test : tests added.

opr/functions.py

@@ -3,7 +3,7 @@
 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
+from .params import CHEMICAL_FORMULA_BASES, CHEMICAL_FORMULA_WATER, CHEMICAL_FORMULA_PHOSPHODIESTER
 
 
 def molecular_weight_calc(sequence):
@@ -67,14 +67,19 @@ def chemical_formula_calc(sequence):
         '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()])
-    hydrogen_count -= (len(sequence) - 1) * CHEMICAL_FORMULA_WATER['H']
     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()])
-    oxygen_count += (len(sequence) - 1) * CHEMICAL_FORMULA_WATER['O']
+    # 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, len(sequence) - 1)
+    return CHEMICAL_FORMULA_FORMAT.format(carbon_count, hydrogen_count, nitrogen_count, oxygen_count, phosphor_count)

opr/params.py

@@ -5,33 +5,23 @@
 DNA_COMPLEMENT_MAP = {"A": "T", "C": "G", "G": "C", "T": "A"}
 CHEMICAL_FORMULA_BASES = {
     'A': {
-        'C': 10,
-        'H': 13,
-        'N': 5,
-        'O': 3,
+        'C': 10, 'H': 15, 'N': 5, 'O': 4,
     },
     'T': {
-        'C': 10,
-        'H': 14,
-        'N': 2,
-        'O': 5,
+        'C': 10, 'H': 16, 'N': 2, 'O': 6,
     },
     'C': {
-        'C': 9,
-        'H': 13,
-        'N': 3,
-        'O': 4,
+        'C': 9, 'H': 15, 'N': 3, 'O': 5,
     },
     'G': {
-        'C': 10,
-        'H': 13,
-        'N': 5,
-        'O': 4,
+        'C': 10, 'H': 15, 'N': 5, 'O': 5,
     },
 }
 CHEMICAL_FORMULA_WATER = {
-    'H': 2,
-    'O': 1,
+    '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}"

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