purify_bedpe


def chr3d.peak_based.purifying.purify_bedpe(
    bedpe_file: str,
    fragment_index: FragmentIndex,
    output_kept: str,
    output_removed: str,
    compute_inserts: bool = True,
) -> Dict[str, Any]

Purify BEDPE file by removing reads from same-fragment PETs.

Parameters:

Parameter	Type	Description
bedpe_file	`str`	Input BEDPE file path
fragment_index	`FragmentIndex`	Fragment index for overlap lookup
output_kept	`str`	Output path for kept (purified) PETs
output_removed	`str`	Output path for removed (same-fragment) PETs
compute_inserts	`bool`	Compute insert sizes (default: `True`)

Returns:

Dict[str, Any] with purification statistics.

Example:


from chr3d.peak_based.purifying import FragmentIndex, purify_bedpe
 
frag_idx = FragmentIndex("restriction_fragments.bed")
 
stats = purify_bedpe(
    bedpe_file="dedup.bedpe",
    fragment_index=frag_idx,
    output_kept="purified.bedpe",
    output_removed="removed.bedpe",
)
 
print(f"Kept: {stats['n_kept']}, Removed: {stats['n_removed']}")