Will testing

excelutils/excel_sbol_utils/helpers.py

@@ -2,6 +2,7 @@
 import string
 import rdflib
 from openpyxl.worksheet import cell_range, worksheet
+from openpyxl import load_workbook
 from pathlib import Path
 
 def check_name(nm_to_chck):
@@ -22,6 +23,11 @@ def check_name(nm_to_chck):
         for ltr in nm_to_chck:
             if ord(ltr) == 32:
                 nm_to_chck = nm_to_chck.replace(ltr, "_")
+            elif ord(ltr) == 45:
+                # Allow hyphens to be reinterpreted as underscores
+                nm_to_chck = nm_to_chck.replace(ltr, "_")
+            elif ord(ltr) == 46:
+                nm_to_chck = nm_to_chck.replace(ltr, "_")
             elif ord(ltr) > 122 or ord(ltr) < 48:
                 # 122 is the highest decimal code number
                 # for common latin ltrs or arabic numbers
@@ -124,7 +130,7 @@ def read_variant_table(excel_file: Path) -> tuple[str, str, list[list]]:
     LAST_VARIANT_ROW = 35
 
     print(f'Loading workbook "{excel_file}"')
-    work_book = openpyxl.load_workbook(excel_file, data_only=True)
+    work_book = load_workbook(excel_file, data_only=True)
     sheet = work_book[VARIANTS_SHEET]
 
     # First, get the library name
@@ -133,7 +139,7 @@ def read_variant_table(excel_file: Path) -> tuple[str, str, list[list]]:
 
     # Then get the base sequence
     print('Extracting base sequence')
-    first_aa_column = get_column_number(FIRST_AMINO_ACID_COLUMN)
+    first_aa_column = col_to_num(FIRST_AMINO_ACID_COLUMN)
     last_aa_column = row_ends(sheet, ORIGINAL_AMINO_ACID_ROW, first_aa_column)
     # Get row from sheet and concatenate it into a string
     row_iterator = sheet.iter_rows(min_row=ORIGINAL_AMINO_ACID_ROW, max_row=ORIGINAL_AMINO_ACID_ROW,

excelutils/excel_sbol_utils/library2.py

@@ -370,8 +370,7 @@ def subcomponents(rowobj):
 		template.assemblePrimaryStructure(comp_list)
 		#template.compile(assembly_method=None)
 
-		f#or comp in non_var_comps:
-
+		#or comp in non_var_comps:			
 
 		rowobj.obj.masterTemplate = template
 		for var in variant_comps:

excelutils/excel_sbol_utils/library3.py

@@ -34,6 +34,7 @@ def addToDescription(rowobj):
                    'different from': sbol3.SBOL_DIFFERENT_FROM,
                    'same orientation as': sbol3.SBOL_SAME_ORIENTATION_AS,
                    'different orientation from': sbol3.SBOL_SAME_ORIENTATION_AS}
+
 def make_constraint(constraint, part_list, template):
     m = constraint_pattern.match(constraint)
     if not m:
@@ -63,16 +64,58 @@ def subcomponents(rowobj): #UPDATE TO WORK WITH CELL DICT, ALLOW CONSTRAINTS
 
 
 	if 'backbone' in rowobj.col_cell_dict:
-		temp = sbol3.Component(identity=f'{rowobj.obj.displayId}_ins_template', types=sbol3.SBO_DNA, name=f'{rowobj.obj.displayId}_ins_template')
-		newobj = sbol3.CombinatorialDerivation(identity=f'{rowobj.obj.displayId}_ins', template=temp, name=f'{rowobj.obj.displayId}_ins', strategy=sbol3.SBOL_ENUMERATE)
-		rowobj.doc.add(temp)
-		rowobj.doc.add(newobj)
-		rowobj.obj_dict[temp.display_id] = {'uri': temp.type_uri, 'object': temp,
-                                'displayId': temp.display_id}
-		backbones = list(rowobj.col_cell_dict['backbone'].values())
-		back = True
-		oldobj = rowobj.obj
-		rowobj.obj = newobj
+		# If this row has a backbone, create a new combinatorial derivation
+
+		# Determine if there are multiple comps per part
+		multiple = False
+
+		for sub in rowobj.col_cell_dict['subcomp']:
+			if "," in rowobj.col_cell_dict['subcomp'][sub]:
+				multiple = True
+				break
+			else:
+				multiple = False
+
+		# 1. If there are multiple comps per part, create ins_templat
+
+		if multiple:
+			temp = sbol3.Component(identity=f'{rowobj.obj.displayId}_ins_template', types=sbol3.SBO_DNA)
+
+			newobj = sbol3.CombinatorialDerivation(identity=f'{rowobj.obj.displayId}_ins', template=temp, name=f'{rowobj.obj.name} insert', \
+				strategy=sbol3.SBOL_ENUMERATE, description=rowobj.obj.description)
+
+			rowobj.obj.description = None
+
+			rowobj.doc.add(temp) # Add the template
+			rowobj.doc.add(newobj) # Add the combdev _ins to the document connected to the template
+
+			rowobj.obj_dict[temp.display_id] = {'uri': temp.type_uri, 'object': temp,
+									'displayId': temp.display_id}
+			backbones = list(rowobj.col_cell_dict['backbone'].values())
+			backbones = backbones[0].split(", ")
+
+			back = True
+			oldobj = rowobj.obj
+			rowobj.obj = newobj
+		else:
+			# 2. Otherwise, create _ins without the template 
+
+			# Create new component _ins without the template
+			newobj = sbol3.Component(identity=f'{rowobj.obj.displayId}_ins', name=f'{rowobj.obj.name} insert', \
+				 description=rowobj.obj.description, types=sbol3.SBO_DNA, roles=sbol3.SO_ENGINEERED_REGION)
+
+			# Set description to None
+			rowobj.obj.description = None
+
+			rowobj.doc.add(newobj)
+
+			backbones = list(rowobj.col_cell_dict['backbone'].values())
+			backbones = backbones[0].split(", ")
+
+
+			back = True
+			oldobj = rowobj.obj
+			rowobj.obj = newobj
 	else:
 		back = False
 
