def classify_read_pairs(pe_reads, max_isize,
library_type, tid_genome_map,
tid_tx_cluster_map):
"""
examines all the alignments of a single fragment and tries to find ways
to pair reads together.
annotates all read pairs with an integer tag corresponding to a value
in the DiscordantTags class
returns a tuple with the following lists:
1) pairs (r1,r2) aligning to genes (pairs may be discordant)
2) pairs (r1,r2) aligning to genome (pairs may be discordant)
3) unpaired reads, if any
"""
# to satisfy library type reads must either be on
# same strand or opposite strands
concordant_tx_pairs = []
discordant_tx_pairs = []
concordant_gene_pairs = []
discordant_gene_pairs = []
concordant_genome_pairs = []
discordant_genome_pairs = []
#
# first, try to pair reads that map to the same transcript, or to the
# genome within the insert size range
#
same_strand = LibraryTypes.same_strand(library_type)
refdict,clusterdict = map_reads_to_references(pe_reads, tid_tx_cluster_map)
found_pair = False
for tid, tid_pe_reads in refdict.iteritems():
# check if there are alignments involving both reads in a pair
if len(tid_pe_reads[0]) == 0 or len(tid_pe_reads[1]) == 0:
# no paired alignments exist at this reference
continue
# check if there are alignments involving both reads in a pair
for r1 in tid_pe_reads[0]:
for r2 in tid_pe_reads[1]:
# read strands must agree with library type
strand_match = (same_strand == (r1.is_reverse == r2.is_reverse))
# check to see if this tid is a gene or genomic
if (tid not in tid_genome_map):
# this is a genomic hit so check insert size
if r1.pos > r2.pos:
isize = r1.aend - r2.pos
else:
isize = r2.aend - r1.pos
if (isize <= max_isize):
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
# reads are close to each other on same chromosome
# so check strand
if strand_match:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.CONCORDANT_GENOME)]
concordant_genome_pairs.append((cr1,cr2))
else:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.DISCORDANT_STRAND_GENOME)]
discordant_genome_pairs.append((cr1, cr2))
pair_reads(cr1,cr2,tags)
else:
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
# this is a hit to same transcript (gene)
# pair the reads if strand comparison is correct
if strand_match:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.CONCORDANT_TX)]
concordant_tx_pairs.append((cr1,cr2))
else:
# hit to same gene with wrong strand, which
# could happen in certain wacky cases
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.DISCORDANT_STRAND_TX)]
discordant_tx_pairs.append((cr1,cr2))
pair_reads(cr1,cr2,tags)
# at this point, if we have not been able to find a suitable way
# to pair the reads, then search within the transcript cluster
if not found_pair:
for cluster_id, cluster_pe_reads in clusterdict.iteritems():
# check if there are alignments involving both reads in a pair
if len(cluster_pe_reads[0]) == 0 or len(cluster_pe_reads[1]) == 0:
# no paired alignments in this transcript cluster
continue
for r1 in cluster_pe_reads[0]:
for r2 in cluster_pe_reads[1]:
# check strand compatibility
strand_match = (same_strand == (r1.is_reverse == r2.is_reverse))
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
if strand_match:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.CONCORDANT_GENE)]
concordant_gene_pairs.append((cr1,cr2))
else:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.DISCORDANT_STRAND_GENE)]
discordant_gene_pairs.append((cr1,cr2))
pair_reads(cr1,cr2,tags)
# at this point, we have tried all combinations. if any paired reads
# are concordant then return them without considering discordant reads
gene_pairs = []
if len(concordant_tx_pairs) > 0:
gene_pairs = concordant_tx_pairs
elif len(concordant_gene_pairs) > 0:
gene_pairs = concordant_gene_pairs
if len(gene_pairs) > 0 or len(concordant_genome_pairs) > 0:
return gene_pairs, concordant_genome_pairs, []
# if no concordant reads in transcripts or genome, return any
# discordant reads that may violate strand requirements but still
# remain colocalized on the same gene/chromosome
gene_pairs = []
if len(discordant_tx_pairs) > 0:
gene_pairs = discordant_tx_pairs
elif len(discordant_gene_pairs) > 0:
gene_pairs = discordant_gene_pairs
if len(gene_pairs) > 0 or len(discordant_genome_pairs) > 0:
return gene_pairs, discordant_genome_pairs, []
