform_filename = isoform_filename # input, uncollapsed fa|fq|ds
self.sam_filename = sam_filename # input, sorted, gmap sam
#self.collapsed_isoform_filename = collapsed_isoform_filename # output, collapsed, fa|fq|ds
self.min_aln_coverage = float(min_aln_coverage)
self.min_aln_identity = float(min_aln_identity)
self.min_flnc_coverage = int(min_flnc_coverage)
self.max_fuzzy_junction = int(max_fuzzy_junction)
self.allow_extra_5exon = bool(allow_extra_5exon)
self.skip_5_exon_alt = bool(skip_5_exon_alt)
def write_good_collapsed_isoforms(in_abundance_filename, in_gff_filename,
in_rep_filename, out_abundance_filename,
out_gff_filename, out_rep_filename, good):
"""Write good collapsed isoforms."""
in_suffix = parse_ds_filename(in_rep_filename)[1]
out_suffix = parse_ds_filename(out_rep_filename)[1]
if in_suffix != out_suffix:
raise ValueError("Format of input %s and output %s must match." %
(in_rep_filename, out_rep_filename))
if in_suffix not in ("fasta", "fastq"):
raise ValueError(
"Format of input %s and output %s must be either FASTA or FASTQ." %
(in_rep_filename, out_rep_filename))
# then read gff, and write good gff record.
with CollapseGffWriter(out_gff_filename) as gff_writer:
for r in CollapseGffReader(in_gff_filename):
if r.seqid in good:
gff_writer.writeRecord(r)
# next read rep fasta/fastq, and write good rep fasta/fastq record.
rep_reader = FastaReader(in_rep_filename) if in_suffix == "fasta" \
else FastqReader(in_rep_filename)
rep_writer = FastaWriter(out_rep_filename) if in_suffix == "fasta" \
else FastqWriter(out_rep_filename)
for r in rep_reader:
# r.name e.g., PB.1.1|PB.1.1:10712-11643(+)|i0_HQ_sample18ba5d|c1543/f8p1/465
if r.name.split('|')[0] in good:
rep_writer.writeRecord(r)
# finally write abundance info of good records.
with AbundanceReader(in_abundance_filename) as a_reader, \
AbundanceWriter(out_abundance_filename, comments=a_reader.comments) as a_writer:
for r in a_reader:
if r.pbid in good:
a_writer.writeRecord(r)
def args_runner(args):
"""Run given input args"""
c = CollapseIsoformsRunner(isoform_filename=args.input_isoforms,
sam_filename=args.sam_filename,
output_prefix=args.output_prefix,
min_aln_coverage=args.min_aln_coverage,
min_aln_identity=args.min_aln_identity,
min_flnc_coverage=args.min_flnc_coverage,
max_fuzzy_junction=args.max_fuzzy_junction,
allow_extra_5exon=args.allow_extra_5exon,
skip_5_exon_alt=args.skip_5_exon_alt)
c.run()
if args.collapsed_isoforms is not None:
suffix = parse_ds_filename(args.collapsed_isoforms)[1]
if op.exists(c.rep_fn(suffix)):
ln(c.rep_fn(suffix), args.collapsed_isoforms)
else:
if suffix == ".contigset.xml": # make contigset from fasta
as_contigset(c.rep_fn("fasta"), args.collapsed_isoforms)
else:
raise IOError("Could not make collapsed isoform file %s" % args.collapsed_isoforms)
return 0
def args_runner(args):
"""Run given input args"""
c = CollapseIsoformsRunner(isoform_filename=args.input_isoforms,
sam_filename=args.sam_filename,
output_prefix=args.output_prefix,
min_aln_coverage=args.min_aln_coverage,
min_aln_identity=args.min_aln_identity,
min_flnc_coverage=args.min_flnc_coverage,
max_fuzzy_junction=args.max_fuzzy_junction,
allow_extra_5exon=args.allow_extra_5exon,
skip_5_exon_alt=args.skip_5_exon_alt)
c.run()
if args.collapsed_isoforms is not None:
suffix = parse_ds_filename(args.collapsed_isoforms)[1]
if op.exists(c.rep_fn(suffix)):
ln(c.rep_fn(suffix), args.collapsed_isoforms)
else:
if suffix == ".contigset.xml": # make contigset from fasta
as_contigset(c.rep_fn("fasta"), args.collapsed_isoforms)
else:
raise IOError("Could not make collapsed isoform file %s" %
args.collapsed_isoforms)
return 0
def pick_rep(isoform_filename,
gff_filename,
group_filename,
output_filename,
pick_least_err_instead=False,
bad_gff_filename=None):
"""
For each group of collapsed sam records, select the representative record.
