Chemical Formula & Minor Edits

CHANGELOG.md

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

opr/functions.py

@@ -1,6 +1,9 @@
 # -*- coding: utf-8 -*-
 """OPR functions."""
-from .params import A_WEIGHT, T_WEIGHT, C_WEIGHT, G_WEIGHT, ANHYDROUS_MOLECULAR_WEIGHT_CONSTANT
+from .params import A_WEIGHT, T_WEIGHT, C_WEIGHT, G_WEIGHT
+from .params import ANHYDROUS_MOLECULAR_WEIGHT_CONSTANT
+from .params import CHEMICAL_FORMULA_FORMAT, CHEMICAL_FORMULA_FORMAT_SHORT
+from .params import CHEMICAL_FORMULA_BASES, CHEMICAL_FORMULA_WATER, CHEMICAL_FORMULA_PHOSPHODIESTER
 
 
 def molecular_weight_calc(sequence):
@@ -36,3 +39,47 @@ def basic_melting_temperature_calc(sequence):
     else:
         melting_temperature = 64.9 + 41 * ((g_count + c_count - 16.4) / (a_count + t_count + g_count + c_count))
     return melting_temperature
+
+
+def gc_content_calc(sequence):
+    """
+    Calculate gc content.
+
+    :param sequence: primer nucleotides sequence
+    :type sequence: str
+    :return: gc content as float
+    """
+    gc_count = sequence.count('G') + sequence.count('C')
+    return gc_count / len(sequence)
+
+
+def chemical_formula_calc(sequence):
+    """
+    Calculate the chemical formula.
+
+    :param sequence: primer nucleotides sequence
+    :type sequence: str
+    :return: chemical formula as dict
+    """
+    count_mapping = {
+        'A': sequence.count('A'),
+        'T': sequence.count('T'),
+        'C': sequence.count('C'),
+        'G': sequence.count('G'),
+    }
+    n = len(sequence)
+
+    carbon_count = sum([count_mapping[x] * y['C'] for x, y in CHEMICAL_FORMULA_BASES.items()])
+    hydrogen_count = sum([count_mapping[x] * y['H'] for x, y in CHEMICAL_FORMULA_BASES.items()])
+    nitrogen_count = sum([count_mapping[x] * y['N'] for x, y in CHEMICAL_FORMULA_BASES.items()])
+    oxygen_count = sum([count_mapping[x] * y['O'] for x, y in CHEMICAL_FORMULA_BASES.items()])
+    # A water is removed from the formula for each phosphodiester bond
+    hydrogen_count -= (n - 1) * CHEMICAL_FORMULA_WATER['H']
+    hydrogen_count += (n - 1) * CHEMICAL_FORMULA_PHOSPHODIESTER['H']
+    oxygen_count -= (n - 1) * CHEMICAL_FORMULA_WATER['O']
+    oxygen_count += (n - 1) * CHEMICAL_FORMULA_PHOSPHODIESTER['O']
+    phosphor_count = (n - 1) * CHEMICAL_FORMULA_PHOSPHODIESTER['P']
+
+    if len(sequence) == 1:
+        return CHEMICAL_FORMULA_FORMAT_SHORT.format(carbon_count, hydrogen_count, nitrogen_count, oxygen_count)
+    return CHEMICAL_FORMULA_FORMAT.format(carbon_count, hydrogen_count, nitrogen_count, oxygen_count, phosphor_count)

opr/params.py

@@ -3,6 +3,28 @@
 OPR_VERSION = "0.1"
 VALID_BASES = set('ATCG')
 DNA_COMPLEMENT_MAP = {"A": "T", "C": "G", "G": "C", "T": "A"}
+CHEMICAL_FORMULA_BASES = {
+    'A': {
+        'C': 10, 'H': 15, 'N': 5, 'O': 4,
+    },
+    'T': {
+        'C': 10, 'H': 16, 'N': 2, 'O': 6,
+    },
+    'C': {
+        'C': 9, 'H': 15, 'N': 3, 'O': 5,
+    },
+    'G': {
+        'C': 10, 'H': 15, 'N': 5, 'O': 5,
+    },
+}
+CHEMICAL_FORMULA_WATER = {
+    'H': 2, 'O': 1,
+}
+CHEMICAL_FORMULA_PHOSPHODIESTER = {
+    'H': 3, 'O': 4, 'P': 1,
+}
+CHEMICAL_FORMULA_FORMAT = "C{0}H{1}N{2}O{3}P{4}"
+CHEMICAL_FORMULA_FORMAT_SHORT = "C{0}H{1}N{2}O{3}"
 