#
# at this point, no read pairings were found so the read is
# assumed to be discordant.
#
# TODO: now that we know that the reads are discordant, no reason
# to keep all the mappings hanging around if there is a small subset
# with a small number of mismatches. is this the right thing to do
# here?
#
pe_reads = (select_best_mismatch_strata(pe_reads[0]),
select_best_mismatch_strata(pe_reads[1]))
#
# now we can create all valid combinations of read1/read2 as putative
# discordant read pairs
#
gene_pairs, genome_pairs, combo_pairs = \
find_discordant_pairs(pe_reads, tid_genome_map, library_type)
if len(gene_pairs) > 0 or len(genome_pairs) > 0:
return gene_pairs, genome_pairs, []
elif len(combo_pairs) > 0:
return combo_pairs, [], []
# last resort suggests that there are some complex read mappings that
# don't make sense and cannot be explained, warranting further
# investigation
return [], [], pe_reads
def classify_read_pairs(pe_reads, max_isize, library_type, tid_tx_map):
"""
examines all the alignments of a single fragment and tries to find ways
to pair reads together.
annotates all read pairs with an integer tag corresponding to a value
in the DiscordantTags class
returns a tuple containing 3 lists:
1) concordant (r1,r2) pairs
2) discordant (r1,r2) pairs
3) unpaired reads
"""
# to satisfy library type reads must either be on
# same strand or opposite strands
concordant_tx_pairs = []
discordant_tx_pairs = []
concordant_cluster_pairs = []
discordant_cluster_pairs = []
#
# first, try to pair reads that map to the same transcript or
# cluster or overlapping transcripts
#
same_strand = LibraryTypes.same_strand(library_type)
refdict, clusterdict = map_reads_to_references(pe_reads, tid_tx_map)
found_pair = False
for tid, tid_pe_reads in refdict.iteritems():
# check if there are alignments involving both reads in a pair
if len(tid_pe_reads[0]) == 0 or len(tid_pe_reads[1]) == 0:
# no paired alignments exist at this reference
continue
for r1 in tid_pe_reads[0]:
for r2 in tid_pe_reads[1]:
# read strands must agree with library type
strand_match = (same_strand == (
r1.is_reverse == r2.is_reverse))
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
# this is a hit to same transcript (gene)
# pair the reads if strand comparison is correct
if strand_match:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.CONCORDANT_TX)
]
concordant_tx_pairs.append((cr1, cr2))
else:
# hit to same gene with wrong strand, which
# could happen in certain wacky cases
tags = [(DISCORDANT_TAG_NAME,
DiscordantTags.DISCORDANT_STRAND_TX)]
discordant_tx_pairs.append((cr1, cr2))
pair_reads(cr1, cr2, tags)
# at this point, if we have not been able to find a suitable way
# to pair the reads, then search within the transcript cluster
if not found_pair:
for cluster_id, cluster_pe_reads in clusterdict.iteritems():
# check if there are alignments involving both reads in a pair
if len(cluster_pe_reads[0]) == 0 or len(cluster_pe_reads[1]) == 0:
# no paired alignments in this transcript cluster
continue
for r1 in cluster_pe_reads[0]:
for r2 in cluster_pe_reads[1]:
# check strand compatibility
strand_match = (same_strand == (
r1.is_reverse == r2.is_reverse))
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
if strand_match:
tags = [(DISCORDANT_TAG_NAME,
DiscordantTags.CONCORDANT_GENE)]
concordant_cluster_pairs.append((cr1, cr2))
else:
tags = [(DISCORDANT_TAG_NAME,
DiscordantTags.DISCORDANT_STRAND_GENE)]
discordant_cluster_pairs.append((cr1, cr2))
pair_reads(cr1, cr2, tags)
# at this point, we have tried all combinations. if any paired reads
# are concordant then return them without considering discordant reads
gene_pairs = []
