Single runs (#33)

* run_length function implemented, to count consecutive occurrences of a nucleic acid

* `single_runs` property & `_single_runs` attribute implemented

* single runs testcases added

* `CHANGELOG.md` updated

* apply feedbacks

* `README.md` updated

* unnecessary indent removed, docstring modified, README.md updated

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 ### Added
 - `equality` operator overload
 - `gc_clamp` property
+- `single_runs` property
 ## [0.1] - 2024-11-27
 ### Added
 - `MeltingTemperature` enum

README.md

@@ -87,6 +87,11 @@
 >>> primer1.gc_clamp
 1
 ```
+#### Single run length
+```pycon
+>>> primer1.single_runs
+{'A': 2, 'T': 0, 'C': 0, 'G': 2}
+```
 #### Melting temperature
 ```pycon
 >>> primer1.melting_temperature()
@@ -120,7 +125,7 @@ You can also join our discord server
 </a>
 
 ## References
-					
+
 <blockquote>1- <a href="http://biotools.nubic.northwestern.edu/OligoCalc.html">Oligo Calc: Oligonucleotide Properties Calculator</a></blockquote>
 
 <blockquote>2- Marmur, Julius, and Paul Doty. "Determination of the base composition of deoxyribonucleic acid from its thermal denaturation temperature." <i>Journal of molecular biology</i> 5.1 (1962): 109-118.</blockquote>

opr/functions.py

@@ -49,3 +49,25 @@ 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

@@ -10,7 +10,7 @@
 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
+from .functions import molecular_weight_calc, basic_melting_temperature_calc, gc_clamp_calc, single_run_length
 
 
 class MeltingTemperature(Enum):
@@ -41,6 +41,7 @@ def __init__(self, sequence):
         self._molecular_weight = None
         self._gc_content = None
         self._gc_clamp = None
+        self._single_runs = None
         self._melting_temperature = {
             MeltingTemperature.BASIC: None,
             MeltingTemperature.SALT_ADJUSTED: None,
@@ -217,6 +218,34 @@ def gc_clamp(self, _):
     def gc_clamp(self, _):
         raise OPRBaseError(PRIMER_NOT_REMOVABLE_ATTRIBUTE_ERROR)
 
+    @property
+    def single_runs(self):
+        """
+        Calculate Single Runs of the primer.
+
+        Run length refers to how many times a single base is repeated consecutively in the primer.
+
+        :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)
+        return self._single_runs
+
+    @single_runs.setter
+    def single_runs(self, _):
+        raise OPRBaseError(PRIMER_READ_ONLY_ATTRIBUTE_ERROR)
+
+    @single_runs.deleter
+    def single_runs(self, _):
+        raise OPRBaseError(PRIMER_NOT_REMOVABLE_ATTRIBUTE_ERROR)
+
     def melting_temperature(self, method=MeltingTemperature.BASIC):
         """
         Calculate(if needed) the melting temperature.

tests/test_calculations.py

@@ -40,3 +40,18 @@ def test_melt_temp_2(): #Reference: http://biotools.nubic.northwestern.edu/Oligo
     oprimer = Primer("ATCG")
     basic_melt_temp = oprimer.melting_temperature(method=MeltingTemperature.BASIC)
     assert round(basic_melt_temp,1) == 12
+
+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
+
+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
+
+def test_single_runs_3(): #Reference: https://www.oligoevaluator.com/OligoCalcServlet
+    oprimer = Primer("AAAAATTCGGGGATCCCCG")
+    runs = oprimer.single_runs
+    assert runs['A'] == 5 and runs['T'] == 2 and runs['C'] == 4 and runs['G'] == 4