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)