if len(concordant_tx_pairs) > 0:
gene_pairs = concordant_tx_pairs
elif len(concordant_cluster_pairs) > 0:
gene_pairs = concordant_cluster_pairs
if len(gene_pairs) > 0:
return gene_pairs, [], []
# if no concordant reads in transcripts, return any discordant reads
# that may violate strand requirements but still remain colocalized
# on the same gene/chromosome
gene_pairs = []
if len(discordant_tx_pairs) > 0:
gene_pairs = discordant_tx_pairs
elif len(discordant_cluster_pairs) > 0:
gene_pairs = discordant_cluster_pairs
if len(gene_pairs) > 0:
return gene_pairs, [], []
#
# at this point, no read pairings were found so the read is
# assumed to be discordant. now we can create all valid
# combinations of read1/read2 as putative discordant read pairs
#
pairs = find_discordant_pairs(pe_reads, library_type)
if len(pairs) > 0:
# sort valid pairs by sum of alignment score and retain the best
# scoring pairs
pairs = select_best_scoring_pairs(pairs)
return [], pairs, []
#
# no valid pairs could be found suggesting that these alignments are
# either artifacts or that the current transcript annotations do not
# support this pair
#
return [], [], pe_reads
def get_argument_parser():
parser = argparse.ArgumentParser(usage="%(prog)s [options] <index> "
"<mate1.fq> <mate2.fq> <output_dir>")
# required options
parser.add_argument("index_dir", default=None,
help="Location of chimerascan index directory")
parser.add_argument("read1", default=None,
help="Path to read1 FASTQ file")
parser.add_argument("read2", default=None,
help="Path to read2 FASTQ file")
parser.add_argument("output_dir", default=None,
help="Location of output files")
# standard options
parser.add_argument('--version', action='version',
version='%s' % __version__)
parser.add_argument("--config-file", dest="config_file",
help="Load parameters from a XML file "
"generated during a previous run ",
default=None)
parser.add_argument("-v", "--verbose", dest="verbose",
action="store_true", default=False,
help="enable verbose logging output "
"[default=%(default)s]")
parser.add_argument("-p", "--processors", dest="num_processors",
type=int, default=DEFAULT_NUM_PROCESSORS,
help="Number of processor cores to allocate to "
"chimerascan [default=%(default)s]")
parser.add_argument("--keep-tmp", dest="keep_tmp",
action="store_true",
default=DEFAULT_KEEP_TMP,
help="DO NOT delete intermediate files after "
"run [default=%(default)s]")
parser.add_argument("--rm-tmp", dest="keep_tmp",
action="store_false",
help="Delete intermediate files after run "
"[default=%s]" % str(not DEFAULT_KEEP_TMP))
parser.add_argument("--quals", dest="quals",
choices=FASTQ_QUAL_FORMATS,
default=DEFAULT_FASTQ_QUAL_FORMAT, metavar="FMT",
help="FASTQ quality score format "
"[default=%(default)s]")
parser.add_argument('--library-type', dest="library_type",
choices=LibraryTypes.choices(),
default=DEFAULT_LIBRARY_TYPE,
help="Library type [default=%(default)s]")
parser.add_argument("--isize-mean", dest="isize_mean", type=int,
default=DEFAULT_ISIZE_MEAN, metavar="N",
help="Mean insert size to sample from when "
"insert size distribution cannot be determined "
"empirically [default=%(default)s]")
parser.add_argument("--isize-stdev", dest="isize_stdev", type=float,
default=DEFAULT_ISIZE_STDEV, metavar="N",
help="Insert size standard deviation to sample "
"from when insert size distribution cannot be "
"determined empirically [default=%(default)s]")
parser.add_argument("--trim5", type=int, dest="trim5",
default=DEFAULT_TRIM5, metavar="N",
help="Trim N bases from 5' end of read")
