Merge branch 'HC_fix' into 'master'

Fix HC and OC calculations

See merge request mass-spectrometry/corems!113

Author: corilo

corems/molecular_formula/factory/MolecularFormulaFactory.py

@@ -250,14 +250,20 @@ def isotopologue_count_percentile(self, ):
 
     @property
     def O_C(self): 
-            
             if 'O' in self._d_molecular_formula.keys():
-                return self._d_molecular_formula.get("O")/self._d_molecular_formula.get("C")
+                # gather all the Os and Hs, regardless of the isotopic composition
+                Os =sum([self._d_molecular_formula.get(key) for key in ['O'] + Atoms.isotopes['O'][1] if key in self._d_molecular_formula.keys()])
+                Cs = sum([self._d_molecular_formula.get(key) for key in ['C'] + Atoms.isotopes['C'][1] if key in self._d_molecular_formula.keys()])
+                return Os/Cs
             else:
                 return 0    
 
     @property
-    def H_C(self): return self._d_molecular_formula.get("H")/self._d_molecular_formula.get("C")
+    def H_C(self): 
+        # gather all the Cs and Hs, regardless of the isotopic composition
+        Cs = sum([self._d_molecular_formula.get(key) for key in ['C'] + Atoms.isotopes['C'][1] if key in self._d_molecular_formula.keys()])
+        Hs = sum([self._d_molecular_formula.get(key) for key in ['H'] + Atoms.isotopes['H'][1] if key in self._d_molecular_formula.keys()])
+        return Hs/Cs
 
     @property
     def dbe(self): return self._calc_dbe()

support_code/nmdc/README.md

@@ -0,0 +1,5 @@
+Scripts in this folder (support_code/nmdc) are for development and running locally.  They should not be considered the "source of truth" for NMDC's workflows or metadata generation.  
+
+Production workflows and metadata generation scripts source locations:
+-  NOM worklfow and metadata generation scripts live in the EnviroMS repository
+-  GC-MS metabolomics workflow and metadata generation scripts live in the MetaMS repository

tests/test_molecularFormulaSearch.py

@@ -87,7 +87,7 @@ def test_run_molecular_formula_search():
 def test_run_molecular_formula_search_adduct():
     # Test for generating accurate molecular formula from a single mass using the local sql database
     # Now also tests that it is handling isotopes correctly (for non-adducts)
-    mz = [782.563522, 783.566877] #Na+ adduct of C56H73N1 and it's M+1
+    mz = [782.563522, 783.566877] #Na+ adduct of C56H73N1 and its M+1
     abundance = [1, 0.4]
     rp, s2n = [[1, 1],[1, 1]]
 
@@ -112,8 +112,10 @@ def test_run_molecular_formula_search_adduct():
     SearchMolecularFormulas(mass_spectrum_obj, find_isotopologues=True).run_worker_ms_peaks([mass_spectrum_obj[0]])
     mass_spectrum_obj.to_dataframe()
 
-    assert  mass_spectrum_obj[0][0].string == 'C56 H73 N1'
+    assert mass_spectrum_obj[0][0].string == 'C56 H73 N1'
+    assert mass_spectrum_obj[0][0].H_C == 73/56
     assert mass_spectrum_obj[1][0].string == 'C55 H73 N1 13C1'
+    assert mass_spectrum_obj[1][0].H_C == 73/56