def _trim_all_sequences(aligned_sequences: AlignedDNAFASTAFormat,
trim_positions: dict) -> AlignedDNAFASTAFormat:
"""
Trim all sequences within given alignment based on provided positions.
Arguments:
aligned_sequences (AlignedDNAFASTAFormat): original, aligned sequences
trim_positions (dict): dictionary containing positions for trimming
Returns:
result (AlignedDNAFASTAFormat): trimmed aligned sequences
"""
result = AlignedDNAFASTAFormat()
with result.open() as out_fasta:
for seq in aligned_sequences.view(AlignedDNAIterator):
seq_trimmed = _trim_sequence(seq, trim_positions["start"],
trim_positions["end"])
seq_trimmed.write(out_fasta)
return result
def _locate_primer_positions(
alignment_with_primers: AlignedDNAFASTAFormat) -> dict:
"""
Identify position of each primer within the alignment.
Arguments:
alignment_with_primers (AlignedDNAFASTAFormat): sequence alignment
containing at least one aligned primer
Returns:
(dict): dictionary containing trimming positions
using 0-based indexing
"""
primers_aligned = dict()
for aln_seq in alignment_with_primers.view(DNAIterator):
if aln_seq.metadata["id"] in ["forward", "reverse"]:
primers_aligned[aln_seq.metadata["id"]] = (str(aln_seq))
primer_positions = dict()
for primer_id, primer_seq in primers_aligned.items():
primer_positions[primer_id] = {
'start':
next((i for i, nt in enumerate(primer_seq) if nt != "-")),
'end':
len(primer_seq) - next(
(i for i, nt in enumerate(primer_seq[::-1]) if nt != "-"))
}
pos_start, pos_end = _find_terminal_positions(primer_positions)
# not doing any validation like in _prepare_positions since none of
# the conditions checked there are possible to run into with the way
# _locate_primer_positions and _find_terminal_positions are implemented
return {"start": pos_start, "end": pos_end}
