added possibility of incomplete molecular species structures such as …

…'TG 18:0_42:2'

pygoslin/domain/FattyAcid.py

@@ -38,6 +38,7 @@ def __init__(self, name, num_carbon = 0, double_bonds = 0, functional_groups = N
         super().__init__(name, double_bonds = double_bonds, position = position, functional_groups = functional_groups)
         self.num_carbon = num_carbon
         self.lipid_FA_bond_type = lipid_FA_bond_type
+        self.unresolved_hidden_fa = False
 
         if lipid_FA_bond_type == LipidFaBondType.LCB_REGULAR: self.functional_groups["[X]"] = [get_functional_group("X")]
 
@@ -184,6 +185,11 @@ def num_oxygens(self):
 
     def compute_elements(self):
         self.elements = {e: 0 for e in Element}
+        if self.unresolved_hidden_fa:
+            self.elements[Element.O] = 1
+            self.elements[Element.H] = -1
+            return self.elements
+
         num_double_bonds = len(self.double_bonds) if type(self.double_bonds) != int else self.double_bonds
         if self.lipid_FA_bond_type == LipidFaBondType.ETHER_PLASMENYL: num_double_bonds += 1
 

pygoslin/domain/LipidMolecularSpecies.py

@@ -50,6 +50,7 @@ def __init__(self, head_group, fa = []):
         # add 0:0 dummys
         for i in range(len(fa), self.info.total_fa):
             fatty_acid = FattyAcid("FA%i" % (i + 1), position = -1)
+            fatty_acid.unresolved_hidden_fa = 1 < len(fa) < self.info.poss_fa
             self.info.add(fatty_acid)
             self.fa[fatty_acid.name] = fatty_acid
             self.fa_list.append(fatty_acid)

pygoslin/domain/LipidSpeciesInfo.py

@@ -39,6 +39,7 @@ def __init__(self, lipid_class):
         self.level = None
         self.num_ethers = 0
         self.num_specified_fa = 0
+        self.poss_fa = all_lipids[lipid_class]["poss_fa"]
         self.total_fa = all_lipids[lipid_class]["max_fa"]
         self.extended_class = LipidFaBondType.ESTER
         self.lipid_class = lipid_class

pygoslin/parser/LipidBaseParserEventHandler.py

@@ -86,7 +86,7 @@ def sp_regular_lcb(self):
 
 
 
-    def prepare_headgroup_and_checks(self):
+    def prepare_headgroup_and_checks(self, allow_class_shift = True):
         # checking if head group is a glyco-sphingolipid
         """
         hg = self.head_group.lower()
@@ -118,17 +118,19 @@ def prepare_headgroup_and_checks(self):
         # make lyso
         can_be_lyso = "Lyso" in all_lipids[get_class("L" + self.head_group)]["specials"] if get_class("L" + self.head_group) < len(all_lipids) else False
 
-        if (true_fa + 1 == poss_fa or true_fa + 2 == poss_fa) and self.level != LipidLevel.SPECIES and headgroup.lipid_category == LipidCategory.GP and can_be_lyso:
-            if true_fa + 1 == poss_fa: self.head_group = "L" + self.head_group
-            else: self.head_group = "DL" + self.head_group
-            headgroup = HeadGroup(self.head_group, self.headgroup_decorators, self.use_head_group)
-            poss_fa = all_lipids[headgroup.lipid_class]["poss_fa"] if headgroup.lipid_class < len(all_lipids) else 0
-
-        elif (true_fa + 1 == poss_fa or true_fa + 2 == poss_fa) and self.level != LipidLevel.SPECIES and headgroup.lipid_category == LipidCategory.GL and self.head_group == "TG":
-            if true_fa + 1 == poss_fa: self.head_group = "DG"
-            else: self.head_group = "MG"
-            headgroup = HeadGroup(self.head_group, self.headgroup_decorators, self.use_head_group)
-            poss_fa = all_lipids[headgroup.lipid_class]["poss_fa"] if headgroup.lipid_class < len(all_lipids) else 0
+        if allow_class_shift:
+            if (true_fa + 1 == poss_fa or true_fa + 2 == poss_fa) and self.level != LipidLevel.SPECIES and headgroup.lipid_category == LipidCategory.GP and can_be_lyso:
+                if true_fa + 1 == poss_fa: self.head_group = "L" + self.head_group
+                else: self.head_group = "DL" + self.head_group
+                headgroup = HeadGroup(self.head_group, self.headgroup_decorators, self.use_head_group)
+                poss_fa = all_lipids[headgroup.lipid_class]["poss_fa"] if headgroup.lipid_class < len(all_lipids) else 0
+
+            elif (true_fa + 1 == poss_fa or true_fa + 2 == poss_fa) and self.level != LipidLevel.SPECIES and headgroup.lipid_category == LipidCategory.GL and self.head_group == "TG":
+                if true_fa + 1 == poss_fa: self.head_group = "DG"
+                else: self.head_group = "MG"
+                print(self.head_group)
+                headgroup = HeadGroup(self.head_group, self.headgroup_decorators, self.use_head_group)
+                poss_fa = all_lipids[headgroup.lipid_class]["poss_fa"] if headgroup.lipid_class < len(all_lipids) else 0
 
 
         # check if all functional groups have a position to be full structure
@@ -143,7 +145,7 @@ def prepare_headgroup_and_checks(self):
             if true_fa == 0 and poss_fa != 0:
                 raise ConstraintViolationException("No fatty acyl information lipid class '%s' provided." % headgroup.headgroup)
 
-        elif true_fa != poss_fa and self.level in {LipidLevel.COMPLETE_STRUCTURE, LipidLevel.FULL_STRUCTURE, LipidLevel.STRUCTURE_DEFINED, LipidLevel.SN_POSITION, LipidLevel.MOLECULAR_SPECIES}:
+        elif true_fa > poss_fa and self.level in {LipidLevel.COMPLETE_STRUCTURE, LipidLevel.FULL_STRUCTURE, LipidLevel.STRUCTURE_DEFINED, LipidLevel.SN_POSITION, LipidLevel.MOLECULAR_SPECIES}:
             raise ConstraintViolationException("Number of specified fatty acyl chains (%i) not allowed for lipid class '%s' (having %i fatty aycl chains)." % (true_fa, headgroup.headgroup, poss_fa))
 
         elif "Lyso" in all_lipids[get_class(self.head_group)]["specials"] and true_fa > poss_fa:

pygoslin/parser/ShorthandParserEventHandler.py

@@ -683,7 +683,7 @@ def set_double_bond_count(self, node):
 
     def build_lipid(self, node):
         if self.acer_species: self.fa_list[0].num_carbon -= 2
-        headgroup = self.prepare_headgroup_and_checks()
+        headgroup = self.prepare_headgroup_and_checks(False)
 
         lipid = LipidAdduct()
         lipid.adduct = self.adduct