def _make_ref_map(self):
if self.aln_map and self.aln_loc is not None:
return
ref_record = self._cached
record_start = ref_record["dnafrag_start"]
record_end = ref_record["dnafrag_end"]
record_strand = ref_record["dnafrag_strand"]
block_loc = self.genome.make_location(
coord_name=ref_record["name"],
start=record_start,
end=record_end,
strand=record_strand,
ensembl_coord=True,
)
ref_location = self.parent.ref_location
relative_start = ref_location.start - block_loc.start
relative_end = relative_start + len(ref_location)
if block_loc.strand != 1:
relative_start = len(block_loc) - relative_end
relative_end = relative_start + len(ref_location)
aln_map, aln_loc = cigar.slice_cigar(self.cigar_line,
relative_start,
relative_end,
by_align=False)
self.aln_map = aln_map
self.aln_loc = aln_loc
region_loc = ref_location.copy()
region_loc.strand = block_loc.strand
region = self.genome.get_region(region=region_loc)
self._cached["region"] = region
def test_slice_cigar(self):
"""test slicing cigars"""
for start, end in self.slices:
# test by_align = True
map1, loc1 = slice_cigar(self.cigar_text, start, end)
ori1 = self.aln_seq[start:end]
if loc1:
slicealn1 = self.seq[loc1[0] : loc1[1]].gapped_by_map(map1)
assert ori1 == slicealn1
else:
assert map1.length == len(ori1)
# test by_align = False
map2, loc2 = slice_cigar(self.cigar_text, start, end, by_align=False)
slicealn2 = self.seq[start:end].gapped_by_map(map2)
ori2 = self.aln_seq[loc2[0] : loc2[1]]
assert slicealn2 == ori2
def _make_map_from_ref(self):
# this is the 'other' species
if self.aln_loc and self.aln_map is not None:
return
record = self._cached
aln_map, aln_loc = cigar.slice_cigar(
self.cigar_line,
self.parent.cigar_start,
self.parent.cigar_end,
by_align=True,
)
if not aln_loc:
self._cached["region"] = self.NULL_VALUE
return
self.aln_map = aln_map
self.aln_loc = aln_loc # probably unnecesary to store??
# we make a loc for the aligned region
block_loc = self.genome.make_location(
coord_name=record["name"],
start=record["dnafrag_start"],
end=record["dnafrag_end"],
strand=record["dnafrag_strand"],
ensembl_coord=True,
)
relative_start = aln_loc[0]
relative_end = aln_loc[1]
# new location with correct length ensembl_start
loc = block_loc.copy()
loc.end = loc.start + (relative_end - relative_start)
if block_loc.strand != 1:
shift = len(block_loc) - relative_end
else:
shift = relative_start
loc = loc.shifted(shift)
region = self.genome.get_region(region=loc)
self._cached["region"] = region