parser.add_argument("--trim3", type=int, dest="trim3",
default=DEFAULT_TRIM3, metavar="N",
help="Trim N bases from 3' end of read")
parser.add_argument("--min-fragment-length", type=int,
dest="min_fragment_length",
default=config.DEFAULT_MIN_FRAG_LENGTH,
help="Smallest expected fragment length "
"[default=%(default)s]")
parser.add_argument("--max-fragment-length", type=int,
dest="max_fragment_length",
default=config.DEFAULT_MAX_FRAG_LENGTH,
help="Largest expected fragment length (reads "
"less than this fragment length are assumed to "
"be unspliced and contiguous) "
"[default=%(default)s]")
parser.add_argument("--segment-length", type=int,
dest="segment_length",
default=DEFAULT_SEGMENT_LENGTH,
metavar="N",
help="Override size of soft-clipped read "
"segments during discordant alignment phase "
"(determined empirically by default)")
parser.add_argument("--multihits", type=int,
dest="max_multihits",
default=config.DEFAULT_MAX_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-multihits", type=int,
dest="local_multihits",
default=config.DEFAULT_LOCAL_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-anchor-length", type=int,
dest="local_anchor_length",
default=config.DEFAULT_LOCAL_ANCHOR_LENGTH,
metavar="N",
help="Number of bases that read must span "
"on each side of a chimera to be considered "
"a valid breakpoint read")
# filtering options
group = parser.add_argument_group('Filtering options')
group.add_argument("--filter-num-frags", type=float,
default=config.DEFAULT_FILTER_FRAGS,
dest="filter_num_frags", metavar="N",
help="Filter chimeras with less than N "
"aligned fragments [default=%(default)s]")
group.add_argument("--filter-allele-fraction", type=float,
default=config.DEFAULT_FILTER_ALLELE_FRACTION,
dest="filter_allele_fraction", metavar="X",
help="Filter chimeras with expression less than "
"the specified fraction of the total expression "
"level [default=%(default)s")
group.add_argument("--mask-biotypes-file", default="",
dest="mask_biotypes_file",
help="File containing list of gene biotypes "
"to ignore (ex. pseudogenes, rRNA)")
group.add_argument("--mask-rnames-file", default="",
dest="mask_rnames_file",
help="File containing list of reference names "
"to ignore (ex. MT or chrM)")
# filtering options
return parser
def get_argument_parser():
parser = argparse.ArgumentParser(usage="%(prog)s [options] <index> "
"<mate1.fq> <mate2.fq> <output_dir>")
# required options
parser.add_argument("index_dir",
default=None,
help="Location of chimerascan index directory")
parser.add_argument("read1",
default=None,
help="Path to read1 FASTQ file")
parser.add_argument("read2",
default=None,
help="Path to read2 FASTQ file")
parser.add_argument("output_dir",
default=None,
help="Location of output files")
# standard options
parser.add_argument('--version',
action='version',
version='%s' % __version__)
parser.add_argument("--config-file",
dest="config_file",
help="Load parameters from a XML file "
"generated during a previous run ",
default=None)
parser.add_argument("-v",
"--verbose",
dest="verbose",
action="store_true",
default=False,
help="enable verbose logging output "
"[default=%(default)s]")
parser.add_argument("-p",
"--processors",
dest="num_processors",
type=int,
default=DEFAULT_NUM_PROCESSORS,
help="Number of processor cores to allocate to "
"chimerascan [default=%(default)s]")
parser.add_argument("--keep-tmp",
dest="keep_tmp",
action="store_true",
default=DEFAULT_KEEP_TMP,
help="DO NOT delete intermediate files after "
"run [default=%(default)s]")
parser.add_argument("--rm-tmp",
dest="keep_tmp",