If is FASTA file -- then always pick the longest one
If is FASTQ file -- then
If pick_least_err_instead is True, pick the one w/ least number of expected base errors
Else, pick the longest one
"""
fd = None
is_fq = False
dummy_prefix, _suffix = parse_ds_filename(isoform_filename)
if _suffix == "fasta":
fd = FastaRandomReader(isoform_filename)
elif _suffix == "fastq":
fd = FastqRandomReader(isoform_filename)
is_fq = True
elif _suffix == "contigset.xml":
fd = ContigSet(isoform_filename)
_fns = fd.toExternalFiles()
if len(_fns) == 1 and _fns[0].endswith(".fq") or _fns[0].endswith(
".fastq"):
fd = FastqRandomReader(_fns[0])
is_fq = True
else:
if not fd.isIndexed:
# Must be indexed FASTA, or exactly contains one FASTQ file
raise IOError(
"%s must contain either indexed FASTA files or " %
isoform_filename + "contain exactly one FASTQ file!")
else:
raise IOError("Unable to recognize file type of %s." %
isoform_filename)
fa_out_fn, fq_out_fn, ds_out_fn = None, None, None
_prefix, _suffix = parse_ds_filename(output_filename)
if _suffix == "fasta":
fa_out_fn = output_filename
elif _suffix == "fastq":
if not is_fq:
raise ValueError("Input file %s is not FASTQ while output is." %
isoform_filename)
else:
fq_out_fn = output_filename
elif _suffix == "contigset.xml": # output is contigset.xml
ds_out_fn = output_filename
fa_out_fn = _prefix + ".fasta"
if is_fq:
fq_out_fn = _prefix + ".fastq"
else:
raise IOError("Unable to recognize file type of %s." % output_filename)
fa_writer = FastaWriter(fa_out_fn) if fa_out_fn is not None else None
fq_writer = FastqWriter(fq_out_fn) if fq_out_fn is not None else None
coords = {}
for r in CollapseGffReader(gff_filename):
tid = r.transcript_id
coords[tid] = "{0}:{1}-{2}({3})".format(r.seqid, r.start, r.end,
r.strand)
if bad_gff_filename is not None:
for r in CollapseGffReader(gff_filename):
tid = r.transcript_id
coords[tid] = "{0}:{1}-{2}({3})".format(r.seqid, r.start, r.end,
r.strand)
for group in GroupReader(group_filename):
pb_id, members = group.name, group.members
if not pb_id in coords:
raise ValueError("Could not find %s in %s and %s" %
(pb_id, gff_filename, bad_gff_filename))
#logging.info("Picking representative sequence for %s", pb_id)
best_id = None
best_seq = None
best_qual = None
best_err = 9999999
err = 9999999
max_len = 0
for x in members:
if is_fq and pick_least_err_instead:
err = sum(i**-(i / 10.) for i in fd[x].quality)
if (is_fq and pick_least_err_instead and err < best_err) or \
((not is_fq or not pick_least_err_instead) and len(fd[x].sequence) >= max_len):
best_id = x
best_seq = fd[x].sequence
if is_fq:
best_qual = fd[x].quality
best_err = err
max_len = len(fd[x].sequence)
_id_ = "{0}|{1}|{2}".format(pb_id, coords[pb_id], best_id)
_seq_ = best_seq
if fq_writer is not None:
fq_writer.writeRecord(_id_, _seq_, best_qual)
if fa_writer is not None:
fa_writer.writeRecord(_id_, _seq_)
if fa_writer is not None:
fa_writer.close()
if fq_writer is not None:
fq_writer.close()
if ds_out_fn is not None:
as_contigset(fa_out_fn, ds_out_fn)
def post_mapping_to_genome_runner(
in_isoforms,
in_sam,
in_pickle,
out_isoforms,
out_gff,
out_abundance,
out_group,
out_read_stat,
min_aln_coverage=cmi.Constants.MIN_ALN_COVERAGE_DEFAULT,
min_aln_identity=cmi.Constants.MIN_ALN_IDENTITY_DEFAULT,
min_flnc_coverage=cmi.Constants.MIN_FLNC_COVERAGE_DEFAULT,
max_fuzzy_junction=cmi.Constants.MAX_FUZZY_JUNCTION_DEFAULT,
allow_extra_5exon=cmi.Constants.ALLOW_EXTRA_5EXON_DEFAULT,
skip_5_exon_alt=cmi.Constants.SKIP_5_EXON_ALT_DEFAULT,
min_count=fci.Constants.MIN_COUNT_DEFAULT,
to_filter_out_subsets=True):
"""
(1) Collapse isoforms and merge fuzzy junctions if needed.
(2) Generate read stat file and abundance file
(3) Based on abundance file, filter collapsed isoforms by min FL count
"""
log.info('args: {!r}'.format(locals()))
# Check input and output format
in_suffix = parse_ds_filename(in_isoforms)[1]
out_prefix, out_suffix = parse_ds_filename(out_isoforms)
if in_suffix != out_suffix:
raise ValueError(
"Format of input and output isoforms %s, %s must be the same." %
(in_isoforms, out_isoforms))
if in_suffix not in ("fasta", "fastq"):
raise ValueError(
"Format of input and output isoforms %s, %s must be FASTA or FASTQ."
% (in_isoforms, out_isoforms))
#(1) Collapse isoforms and merge fuzzy junctions if needed.
cf = CollapsedFiles(prefix=out_prefix, allow_extra_5exon=allow_extra_5exon)
cir = CollapseIsoformsRunner(isoform_filename=in_isoforms,
sam_filename=in_sam,
output_prefix=out_prefix,
min_aln_coverage=min_aln_coverage,
min_aln_identity=min_aln_identity,
min_flnc_coverage=min_flnc_coverage,
max_fuzzy_junction=max_fuzzy_junction,
allow_extra_5exon=allow_extra_5exon,
skip_5_exon_alt=skip_5_exon_alt)
cir.run()
# (2) Generate read stat file and abundance file
cr = CountRunner(group_filename=cf.group_fn,
pickle_filename=in_pickle,
output_read_stat_filename=cf.read_stat_fn,
output_abundance_filename=cf.abundance_fn)
cr.run()
# (3) Filter collapsed isoforms by min FL count based on abundance file.
fff = FilteredFiles(prefix=out_prefix,
allow_extra_5exon=allow_extra_5exon,
min_count=min_count,
filter_out_subsets=False)
filter_by_count(in_group_filename=cf.group_fn,
in_abundance_filename=cf.abundance_fn,
in_gff_filename=cf.good_gff_fn,
in_rep_filename=cf.rep_fn(out_suffix),
out_abundance_filename=fff.filtered_abundance_fn,
out_gff_filename=fff.filtered_gff_fn,
out_rep_filename=fff.filtered_rep_fn(out_suffix),
min_count=min_count)
fft = FilteredFiles(prefix=out_prefix,
allow_extra_5exon=allow_extra_5exon,
min_count=min_count,
filter_out_subsets=True)
# (4) Remove collapsed isoforms which are a subset of another isoform
if to_filter_out_subsets is True:
filter_out_subsets(in_abundance_filename=fff.filtered_abundance_fn,
in_gff_filename=fff.filtered_gff_fn,
in_rep_filename=fff.filtered_rep_fn(out_suffix),
out_abundance_filename=fft.filtered_abundance_fn,
out_gff_filename=fft.filtered_gff_fn,
out_rep_filename=fft.filtered_rep_fn(out_suffix),
max_fuzzy_junction=max_fuzzy_junction)
fff = fft
# (5) ln outputs files
ln_pairs = [
(fff.filtered_rep_fn(out_suffix), out_isoforms), # rep isoforms
(fff.filtered_gff_fn, out_gff), # gff annotation
(fff.filtered_abundance_fn, out_abundance), # abundance info
(fff.group_fn, out_group), # groups
(fff.read_stat_fn, out_read_stat)
] # read stat info
for src, dst in ln_pairs:
if dst is not None:
ln(src, dst)
logging.info("Filter arguments: min_count = %s, filter_out_subsets=%s",
min_count, filter_out_subsets)
logging.info(
"Collapsed and filtered isoform sequences written to %s",
realpath(out_isoforms) if out_isoforms is not None else realpath(
fff.filtered_rep_fn(out_suffix)))
logging.info(
"Collapsed and filtered isoform annotations written to %s",
realpath(out_gff)
if out_gff is not None else realpath(fff.filtered_gff_fn))
logging.info(
"Collapsed and filtered isoform abundance info written to %s",
realpath(out_abundance)
if out_abundance is not None else realpath(fff.filtered_abundance_fn))
logging.info(
"Collapsed isoform groups written to %s",
realpath(out_group)
if out_group is not None else realpath(fff.group_fn))
logging.info(
"Read status of FL and nFL reads written to %s",
realpath(out_read_stat)
if out_read_stat is not None else realpath(fff.read_stat_fn))
def pick_rep(isoform_filename, gff_filename,
group_filename, output_filename,
pick_least_err_instead=False,
bad_gff_filename=None):
"""
For each group of collapsed sam records, select the representative record.
