def processChunk( contig, regions ):
if contig == None: return
start = 0
end = contigs[contig]
regions = Intervals.combineIntervals( regions )
for xstart, xend in Intervals.complementIntervals( regions, start, end ):
locations.append( ("intergenic", "intergenic", contig, "+", xstart, xend, ".") )
def FilterEliminateOverlappingTranscripts(
exons, filter_exons,
eliminated_predictions, contig_sizes, options):
"""eliminate predictions that overlap or span a positive set of transcripts.
"""
eliminated = []
# convert list of filter exons into a list of ranges.
filter_ranges = getRangesFromExons(
filter_exons,
both_strands=options.filter_remove_spanning_both_strands,
contig_sizes=contig_sizes)
for k, r in filter_ranges.items():
filter_ranges[k] = Intervals.combineIntervals(map(lambda x: x[:2], r))
exon_ranges = getRangesFromExons(exons,
both_strands=False)
# and now go through exons and delete transcripts whose
# exons overlap one of the forbidden ranges
for k, ee in exon_ranges.items():
if k not in filter_ranges:
continue
ff = filter_ranges[k]
ee.sort()
# set exon index e and filter index f
# (both are indices in sorted lists)
e, f = 0, 0
while e < len(ee):
efrom, eto, id = ee[e]
# increment filter, such that its extent
# is larger than current range ee[e] to test.
while f < len(ff) and ff[f][1] < efrom:
f += 1
if f == len(ff):
break
if eto < ff[f][0]:
# no overlap
pass
else:
options.stdout.write(
"%s\t%s\n" % (id, "eliminated: filtered by %s:%i:%i" % (k, ff[f][0], ff[f][1])))
eliminated_predictions[id] = 0
eliminated.append((id, "f"))
e += 1
return eliminated
def FilterEliminateOverlappingTranscripts(exons, filter_exons,
eliminated_predictions, contig_sizes,
options):
"""eliminate predictions that overlap or span a positive set of transcripts.
"""
eliminated = []
# convert list of filter exons into a list of ranges.
filter_ranges = getRangesFromExons(
filter_exons,
both_strands=options.filter_remove_spanning_both_strands,
contig_sizes=contig_sizes)
for k, r in filter_ranges.items():
filter_ranges[k] = Intervals.combineIntervals(map(lambda x: x[:2], r))
exon_ranges = getRangesFromExons(exons, both_strands=False)
# and now go through exons and delete transcripts whose
# exons overlap one of the forbidden ranges
for k, ee in exon_ranges.items():
if k not in filter_ranges:
continue
ff = filter_ranges[k]
ee.sort()
# set exon index e and filter index f
# (both are indices in sorted lists)
e, f = 0, 0
while e < len(ee):
efrom, eto, id = ee[e]
# increment filter, such that its extent
# is larger than current range ee[e] to test.
while f < len(ff) and ff[f][1] < efrom:
f += 1
if f == len(ff):
break
if eto < ff[f][0]:
# no overlap
pass
else:
options.stdout.write("%s\t%s\n" %
(id, "eliminated: filtered by %s:%i:%i" %
(k, ff[f][0], ff[f][1])))
eliminated_predictions[id] = 0
eliminated.append((id, "f"))
e += 1
return eliminated
def processChunk(contig, regions):
if contig == None: return
start = 0
end = contigs[contig]
regions = Intervals.combineIntervals(regions)
for xstart, xend in Intervals.complementIntervals(regions, start, end):
locations.append(
("intergenic", "intergenic", contig, "+", xstart, xend, "."))
def transform_third_codon(start, end, intervals_with_gff):
"""transform: only return nucleotide positions in window (start, end)
that are in third codon position.
"""
intervals = []
for istart, iend, gff in intervals_with_gff:
if gff.frame == ".":
raise ValueError("need a frame for third codon positions.")
