add helper function for stripping out unmatched brackets

build/lib/glycowork/glycan_data/loader.py

@@ -89,6 +89,37 @@ def find_nth_reverse(string, substring, n, ignore_branches = False):
   return original_start_index
 
 
+def remove_unmatched_brackets(s):
+  """Removes all unmatched brackets from the string s.\n
+  | Arguments:
+  | :-
+  | s (string): glycan string in IUPAC-condensed\n
+  | Returns:
+  | :-
+  | Returns glycan without unmatched brackets
+   """
+  while True:
+    # Keep track of the indexes of the brackets
+    stack = []
+    unmatched_open = set()
+    unmatched_close = set()
+    for i, char in enumerate(s):
+      if char == '[':
+        stack.append(i)
+      elif char == ']':
+        if stack:
+          stack.pop()
+        else:
+          unmatched_close.add(i)
+    unmatched_open.update(stack)
+    # If there are no unmatched brackets, break the loop
+    if not unmatched_open and not unmatched_close:
+      break
+    # Build a new string without the unmatched brackets
+    s = ''.join([char for i, char in enumerate(s) if i not in unmatched_open and i not in unmatched_close])
+  return s
+
+
 def reindex(df_new, df_old, out_col, ind_col, inp_col):
   """Returns columns values in order of new dataframe rows\n
   | Arguments:

build/lib/glycowork/motif/annotate.py

@@ -3,7 +3,7 @@
 import re
 from collections import defaultdict
 
-from glycowork.glycan_data.loader import lib, linkages, motif_list, find_nth, unwrap, replace_every_second
+from glycowork.glycan_data.loader import lib, linkages, motif_list, find_nth, unwrap, replace_every_second, remove_unmatched_brackets
 from glycowork.motif.graph import subgraph_isomorphism, generate_graph_features, glycan_to_nxGraph, graph_to_string, ensure_graph
 from glycowork.motif.processing import IUPAC_to_SMILES, get_lib, find_isomorphs, expand_lib, rescue_glycans
 
@@ -304,6 +304,8 @@ def get_k_saccharides(glycans, size = 2, libr = None, up_to = False, just_motifs
       if col_sums[col1] == col_sums[col2] and col_subs[col1] == col2:
         drop_columns.append(col2)
   out_matrix = out_matrix.drop(drop_columns, axis = 1)
+  if size > 3:
+    out_matrix.columns = [remove_unmatched_brackets(g) for g in out_matrix.columns]
   if up_to:
     combined_df= pd.concat([wga_letter, out_matrix], axis = 1).fillna(0).astype(int)
     if just_motifs:

glycowork/glycan_data/loader.py

@@ -89,6 +89,37 @@ def find_nth_reverse(string, substring, n, ignore_branches = False):
   return original_start_index
 
 
+def remove_unmatched_brackets(s):
+  """Removes all unmatched brackets from the string s.\n
+  | Arguments:
+  | :-
+  | s (string): glycan string in IUPAC-condensed\n
+  | Returns:
+  | :-
+  | Returns glycan without unmatched brackets
+   """
+  while True:
+    # Keep track of the indexes of the brackets
+    stack = []
+    unmatched_open = set()
+    unmatched_close = set()
+    for i, char in enumerate(s):
+      if char == '[':
+        stack.append(i)
+      elif char == ']':
+        if stack:
+          stack.pop()
+        else:
+          unmatched_close.add(i)
+    unmatched_open.update(stack)
+    # If there are no unmatched brackets, break the loop
+    if not unmatched_open and not unmatched_close:
+      break
+    # Build a new string without the unmatched brackets
+    s = ''.join([char for i, char in enumerate(s) if i not in unmatched_open and i not in unmatched_close])
+  return s
+
+
 def reindex(df_new, df_old, out_col, ind_col, inp_col):
   """Returns columns values in order of new dataframe rows\n
   | Arguments:

glycowork/motif/annotate.py

@@ -3,7 +3,7 @@
 import re
 from collections import defaultdict
 
-from glycowork.glycan_data.loader import lib, linkages, motif_list, find_nth, unwrap, replace_every_second
+from glycowork.glycan_data.loader import lib, linkages, motif_list, find_nth, unwrap, replace_every_second, remove_unmatched_brackets
 from glycowork.motif.graph import subgraph_isomorphism, generate_graph_features, glycan_to_nxGraph, graph_to_string, ensure_graph
 from glycowork.motif.processing import IUPAC_to_SMILES, get_lib, find_isomorphs, expand_lib, rescue_glycans
 
@@ -304,6 +304,8 @@ def get_k_saccharides(glycans, size = 2, libr = None, up_to = False, just_motifs
       if col_sums[col1] == col_sums[col2] and col_subs[col1] == col2:
         drop_columns.append(col2)
   out_matrix = out_matrix.drop(drop_columns, axis = 1)
+  if size > 3:
+    out_matrix.columns = [remove_unmatched_brackets(g) for g in out_matrix.columns]
   if up_to:
     combined_df= pd.concat([wga_letter, out_matrix], axis = 1).fillna(0).astype(int)
     if just_motifs: