Better handling for SMILES

chaidiscovery · Sep 10, 2024 · 4e5d78a · 4e5d78a
1 parent 60a60ff
commit 4e5d78a
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
diff --git a/chai_lab/data/parsing/input_validation.py b/chai_lab/data/parsing/input_validation.py
@@ -10,7 +10,7 @@
 
 def constituents_of_modified_fasta(x: str) -> list[str] | None:
     """
-    Accepts RNA/DNA inputs: 'agtc', 'AGT[ASP]TG', etc
+    Accepts RNA/DNA inputs: 'agtc', 'AGT[ASP]TG', etc. Does not accept SMILES strings.
     Returns constituents, e.g, [A, G, T, ASP, T, G] or None if string is incorrect
     """
     x = x.strip().upper()
@@ -67,7 +67,7 @@ def identify_potential_entity_types(sequence: str) -> list[EntityType]:
         if "U" not in one_letter_constituents:
             possible_entity_types.append(EntityType.PROTEIN)
 
-    ascii_symbols = string.ascii_letters + string.digits + ".-+=#$%:/\\[]()@"
+    ascii_symbols = string.ascii_letters + string.digits + ".-+=#$%:/\\[]()<>@"
     if set.issubset(set(sequence.upper()), set(ascii_symbols)):
         possible_entity_types.append(EntityType.LIGAND)
     return possible_entity_types
diff --git a/tests/example_inputs.py b/tests/example_inputs.py
@@ -5,6 +5,7 @@
     "[O-]S(=O)(=O)[O-]",
     "CC1=C(C(CCC1)(C)C)/C=C/C(=C/C=C/C(=C/C=O)/C)/C",
     "CCC1=C(c2cc3c(c(c4n3[Mg]56[n+]2c1cc7n5c8c(c9[n+]6c(c4)C(C9CCC(=O)OC/C=C(\C)/CCC[C@H](C)CCC[C@H](C)CCCC(C)C)C)[C@H](C(=O)c8c7C)C(=O)OC)C)C=C)C=O",
+    r"C=CC1=C(C)/C2=C/c3c(C)c(CCC(=O)O)c4n3[Fe@TB16]35<-N2=C1/C=c1/c(C)c(C=C)/c(n13)=C/C1=N->5/C(=C\4)C(CCC(=O)O)=C1C",
     # different ions
     "[Mg+2]",
     "[Na+]",