 PRIMER_LOWER_LENGTH = 18
 PRIMER_HIGHEST_LENGTH = 30
@@ -16,9 +38,11 @@
 ANHYDROUS_MOLECULAR_WEIGHT_CONSTANT = 61.96
 
 PRIMER_SEQUENCE_TYPE_ERROR = "Primer sequence should be a string variable."
-PRIMER_SEQUENCE_LENGTH_WARNING = "The recommended range for primer length is between 18 and 30."
+PRIMER_SEQUENCE_LENGTH_WARNING = "The recommended range for primer length is between {0} and {1}.".format(
+    PRIMER_LOWER_LENGTH, PRIMER_HIGHEST_LENGTH)
 PRIMER_SEQUENCE_VALID_BASES_ERROR = "Primer sequence should only contain the nucleotide bases A, T, C, and G."
-PRIMER_SEQUENCE_VALID_GC_CONTENT_RANGE_WARNING = "The recommended range for GC content is between 30% and 80%."
+PRIMER_SEQUENCE_VALID_GC_CONTENT_RANGE_WARNING = "The recommended range for GC content is between {0}% and {1}%.".format(
+    PRIMER_LOWEST_GC_RANGE * 100, PRIMER_HIGHEST_GC_RANGE * 100)
 PRIMER_READ_ONLY_ATTRIBUTE_ERROR = "This attribute is read-only."
 PRIMER_NOT_REMOVABLE_ATTRIBUTE_ERROR = "This attribute is not removable."
 

opr/primer.py

@@ -4,13 +4,17 @@
 from warnings import warn
 from .errors import OPRBaseError
 from .params import VALID_BASES
-from .params import PRIMER_SEQUENCE_TYPE_ERROR, PRIMER_SEQUENCE_LENGTH_WARNING, PRIMER_SEQUENCE_VALID_BASES_ERROR, PRIMER_SEQUENCE_VALID_GC_CONTENT_RANGE_WARNING
-from .params import PRIMER_LOWER_LENGTH, PRIMER_HIGHEST_LENGTH, PRIMER_LOWEST_GC_RANGE, PRIMER_HIGHEST_GC_RANGE
+from .params import PRIMER_SEQUENCE_TYPE_ERROR, PRIMER_SEQUENCE_VALID_BASES_ERROR
 from .params import PRIMER_READ_ONLY_ATTRIBUTE_ERROR, PRIMER_NOT_REMOVABLE_ATTRIBUTE_ERROR
-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 .params import PRIMER_SEQUENCE_LENGTH_WARNING, PRIMER_SEQUENCE_VALID_GC_CONTENT_RANGE_WARNING
+from .params import PRIMER_LOWER_LENGTH, PRIMER_HIGHEST_LENGTH
+from .params import PRIMER_LOWEST_GC_RANGE, PRIMER_HIGHEST_GC_RANGE
+from .params import DNA_COMPLEMENT_MAP
+
 from .functions import molecular_weight_calc, basic_melting_temperature_calc
+from .functions import gc_content_calc, chemical_formula_calc
 
 
 class MeltingTemperature(Enum):
@@ -45,6 +49,7 @@ def __init__(self, sequence):
             MeltingTemperature.SALT_ADJUSTED: None,
             MeltingTemperature.NEAREST_NEIGHBOR: None,
         }
+        self._chemical_formula = None
 
     def __len__(self):
         """
@@ -182,9 +187,9 @@ def gc_content(self):
 
         :return: gc content
         """
-        if self._gc_content is None:
-            gc_count = self._sequence.count('G') + self._sequence.count('C')
-            self._gc_content = gc_count / len(self._sequence)
+        if self._gc_content is not None:
+            return self._gc_content
+        self._gc_content = gc_content_calc(self._sequence)
         if self._gc_content < PRIMER_LOWEST_GC_RANGE or self._gc_content > PRIMER_HIGHEST_GC_RANGE:
             warn(PRIMER_SEQUENCE_VALID_GC_CONTENT_RANGE_WARNING, RuntimeWarning)
         return self._gc_content
@@ -196,6 +201,26 @@ def gc_content(self, _):
     @gc_content.deleter
     def gc_content(self, _):
         raise OPRBaseError(PRIMER_NOT_REMOVABLE_ATTRIBUTE_ERROR)
+
+    @property
+    def chemical_formula(self):
+        """
+        Calculate the chemical formula.
+
+        :return: chemical formula
+        """
+        if self._chemical_formula is not None:
+            return self._chemical_formula
+        self._chemical_formula = chemical_formula_calc(self._sequence)
+        return self._chemical_formula
+
+    @chemical_formula.setter
+    def chemical_formula(self, _):
+        raise OPRBaseError(PRIMER_READ_ONLY_ATTRIBUTE_ERROR)
+
+    @chemical_formula.deleter
+    def chemical_formula(self, _):
+        raise OPRBaseError(PRIMER_NOT_REMOVABLE_ATTRIBUTE_ERROR)
 
     def melting_temperature(self, method=MeltingTemperature.BASIC):
         """

tests/test_operations.py

@@ -33,6 +33,12 @@ def test_complement_3(): #Reference: https://www.qiagen.com/us/applications/enzy
     oprimer.complement(inplace=True)
     assert oprimer.sequence == "TAGCCGATTTAGCCGATT"
 
+
+def test_chemical_formula(): #Reference: https://atdbio.com/tools/oligo-calculator
+    oprimer = Primer("ATCGGCTAAATCGGCTAA")
+    assert oprimer.chemical_formula == "C176H221N70O104P17"
+
+
 def test_length():
     oprimer = Primer("ATCGGCTAAATCGGCTAA")
     assert len(oprimer) == 18