def nw_hamming_metric(s1, s2, matrix='blosum62', open=3, extend=3):
"""Function applying Parasail's Needleman-Wuncsh Algorithm to align and
compute a Hamming Distance between any two sequences: number of
mismatched positions. Gaps count as a mismatch. Penalties and matrix
are used for alignment purposes, not in the distance calculation.
Parameters
----------
s1: string
string containing amino acid letters
s2: string
string containing amino acid letters
matrix : str
Attribute of parasail that names a substitution matrix
Returns
-------
D : float
distance between strings (Hamming Distance: number of mismatched positions)
Notes
-----
.. code-block:: python
xy = parasail.nw_stats(s1, s2, open=open, extend=extend, matrix=matrix)
xy_t = parasail.nw_trace(s1, s2, open=open, extend=extend, matrix=matrix)
hamming_distance = len(xy_t.traceback.comp)-xy.matches
return hamming_distance"""
p_matrix = getattr(parasail, matrix)
xy = parasail.nw_stats(s1, s2, open=open, extend=extend, matrix=p_matrix)
xy_t = parasail.nw_trace(s1, s2, open=open, extend=extend, matrix=p_matrix)
D = len(xy_t.traceback.comp)-xy.matches
return D
def get_cigar(s1, s2):
import parasail
if kind == "local":
result = parasail.sw_trace(s1, s2, 101, 10, parasail.pam100)
elif kind == "semi-global":
result = parasail.sg_trace(s1, s2, 101, 10, parasail.pam100)
elif kind == "global":
result = parasail.nw_trace(s1, s2, 101, 10, parasail.pam100)
else:
raise ValueError(
"The kind of alignment must be global, semi-global, or local.")
output = []
for i in result.cigar.seq:
#print(result.cigar.decode_len(i), result.cigar.decode_op(i).decode())
output += [
result.cigar.decode_len(i),
result.cigar.decode_op(i).decode()
]
for i in output[:0]:
float(i)
total_base = sum(output[:0])
# I'll convert to the canonical way of showing these things (e.g. SAMFILES - pysam)
# CIGAR type
ct = output[1::2]
# CIGAR length
cl = output[::2]
output = list(zip(ct, cl))
return output
def align(sequence1: str, sequence2: str):
""" Run the local pairwise alignment of two strings and return alignment data. """
result = parasail.nw_trace(sequence1, sequence2, GAP_OPEN_PENALTY,
GAP_EXTEND_PENALTY, parasail.blosum80)
cigar_text = result.cigar.decode
result = result.traceback.ref, result.traceback.query, result.score
return result
def align_affine(query: str, target: str, match_score: int, mismatch_cost: int,
gap_open_cost: int, gap_extension_cost: int) -> Cigar:
assert min(match_score, mismatch_cost, gap_open_cost,
gap_extension_cost) >= 0, "Specify positive integers"
return Cigar(
parasail.nw_trace(
query, target, gap_open_cost, gap_extension_cost,
parasail.matrix_create(
"ACGT", match_score,
-mismatch_cost)).cigar.decode.decode('utf-8'))
def align(
self,
x,
y,
open_penalty,
extend_penalty,
matrix=parasail.blosum62,
):
"""
Function that takes two strings and returns a
parasail result object. Uses:
parasail.nw_trace() - Needleman-Wunsch Global Alignment
parasail.blossum62 - blossum62 substitution matrix
The blosum62 matrix may warrant scrutiny:
Selecting the Right Similarity-Scoring Matrix
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3848038/
Parameters
----------
x : string
Amino acid string passed to arg s1 in parasail.sw_trace
y : string
Amino acid string passed to arg s2 in parasail.sw_trace
open_penalty: int
gap opening penalty
extent_penalty: int
gap extension penalty
matrix:
parasail.blossum62 - blossum62 substitution matrix
Returns
-------
r : parasail.bindings_v2.Result
Parasail result from sw_trace alignment
r.traceback.query,
Raises
------
"""
r = parasail.nw_trace(s1=x,
s2=y,
extend=extend_penalty,
open=open_penalty,
matrix=matrix)
return (r)
def pairwise_nw_trace_align(ref_seq,
query_seq,
gap_open=10,
gap_extension=1,
matrix=parasail.blosum62):
"""
:param ref_seq:
:param query_seq:
:param gap_open: Default 10
:param gap_extension: Default 1
:param matrix: Default BLOSUM62
:return: parasail result (includes a cigar which can be decoded)
"""
result = parasail.nw_trace(query_seq, ref_seq, gap_open, gap_extension,
matrix)
logging.debug("Parasail result %s" % result.cigar.decode)
return result
def hm_metric(s1, s2, matrix='blosum62', open=3, extend=3):
"""
Function applying Parasail's Needleman-Wuncsh Algorithm to allign and get
a Hamming Distance between any two sequences: number of mismatched positions
Parameters
----------
s1: string
string containing amino acid letters
s2: string
string containing amino acid letters
Returns
-------
D : float
distance between strings (Hamming Distance: number of mismatched positions)
Notes
-----
.. code-block:: python
xy = parasail.nw_stats(s1, s2, open=open, extend=extend, matrix=matrix)
xy_t = parasail.nw_trace(s1, s2, open=open, extend=extend, matrix=matrix)
hamming_distance = len(xy_t.traceback.comp)-xy.matches
return hamming_distance
"""
p_matrix = getattr(parasail, matrix)
xy = parasail.nw_stats(s1, s2, open=open, extend=extend, matrix=p_matrix)
xy_t = parasail.nw_trace(s1, s2, open=open, extend=extend, matrix=p_matrix)
D = len(xy_t.traceback.comp) - xy.matches
return D
def hm_matches(s1, s2, matrix=parasail.blosum62, open=3, extend=3):
xy = parasail.nw_stats(s1, s2, open=open, extend=extend, matrix=matrix)
xy_t = parasail.nw_trace(s1, s2, open=open, extend=extend, matrix=matrix)
return xy.matches