action="store_false",
help="Delete intermediate files after run "
"[default=%s]" % str(not DEFAULT_KEEP_TMP))
parser.add_argument("--quals",
dest="quals",
choices=FASTQ_QUAL_FORMATS,
default=DEFAULT_FASTQ_QUAL_FORMAT,
metavar="FMT",
help="FASTQ quality score format "
"[default=%(default)s]")
parser.add_argument('--library-type',
dest="library_type",
choices=LibraryTypes.choices(),
default=DEFAULT_LIBRARY_TYPE,
help="Library type [default=%(default)s]")
parser.add_argument("--isize-mean",
dest="isize_mean",
type=int,
default=DEFAULT_ISIZE_MEAN,
metavar="N",
help="Mean insert size to sample from when "
"insert size distribution cannot be determined "
"empirically [default=%(default)s]")
parser.add_argument("--isize-stdev",
dest="isize_stdev",
type=float,
default=DEFAULT_ISIZE_STDEV,
metavar="N",
help="Insert size standard deviation to sample "
"from when insert size distribution cannot be "
"determined empirically [default=%(default)s]")
parser.add_argument("--trim5",
type=int,
dest="trim5",
default=DEFAULT_TRIM5,
metavar="N",
help="Trim N bases from 5' end of read")
parser.add_argument("--trim3",
type=int,
dest="trim3",
default=DEFAULT_TRIM3,
metavar="N",
help="Trim N bases from 3' end of read")
parser.add_argument("--min-fragment-length",
type=int,
dest="min_fragment_length",
default=config.DEFAULT_MIN_FRAG_LENGTH,
help="Smallest expected fragment length "
"[default=%(default)s]")
parser.add_argument("--max-fragment-length",
type=int,
dest="max_fragment_length",
default=config.DEFAULT_MAX_FRAG_LENGTH,
help="Largest expected fragment length (reads "
"less than this fragment length are assumed to "
"be unspliced and contiguous) "
"[default=%(default)s]")
parser.add_argument("--segment-length",
type=int,
dest="segment_length",
default=DEFAULT_SEGMENT_LENGTH,
metavar="N",
help="Override size of soft-clipped read "
"segments during discordant alignment phase "
"(determined empirically by default)")
parser.add_argument("--multihits",
type=int,
dest="max_multihits",
default=config.DEFAULT_MAX_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-multihits",
type=int,
dest="local_multihits",
default=config.DEFAULT_LOCAL_MULTIHITS,
metavar="N",
help="Maximum alignments allowed for each "
"discordant read")
parser.add_argument("--local-anchor-length",
type=int,
dest="local_anchor_length",
default=config.DEFAULT_LOCAL_ANCHOR_LENGTH,
metavar="N",
help="Number of bases that read must span "
"on each side of a chimera to be considered "
"a valid breakpoint read")
# filtering options
group = parser.add_argument_group('Filtering options')
group.add_argument("--filter-num-frags",
type=float,
default=config.DEFAULT_FILTER_FRAGS,
dest="filter_num_frags",
metavar="N",
help="Filter chimeras with less than N "
"aligned fragments [default=%(default)s]")
group.add_argument("--filter-allele-fraction",
type=float,
default=config.DEFAULT_FILTER_ALLELE_FRACTION,
dest="filter_allele_fraction",
metavar="X",
help="Filter chimeras with expression less than "
"the specified fraction of the total expression "
"level [default=%(default)s")
group.add_argument("--mask-biotypes-file",
default="",
dest="mask_biotypes_file",
help="File containing list of gene biotypes "
"to ignore (ex. pseudogenes, rRNA)")
group.add_argument("--mask-rnames-file",
default="",
dest="mask_rnames_file",
help="File containing list of reference names "
"to ignore (ex. MT or chrM)")
# filtering options
return parser
def classify_read_pairs(pe_reads, max_isize,
library_type,
tid_tx_map):
"""
examines all the alignments of a single fragment and tries to find ways
to pair reads together.
