Minor update (#47)

* remove `single_run_length` function

* refactored code to use `repeats` function

* return 1 instead of 0 for cosecutive mode (if the occurence number is 1)

* minor refactorings

* update testcases to follow the new rule

* `CHANGELOG.md` updated

* `README.md` updated

* `CHANGELOG.md` updated

CHANGELOG.md

@@ -11,7 +11,10 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - `repeats` method
 - `name` property
 ### Changed
+- `single_runs` property updated
 - Test system modified
+### Removed
+- `single_run_length` function
 ## [0.2] - 2025-01-09
 ### Added
 - `__eq__` overload

README.md

@@ -90,12 +90,12 @@
 #### Single run length
 ```pycon
 >>> primer1.single_runs
-{'A': 2, 'T': 0, 'C': 0, 'G': 2}
+{'A': 2, 'T': 1, 'C': 1, 'G': 2}
 ```
 #### Double run length
 ```pycon
 >>> primer1.double_runs
-{'AT': 0, 'AG': 4, 'AC': 0, 'TA': 0, 'TG': 0, 'TC': 0, 'GA': 5, 'GT': 0, 'GC': 0, 'CA': 0, 'CT': 0, 'CG': 0}
+{'TA': 1, 'TC': 0, 'TG': 1, 'AT': 0, 'AC': 1, 'AG': 2, 'CT': 1, 'CA': 0, 'CG': 1, 'GT': 1, 'GA': 1, 'GC': 0}
 ```
 #### Repeats
 ```pycon
@@ -104,7 +104,7 @@
 ```
 ```pycon
 >>> primer1.repeats(sequence="GG", consecutive=True)
-0
+1
 ```
 #### Melting temperature
 ```pycon

opr/functions.py

@@ -49,26 +49,3 @@ def gc_clamp_calc(sequence):
     if len(sequence) < 5:
         return 0
     return sequence[-5:].count('G') + sequence[-5:].count('C')
-
-
-def single_run_length(sequence, base):
-    """
-    Calculate the maximum consecutive occurrence of a Nucleic acid (base) in a sequence.
-
-    :param sequence: primer sequence
-    :type sequence: str
-    :param base: target Nucleic acid
-    :type base: str
-    :return: the length of maximum consecutive occurrence
-    """
-    max_length = 0
-    current_length = 0
-    for c in sequence:
-        if c == base:
-            current_length += 1
-            max_length = max(max_length, current_length)
-        else:
-            current_length = 0
-    if max_length == 1:
-        return 0
-    return max_length

opr/primer.py

@@ -11,7 +11,7 @@
 from .params import DNA_COMPLEMENT_MAP
 from .params import PRIMER_ADDITION_ERROR, PRIMER_MULTIPLICATION_ERROR
 from .params import PRIMER_MELTING_TEMPERATURE_NOT_IMPLEMENTED_ERROR
-from .functions import molecular_weight_calc, basic_melting_temperature_calc, gc_clamp_calc, single_run_length
+from .functions import molecular_weight_calc, basic_melting_temperature_calc, gc_clamp_calc
 
 
 class MeltingTemperature(Enum):
@@ -226,14 +226,9 @@ def single_runs(self):
         :return: single runs of the primer
         """
         if self._single_runs is None:
-            self._single_runs = {
-                'A': 0,
-                'T': 0,
-                'C': 0,
-                'G': 0,
-            }
-            for base in self._single_runs:
-                self._single_runs[base] = single_run_length(self._sequence, base)
+            self._single_runs = {}
+            for base in VALID_BASES:
+                self._single_runs[base] = self.repeats(base, consecutive=True)
         return self._single_runs
 
     @property
@@ -247,8 +242,8 @@ def double_runs(self):
         """
         if self._double_runs is None:
             pairs = [''.join(pair) for pair in itertools.product(VALID_BASES, repeat=2) if pair[0] != pair[1]]
-            counts = {pair: 0 for pair in pairs}
-            for pair in counts:
+            counts = {}
+            for pair in pairs:
                 counts[pair] = self.repeats(pair, consecutive=True)
             self._double_runs = counts
         return self._double_runs
@@ -267,8 +262,6 @@ def repeats(self, sequence, consecutive=False):
             pattern = f"(?:{re.escape(sequence)})+"
             matches = re.findall(f"({pattern})+", self.sequence)
             result = max((len(match) // len(sequence) for match in matches), default=0)
-            if result == 1:
-                result = 0
             return result
         else:
             return self.sequence.count(sequence)

tests/test_calculations.py

@@ -53,13 +53,13 @@ def test_melt_temp_2():  # Reference: http://biotools.nubic.northwestern.edu/Oli
 def test_single_runs_1():  # Reference: https://www.oligoevaluator.com/OligoCalcServlet
     oprimer = Primer("ATCGATCG")
     runs = oprimer.single_runs
-    assert runs['A'] == 0 and runs['T'] == 0 and runs['C'] == 0 and runs['G'] == 0
+    assert runs['A'] == 1 and runs['T'] == 1 and runs['C'] == 1 and runs['G'] == 1
 
 
 def test_single_runs_2():  # Reference: https://www.oligoevaluator.com/OligoCalcServlet
     oprimer = Primer("ATTCGATCCCCG")
     runs = oprimer.single_runs
-    assert runs['A'] == 0 and runs['T'] == 2 and runs['C'] == 4 and runs['G'] == 0
+    assert runs['A'] == 1 and runs['T'] == 2 and runs['C'] == 4 and runs['G'] == 1
 
 
 def test_single_runs_3():  # Reference: https://www.oligoevaluator.com/OligoCalcServlet
@@ -71,20 +71,20 @@ def test_single_runs_3():  # Reference: https://www.oligoevaluator.com/OligoCalc
 def test_double_runs():
     p1 = Primer("ATATCGAACACACACACA")
     double_runs = p1.double_runs
-    print(double_runs)
     true_answer = {
-        'GT': 0,
-        'CA': 5,
         'AT': 2,
-        'TA': 0,
-        'GC': 0,
-        'GA': 0,
+        'AC': 5,
         'AG': 0,
+        'TA': 1,
+        'TC': 1,
         'TG': 0,
-        'CG': 0,
-        'TC': 0,
-        'AC': 5,
-        'CT': 0}
+        'CA': 5,
+        'CT': 0,
+        'CG': 1,
+        'GA': 1,
+        'GT': 0,
+        'GC': 0
+        }
     assert len(true_answer) == len(double_runs) and all(double_runs[pair] == true_answer[pair] for pair in double_runs)
 
 
@@ -94,8 +94,8 @@ def test_repeats_1():
         p.repeats(sequence="A", consecutive=False) == 1 and
         p.repeats(sequence="AT", consecutive=False) == 1 and
         p.repeats(sequence="AC", consecutive=False) == 0 and
-        p.repeats(sequence="A", consecutive=True) == 0 and
-        p.repeats(sequence="AT", consecutive=True) == 0
+        p.repeats(sequence="A", consecutive=True) == 1 and
+        p.repeats(sequence="AT", consecutive=True) == 1
     )