Method split

src/alphagenome/data/genome.py:832–868

Splits the variant into two at the anchor point. If the anchor point falls within the variant's reference sequence, the variant is split into two new variants: one upstream of the anchor and one downstream. If the anchor is outside the variant's reference sequence, the original vari

(self, anchor: int)

    )

  def split(self, anchor: int) -> tuple[Self | None, Self | None]:
    """Splits the variant into two at the anchor point.

    If the anchor point falls within the variant's reference sequence, the
    variant is split into two new variants: one upstream of the anchor and one
    downstream. If the anchor is outside the variant's reference sequence,
    the original variant is returned on the appropriate side, and None on the
    other.

    Example:
      position=       3
      ref:       ...[ A C ]...
      alt:       .....T G T C
      anchor=3         |
      returns:    (chr1:3:A>T, chr1:4:C>GTC)

    Args:
      anchor: The 0-based anchor point to split the variant.

    Returns:
      A tuple of the upstream and downstream variants. If the variant is only
      on one side of the anchorpoint, then None is returned.
    """
    if anchor <= self.start:
      return None, self.copy()
    elif anchor >= self.end:
      return self.copy(), None
    else:
      mid = anchor - self.start
      upstream, downstream = self.copy(), self.copy()
      upstream.reference_bases = self.reference_bases[:mid]
      upstream.alternate_bases = self.alternate_bases[:mid]

      downstream.position = anchor + 1
      downstream.reference_bases = self.reference_bases[mid:]
      downstream.alternate_bases = self.alternate_bases[mid:]
      return upstream, downstream


@dataclasses.dataclass