@@ -89,19 +132,40 @@ def subcomponents(rowobj): #UPDATE TO WORK WITH CELL DICT, ALLOW CONSTRAINTS
 		variant_comps = []
 		comp_ind = 0
 
+		# Need to update for multiple backbones, as well as remove hardcoding
+		# Check SBOL Utilities for reasoning for multiple backbones
+
 		if back:
+			# Currently this code creates a template for the insertion of the backbone into the main combinatorialderivation
 			tempObj = rowobj.obj_dict[f'{oldobj.display_id}_template']['object']
-			sub = sbol3.LocalSubComponent(types=sbol3.SBO_DNA, name="Inserted construct")
+
+			sub = sbol3.LocalSubComponent(types=sbol3.SBO_DNA, name="Inserted Construct")
 			tempObj.features.append(sub)
 			backbone_sub = sbol3.VariableFeature(cardinality=sbol3.SBOL_ONE, variable=sub, variant_derivations=rowobj.obj)
 			oldobj.variable_features.append(backbone_sub)
 
-			subComp = sbol3.SubComponent(instance_of=rowobj.obj_dict[backbones[0]]['object'])
-			rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].features.append(subComp)
-			constr1 = sbol3.Constraint(restriction=sbol3.SBOL_MEETS, object=subComp, subject=sub)
-			constr2 = sbol3.Constraint(restriction=sbol3.SBOL_MEETS, object=sub, subject=subComp)
-			rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].constraints.append(constr1)
-			rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].constraints.append(constr2)
+			if len(backbones) == 1:
+
+				subComp = sbol3.SubComponent(instance_of=rowobj.obj_dict[backbones[0]]['object'])
+				rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].features.append(subComp)
+				constr1 = sbol3.Constraint(restriction=sbol3.SBOL_MEETS, object=subComp, subject=sub)
+				constr2 = sbol3.Constraint(restriction=sbol3.SBOL_MEETS, object=sub, subject=subComp)
+				rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].constraints.append(constr1)
+				rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].constraints.append(constr2)
+			else:
+
+				newLocalSub = sbol3.LocalSubComponent(name="Vector", types=sbol3.SBO_DNA)
+				tempObj.features.append(newLocalSub)
+
+				newVarFeature = sbol3.VariableFeature(variable=newLocalSub, variants=(rowobj.obj_dict[i]['object'] for i in backbones), cardinality=sbol3.SBOL_ONE)
+				oldobj.variable_features.append(newVarFeature)
+
+				constr1 = sbol3.Constraint(restriction=sbol3.SBOL_MEETS, object=newLocalSub, subject=sub)
+				constr2 = sbol3.Constraint(restriction=sbol3.SBOL_MEETS, object=sub, subject=newLocalSub)
+
+				rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].constraints.append(constr1)
+				rowobj.obj_dict[f'{oldobj.display_id}_template']['object'].constraints.append(constr2)
+
 
 		else:
 			temp = rowobj.obj_dict[f'{rowobj.obj.display_id}_template']['object']
@@ -124,7 +188,7 @@ def subcomponents(rowobj): #UPDATE TO WORK WITH CELL DICT, ALLOW CONSTRAINTS
 
 				comp_ind += 1
 			else:
-				tempSub = sbol3.SubComponent(name=f'Part {comp_ind}', instance_of=f'{rowobj.obj_dict[comp]["uri"]}', orientation=sbol3.SBOL_INLINE)
+				tempSub = sbol3.SubComponent(name=f'Part {comp_ind + 1}', instance_of=f'{rowobj.obj_dict[comp]["uri"]}', orientation=sbol3.SBOL_INLINE)
 				temp.features.append(tempSub)
 				variant_comps.append(tempSub)
 				if comp_ind != 0:
@@ -202,6 +266,34 @@ def dataSource(rowobj):
 					rowobj.obj.update_all_dependents(id_map) # this function doesn't yet do everything it should
 					rowobj.data_source_id_to_update[old_id] = new_identity
 