If is FASTA file -- then always pick the longest one
If is FASTQ file -- then
If pick_least_err_instead is True, pick the one w/ least number of expected base errors
Else, pick the longest one
"""
fd = None
is_fq = False
dummy_prefix, _suffix = parse_ds_filename(isoform_filename)
if _suffix == "fasta":
fd = FastaRandomReader(isoform_filename)
elif _suffix == "fastq":
fd = FastqRandomReader(isoform_filename)
is_fq = True
elif _suffix == "contigset.xml":
fd = ContigSet(isoform_filename)
_fns = fd.toExternalFiles()
if len(_fns) == 1 and _fns[0].endswith(".fq") or _fns[0].endswith(".fastq"):
fd = FastqRandomReader(_fns[0])
is_fq = True
else:
if not fd.isIndexed:
# Must be indexed FASTA, or exactly contains one FASTQ file
raise IOError("%s must contain either indexed FASTA files or " % isoform_filename +
"contain exactly one FASTQ file!")
else:
raise IOError("Unable to recognize file type of %s." % isoform_filename)
fa_out_fn, fq_out_fn, ds_out_fn = None, None, None
_prefix, _suffix = parse_ds_filename(output_filename)
if _suffix == "fasta":
fa_out_fn = output_filename
elif _suffix == "fastq":
if not is_fq:
raise ValueError("Input file %s is not FASTQ while output is." % isoform_filename)
else:
fq_out_fn = output_filename
elif _suffix == "contigset.xml": # output is contigset.xml
ds_out_fn = output_filename
fa_out_fn = _prefix + ".fasta"
if is_fq:
fq_out_fn = _prefix + ".fastq"
else:
raise IOError("Unable to recognize file type of %s." % output_filename)
fa_writer = FastaWriter(fa_out_fn) if fa_out_fn is not None else None
fq_writer = FastqWriter(fq_out_fn) if fq_out_fn is not None else None
coords = {}
for r in CollapseGffReader(gff_filename):
tid = r.transcript_id
coords[tid] = "{0}:{1}-{2}({3})".format(r.seqid, r.start, r.end, r.strand)
if bad_gff_filename is not None:
for r in CollapseGffReader(gff_filename):
tid = r.transcript_id
coords[tid] = "{0}:{1}-{2}({3})".format(r.seqid, r.start, r.end, r.strand)
for group in GroupReader(group_filename):
pb_id, members = group.name, group.members
if not pb_id in coords:
raise ValueError("Could not find %s in %s and %s" %
(pb_id, gff_filename, bad_gff_filename))
#logging.info("Picking representative sequence for %s", pb_id)
best_id = None
best_seq = None
best_qual = None
best_err = 9999999
err = 9999999
max_len = 0
for x in members:
if is_fq and pick_least_err_instead:
err = sum(i**-(i/10.) for i in fd[x].quality)
if (is_fq and pick_least_err_instead and err < best_err) or \
((not is_fq or not pick_least_err_instead) and len(fd[x].sequence) >= max_len):
best_id = x
best_seq = fd[x].sequence
if is_fq:
best_qual = fd[x].quality
best_err = err
max_len = len(fd[x].sequence)
_id_ = "{0}|{1}|{2}".format(pb_id, coords[pb_id], best_id)
_seq_ = best_seq
if fq_writer is not None:
fq_writer.writeRecord(_id_, _seq_, best_qual)
if fa_writer is not None:
fa_writer.writeRecord(_id_, _seq_)
if fa_writer is not None:
fa_writer.close()
if fq_writer is not None:
fq_writer.close()
if ds_out_fn is not None:
as_contigset(fa_out_fn, ds_out_fn)
def post_mapping_to_genome_runner(in_isoforms, in_sam, in_pickle,
out_isoforms, out_gff, out_abundance, out_group, out_read_stat,
min_aln_coverage=cmi.Constants.MIN_ALN_COVERAGE_DEFAULT,
min_aln_identity=cmi.Constants.MIN_ALN_IDENTITY_DEFAULT,
min_flnc_coverage=cmi.Constants.MIN_FLNC_COVERAGE_DEFAULT,
max_fuzzy_junction=cmi.Constants.MAX_FUZZY_JUNCTION_DEFAULT,
allow_extra_5exon=cmi.Constants.ALLOW_EXTRA_5EXON_DEFAULT,
skip_5_exon_alt=cmi.Constants.SKIP_5_EXON_ALT_DEFAULT,
min_count=fci.Constants.MIN_COUNT_DEFAULT,
to_filter_out_subsets=True):
"""
(1) Collapse isoforms and merge fuzzy junctions if needed.
