mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-02-25 18:38:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

doctesting lowercase upcase empty string cases

Browse Source
This commit is contained in:
Belhadj Ahmed Walid 2023-08-22 18:08:55 +01:00
parent 8e56b7e2c5
commit d8a6bcba6a
1 changed files with 38 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
dynamic_programming/smith_waterman.py
View File

@ -12,16 +12,22 @@ GAP = -2
def score_function(source_char: str, target_char: str) -> int: def score_function(source_char: str, target_char: str) -> int:
""" """
Calculate the score for a character pair based on whether they match or mismatch. Calculate the score for a character pair based on whether they match or mismatch.
Returns 1 if the characters match, -1 if they mismatch. Returns 1 if the characters match, -1 if they mismatch, and -2 if either of the
characters is a gap.
>>> score_function('A', 'A') >>> score_function('A', 'A')
1 1
>>> score_function('A', 'C') >>> score_function('A', 'C')
-1 -1
>>> score_function('-', 'A')
-2
>>> score_function('A', '-')
-2
>>> score_function('-', '-')
-2
""" """
if source_char == target_char: if "-" in (source_char, target_char):
return MATCH return GAP
else: return MATCH if source_char == target_char else MISMATCH
return MISMATCH
def smith_waterman(query: str, subject: str) -> list[list[int]]: def smith_waterman(query: str, subject: str) -> list[list[int]]:
@ -31,7 +37,20 @@ def smith_waterman(query: str, subject: str) -> list[list[int]]:
corresponds to the score of the best local alignment ending at that point. corresponds to the score of the best local alignment ending at that point.
>>> smith_waterman('ACAC', 'CA') >>> smith_waterman('ACAC', 'CA')
[[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]] [[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]]
>>> smith_waterman('acac', 'ca')
[[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]]
>>> smith_waterman('ACAC', 'ca')
[[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]]
>>> smith_waterman('acac', 'CA')
[[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]]
>>> smith_waterman('ACAC', '')
[[0], [0], [0], [0], [0]]
>>> smith_waterman('', 'CA')
[[0, 0, 0]]
""" """
# make both query and subject uppercase
query = query.upper()
subject = subject.upper()
# Initialize score matrix # Initialize score matrix
m = len(query) m = len(query)
@ -58,14 +77,26 @@ def traceback(score: list[list[int]], query: str, subject: str) -> str:
until a 0 score is found. Returns the alignment strings. until a 0 score is found. Returns the alignment strings.
>>> traceback([[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]], 'ACAC', 'CA') >>> traceback([[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]], 'ACAC', 'CA')
'CAC\nCA-' 'CAC\nCA-'
>>> traceback([[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]], 'acac', 'ca')
'CAC\nCA-'
>>> traceback([[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]], 'ACAC', 'ca')
'CAC\nCA-'
>>> traceback([[0, 0, 0], [0, 0, 1], [0, 1, 0], [0, 0, 2], [0, 1, 0]], 'acac', 'CA')
'CAC\nCA-'
>>> traceback([[0, 0, 0]], 'ACAC', '')
''
""" """
# make both query and subject uppercase
query = query.upper()
subject = subject.upper()
# Traceback logic to find optimal alignment # Traceback logic to find optimal alignment
i = len(query) i = len(query)
j = len(subject) j = len(subject)
align1 = "" align1 = ""
align2 = "" align2 = ""
# guard against empty query or subject
if i == 0 or j == 0:
return ""
while i > 0 and j > 0: while i > 0 and j > 0:
if score[i][j] == score[i - 1][j - 1] + score_function( if score[i][j] == score[i - 1][j - 1] + score_function(
query[i - 1], subject[j - 1] query[i - 1], subject[j - 1]