+			if pref == 'URL for GenBank file' or pref == 'URL for FASTA file':	
+				# Namespace is everything except the last part of the url
+				# Loop backward through the value until a '/' is found
+				# Everything before the '/' is the namespace
+				old_val = val
+
+				# Loop through the string backwards
+				for i in range(len(val) - 1, 0, -1):
+					if val[i] == '/':
+						# Everything before the '/' is the namespace
+						ns = val[:i]
+
+						# Everything after the '/' is the display id
+						val = val[i+1:len(val) - 3]
+
+						break
+				old_id = rowobj.obj.identity
+				rowobj.doc.change_object_namespace([rowobj.obj], ns)
+				new_id = rowobj.obj.identity
+				rowobj.data_source_id_to_update[old_id] = new_id
+				rowobj.obj.derived_from = [old_val]
+				if val != rowobj.obj.display_id:
+					new_identity = str(rowobj.obj.identity).replace(rowobj.obj.display_id, helpers.check_name(val))
+					id_map = {rowobj.obj.identity:new_identity}
+					rowobj.obj.set_identity(new_identity)
+					rowobj.obj.update_all_dependents(id_map) # this function doesn't yet do everything it should
+					rowobj.data_source_id_to_update[old_id] = new_identity
+
 def sequence(rowobj):
 	for col in rowobj.col_cell_dict.keys():
 		val = rowobj.col_cell_dict[col]
@@ -218,13 +310,13 @@ def sequence(rowobj):
 
 				# removes spaces, enters, and makes all lower case
 				val = "".join(val.split())
-				val = val.replace(u"\ufeff", "").lower()
+				val = val.replace(u"\ufeff", "").upper()
 
 				# create sequence object
-				sequence = sbol3.Sequence(f"{rowobj.obj.displayId}_sequence",
-										elements=val)
-				if rowobj.obj.name is not None:
-					sequence.name = f"{rowobj.obj.name} Sequence"
+				sequence = sbol3.Sequence(f"{rowobj.obj.namespace}/{rowobj.obj.display_id}_sequence",
+										elements=val, encoding=sbol3.IUPAC_DNA_ENCODING, namespace=rowobj.obj.namespace)
+				# if rowobj.obj.name is not None:
+				# 	sequence.name = f"{rowobj.obj.name} Sequence"
 
 				rowobj.doc.add(sequence)
 
@@ -239,6 +331,11 @@ def sequence(rowobj):
 
 def circular(rowobj): # NOT IMPLEMENTED
 	# if false add to linear collection if true add to types
+
+	tempObj = rowobj.obj
+	if rowobj.col_cell_dict['Circular'] not in tempObj.types:
+		tempObj.types.append(rowobj.col_cell_dict['Circular'])
+
 	pass
 
 def finalProduct(rowobj):
@@ -253,28 +350,30 @@ def finalProduct(rowobj):
 
 			sbol_objs = doc.objects
 			sbol_objs_names = [x.name for x in sbol_objs]
-			if 'FinalProducts' not in sbol_objs_names:
-				colec = sbol3.Collection('FinalProducts', name='FinalProducts')
+			if 'Final Products' not in sbol_objs_names:
+				colec = sbol3.Collection('FinalProducts', name='Final Products')
+				colec.description = 'Final products desired for actual fabrication'
 
 				sbol_objs = doc.objects
 				sbol_objs_names = [x.name for x in sbol_objs]
 
 				doc.add(colec)
 				colec.members.append(rowobj.obj_uri)
 			else:
-				colec = sbol_objs[sbol_objs_names.index('FinalProducts')]
+				colec = sbol_objs[sbol_objs_names.index('Final Products')]
 				colec.members.append(rowobj.obj_uri)
 
-			if 'LinearDNAProducts' not in sbol_objs_names:
-				colec = sbol3.Collection('LinearDNAProducts', name='LinearDNAProducts')
+			if 'Linear DNA Products' not in sbol_objs_names:
+				colec = sbol3.Collection('LinearDNAProducts', name='Linear DNA Products')
+				colec.description = 'Linear DNA constructs to be fabricated'
 
 				sbol_objs = doc.objects
 				sbol_objs_names = [x.name for x in sbol_objs]
 
 				doc.add(colec)
 				colec.members.append(rowobj.obj)
 			else:
-				colec = sbol_objs[sbol_objs_names.index('LinearDNAProducts')]
+				colec = sbol_objs[sbol_objs_names.index('Linear DNA Products')]
 				colec.members.append(rowobj.obj)
 
 

excelutils/excel_sbol_utils/temp.py

@@ -0,0 +1,21 @@
+import sbol2
+import sbol3
+import excel_sbol_utils.library2 as l2
+import excel_sbol_utils.library3 as l3
+import excel_sbol_utils.helpers as help
+import excel2sbol.comp_column_functions2 as ccf
+import excel2sbol.converter as conv
+import os
+
+# Build a barebones combinatorial derivation object
+# Attempt to build subcomponent on it
+
+obj = sbol2.combinatorialderivation()
+
+doc = sbol2.Document()
+obj_dict = {}
+sheet = 'Composite Parts'
+
+
+
+