(2) Generate read stat file and abundance file
(3) Based on abundance file, filter collapsed isoforms by min FL count
"""
# Check input and output format
in_suffix = parse_ds_filename(in_isoforms)[1]
out_prefix, out_suffix = parse_ds_filename(out_isoforms)
if in_suffix != out_suffix:
raise ValueError("Format of input and output isoforms %s, %s must be the same." %
(in_isoforms, out_isoforms))
if in_suffix not in ("fasta", "fastq"):
raise ValueError("Format of input and output isoforms %s, %s must be FASTA or FASTQ." %
(in_isoforms, out_isoforms))
#(1) Collapse isoforms and merge fuzzy junctions if needed.
cf = CollapsedFiles(prefix=out_prefix, allow_extra_5exon=allow_extra_5exon)
cir = CollapseIsoformsRunner(isoform_filename=in_isoforms,
sam_filename=in_sam,
output_prefix=out_prefix,
min_aln_coverage=min_aln_coverage,
min_aln_identity=min_aln_identity,
min_flnc_coverage=min_flnc_coverage,
max_fuzzy_junction=max_fuzzy_junction,
allow_extra_5exon=allow_extra_5exon,
skip_5_exon_alt=skip_5_exon_alt)
cir.run()
# (2) Generate read stat file and abundance file
cr = CountRunner(group_filename=cf.group_fn, pickle_filename=in_pickle,
output_read_stat_filename=cf.read_stat_fn,
output_abundance_filename=cf.abundance_fn)
cr.run()
# (3) Filter collapsed isoforms by min FL count based on abundance file.
fff = FilteredFiles(prefix=out_prefix, allow_extra_5exon=allow_extra_5exon,
min_count=min_count, filter_out_subsets=False)
filter_by_count(in_group_filename=cf.group_fn, in_abundance_filename=cf.abundance_fn,
in_gff_filename=cf.good_gff_fn, in_rep_filename=cf.rep_fn(out_suffix),
out_abundance_filename=fff.filtered_abundance_fn,
out_gff_filename=fff.filtered_gff_fn,
out_rep_filename=fff.filtered_rep_fn(out_suffix),
min_count=min_count)
fft = FilteredFiles(prefix=out_prefix, allow_extra_5exon=allow_extra_5exon,
min_count=min_count, filter_out_subsets=True)
# (4) Remove collapsed isoforms which are a subset of another isoform
if to_filter_out_subsets is True:
filter_out_subsets(in_abundance_filename=fff.filtered_abundance_fn,
in_gff_filename=fff.filtered_gff_fn,
in_rep_filename=fff.filtered_rep_fn(out_suffix),
out_abundance_filename=fft.filtered_abundance_fn,
out_gff_filename=fft.filtered_gff_fn,
out_rep_filename=fft.filtered_rep_fn(out_suffix),
max_fuzzy_junction=max_fuzzy_junction)
fff = fft
# (5) ln outputs files
ln_pairs = [(fff.filtered_rep_fn(out_suffix), out_isoforms), # rep isoforms
(fff.filtered_gff_fn, out_gff), # gff annotation
(fff.filtered_abundance_fn, out_abundance), # abundance info
(fff.group_fn, out_group), # groups
(fff.read_stat_fn, out_read_stat)] # read stat info
for src, dst in ln_pairs:
if dst is not None:
ln(src, dst)
logging.info("Filter arguments: min_count = %s, filter_out_subsets=%s",
min_count, filter_out_subsets)
logging.info("Collapsed and filtered isoform sequences written to %s",
realpath(out_isoforms) if out_isoforms is not None else
realpath(fff.filtered_rep_fn(out_suffix)))
logging.info("Collapsed and filtered isoform annotations written to %s",
realpath(out_gff) if out_gff is not None else realpath(fff.filtered_gff_fn))
logging.info("Collapsed and filtered isoform abundance info written to %s",
realpath(out_abundance) if out_abundance is not None else
realpath(fff.filtered_abundance_fn))
logging.info("Collapsed isoform groups written to %s",
realpath(out_group) if out_group is not None else realpath(fff.group_fn))
logging.info("Read status of FL and nFL reads written to %s",
realpath(out_read_stat) if out_read_stat is not None else
realpath(fff.read_stat_fn))