annotates all read pairs with an integer tag corresponding to a value
in the DiscordantTags class
returns a tuple containing 3 lists:
1) concordant (r1,r2) pairs
2) discordant (r1,r2) pairs
3) unpaired reads
"""
# to satisfy library type reads must either be on
# same strand or opposite strands
concordant_tx_pairs = []
discordant_tx_pairs = []
concordant_cluster_pairs = []
discordant_cluster_pairs = []
#
# first, try to pair reads that map to the same transcript or
# cluster or overlapping transcripts
#
same_strand = LibraryTypes.same_strand(library_type)
refdict, clusterdict = map_reads_to_references(pe_reads, tid_tx_map)
found_pair = False
for tid, tid_pe_reads in refdict.iteritems():
# check if there are alignments involving both reads in a pair
if len(tid_pe_reads[0]) == 0 or len(tid_pe_reads[1]) == 0:
# no paired alignments exist at this reference
continue
for r1 in tid_pe_reads[0]:
for r2 in tid_pe_reads[1]:
# read strands must agree with library type
strand_match = (same_strand == (r1.is_reverse == r2.is_reverse))
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
# this is a hit to same transcript (gene)
# pair the reads if strand comparison is correct
if strand_match:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.CONCORDANT_TX)]
concordant_tx_pairs.append((cr1,cr2))
else:
# hit to same gene with wrong strand, which
# could happen in certain wacky cases
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.DISCORDANT_STRAND_TX)]
discordant_tx_pairs.append((cr1,cr2))
pair_reads(cr1,cr2,tags)
# at this point, if we have not been able to find a suitable way
# to pair the reads, then search within the transcript cluster
if not found_pair:
for cluster_id, cluster_pe_reads in clusterdict.iteritems():
# check if there are alignments involving both reads in a pair
if len(cluster_pe_reads[0]) == 0 or len(cluster_pe_reads[1]) == 0:
# no paired alignments in this transcript cluster
continue
for r1 in cluster_pe_reads[0]:
for r2 in cluster_pe_reads[1]:
# check strand compatibility
strand_match = (same_strand == (r1.is_reverse == r2.is_reverse))
# these reads can be paired
found_pair = True
cr1 = copy_read(r1)
cr2 = copy_read(r2)
if strand_match:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.CONCORDANT_GENE)]
concordant_cluster_pairs.append((cr1,cr2))
else:
tags = [(DISCORDANT_TAG_NAME, DiscordantTags.DISCORDANT_STRAND_GENE)]
discordant_cluster_pairs.append((cr1,cr2))
pair_reads(cr1,cr2,tags)
# at this point, we have tried all combinations. if any paired reads
# are concordant then return them without considering discordant reads
gene_pairs = []
if len(concordant_tx_pairs) > 0:
gene_pairs = concordant_tx_pairs
elif len(concordant_cluster_pairs) > 0:
gene_pairs = concordant_cluster_pairs
if len(gene_pairs) > 0:
return gene_pairs, [], []
# if no concordant reads in transcripts, return any discordant reads
# that may violate strand requirements but still remain colocalized
# on the same gene/chromosome
gene_pairs = []
if len(discordant_tx_pairs) > 0:
gene_pairs = discordant_tx_pairs
elif len(discordant_cluster_pairs) > 0:
gene_pairs = discordant_cluster_pairs
if len(gene_pairs) > 0:
return gene_pairs, [], []
#
# at this point, no read pairings were found so the read is
# assumed to be discordant. now we can create all valid
# combinations of read1/read2 as putative discordant read pairs
#
pairs = find_discordant_pairs(pe_reads, library_type)
if len(pairs) > 0:
# sort valid pairs by sum of alignment score and retain the best
# scoring pairs
pairs = select_best_scoring_pairs(pairs)
return [], pairs, []
#
# no valid pairs could be found suggesting that these alignments are
# either artifacts or that the current transcript annotations do not
# support this pair
#
return [], [], pe_reads