# frame = nucleotides from start to next codon
frame = int(gff.frame)
# to make life easier, convert to 0-based coordinates,
# with zero starting at first position in window
# re-arrange positions on negative strand
if Genomics.IsNegativeStrand(gff.strand):
# convert to negative strand coordinates counting from 0
coordinate_offset = end
reverse = True
istart, iend = end - iend, end - istart
else:
istart, iend = istart - start, iend - start
reverse = False
coordinate_offset = start
# make sure that you start on a second codon position and within window
if istart < 0:
frame = (frame + istart) % 3
istart = 0
if frame != 0:
istart -= (3 - frame)
istart += 2
iend = min(iend, end - start)
for x in range(istart, iend, 3):
if reverse:
c = coordinate_offset - x - 1
else:
c = coordinate_offset + x
intervals.append((c, c + 1))
return Intervals.combineIntervals(intervals)
def transform_third_codon(start, end, intervals_with_gff):
"""transform: only return nucleotide positions in window (start, end)
that are in third codon position.
"""
intervals = []
for istart, iend, gff in intervals_with_gff:
if gff.frame == ".":
raise ValueError("need a frame for third codon positions.")
# frame = nucleotides from start to next codon
frame = int(gff.frame)
# to make life easier, convert to 0-based coordinates,
# with zero starting at first position in window
# re-arrange positions on negative strand
if Genomics.IsNegativeStrand(gff.strand):
# convert to negative strand coordinates counting from 0
coordinate_offset = end
reverse = True
istart, iend = end - iend, end - istart
else:
istart, iend = istart - start, iend - start
reverse = False
coordinate_offset = start
# make sure that you start on a second codon position and within window
if istart < 0:
frame = (frame + istart) % 3
istart = 0
if frame != 0:
istart -= (3 - frame)
istart += 2
iend = min(iend, end - start)
for x in range(istart, iend, 3):
if reverse:
c = coordinate_offset - x - 1
else:
c = coordinate_offset + x
intervals.append((c, c + 1))
return Intervals.combineIntervals(intervals)
def transform_complement(start, end, intervals_with_gff):
y = Intervals.combineIntervals([(x[0], x[1]) for x in intervals_with_gff])
return Intervals.complementIntervals(y, start, end)
def transform_overlap(start, end, intervals_with_gff):
"""transform: overlap of intervals in x with y."""
y = Intervals.combineIntervals([(x[0], x[1]) for x in intervals_with_gff])
return Intervals.pruneIntervals(y, start, end)
def transform_complement(start, end, intervals_with_gff):
y = Intervals.combineIntervals(
map(lambda x: (x[0], x[1]), intervals_with_gff))
return Intervals.complementIntervals(y, start, end)
def transform_overlap(start, end, intervals_with_gff):
"""transform: overlap of intervals in x with y."""
y = Intervals.combineIntervals(
map(lambda x: (x[0], x[1]), intervals_with_gff))
return Intervals.pruneIntervals(y, start, end)
def transform_complement(start, end, intervals_with_gff):
y = Intervals.combineIntervals(
map(lambda x: (x[0], x[1]), intervals_with_gff))
return Intervals.complementIntervals(y, start, end)
def transform_overlap(start, end, intervals_with_gff):
"""transform: overlap of intervals in x with y."""
y = Intervals.combineIntervals(
map(lambda x: (x[0], x[1]), intervals_with_gff))
return Intervals.pruneIntervals(y, start, end)
def transform_complement(start, end, intervals_with_gff):
y = Intervals.combineIntervals(
[(x[0], x[1]) for x in intervals_with_gff])
return Intervals.complementIntervals(y, start, end)
def transform_overlap(start, end, intervals_with_gff):
"""transform: overlap of intervals in x with y."""
y = Intervals.combineIntervals(
[(x[0], x[1]) for x in intervals_with_gff])
return Intervals.pruneIntervals(y, start, end)
def processChunk(gene_id, contig, strand, frame, regions):
if gene_id is None:
return
for start, end in Intervals.combineIntervals(regions):
locations.append((gene_id, gene_id, contig, strand, start, end))
def processChunk(gene_id, contig, strand, frame, regions):
if gene_id == None: return
for start, end in Intervals.combineIntervals(regions):
locations.append((gene_id, gene_id, contig, strand, start, end))
