Merge pull request #20 from TheLostLambda/lanthionine

feat(muropeptide): add meso-Lanthionine as `mL`

Author: TheLostLambda

crates/muropeptide/data/polymer_database.kdl

@@ -133,6 +133,11 @@ residues {
         functional-group "Amino" at="Sidechain"
         functional-group "Carboxyl" at="Sidechain"
     }
+    AminoAcid "mL" "Lanthionine" {
+        composition "C6H12N2O4S"
+        functional-group "Amino" at="Sidechain"
+        functional-group "Carboxyl" at="Sidechain"
+    }
     AminoAcid "K" "Lysine" {
         composition "C6H14N2O2"
         functional-group "Amino" at="Sidechain"

crates/muropeptide/data/smiles_database.kdl

@@ -148,6 +148,17 @@ residues {
 		modification "Am" replace=r"O\)=O\)" with="N)=O)"
 	}
 
+	AminoAcid "mL" {
+		// No `sidechain`, so no L and D forms...
+		isomer "meso" "N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O"
+
+		bond-sites "NToC" donor=r"(\(O\))=O\)"
+		bond-sites "CToN" acceptor=r"\(N()\)"
+		bond-sites "Link" acceptor=r"\(N()\)"
+
+		modification "Am" replace=r"O\)=O\)" with="N)=O)"
+	}
+
 	AminoAcid "K" {
 		sidechain "CCCCN"
 

crates/muropeptide/src/snapshots/muropeptide__smiles_database__tests__build_smiles_database.snap

@@ -791,5 +791,33 @@ SmilesDatabase(
         ],
       },
     ),
+    "mL": ResidueDescription(
+      isomers: [
+        Isomer(
+          name: Some("meso"),
+          smiles: "N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O",
+        ),
+      ],
+      isomer_rules: {},
+      bond_sites: {
+        Acceptor("CToN"): "\\(N()\\)",
+        Acceptor("Link"): "\\(N()\\)",
+        Acceptor("NToC"): "^N()",
+        Acceptor("Pep"): "^N()",
+        Acceptor("Stem"): "^N()",
+        Donor("CToN"): "(\\(O\\))=O$",
+        Donor("Link"): "(\\(O\\))=O$",
+        Donor("NToC"): "(\\(O\\))=O\\)",
+        Donor("Pep"): "(\\(O\\))=O$",
+      },
+      modifications: {
+        "Am": [
+          Modification(
+            replace: "O\\)=O\\)",
+            with: "N)=O)",
+          ),
+        ],
+      },
+    ),
   },
 )

crates/muropeptide/src/snapshots/muropeptide__smiles_database__tests__dump_isomer_positions.snap

@@ -191,3 +191,10 @@ m:
     Stem(4) -> β-D   (O[C@H]([C@H](O1)CO)[C@H](O[C@H](C)C(O)=O)[C@@H](NC(=O)C)[C@@H]1O)
     Stem(5) -> β-D   (O[C@H]([C@H](O1)CO)[C@H](O[C@H](C)C(O)=O)[C@@H](NC(=O)C)[C@@H]1O)
     Lateral -> β-D   (O[C@H]([C@H](O1)CO)[C@H](O[C@H](C)C(O)=O)[C@@H](NC(=O)C)[C@@H]1O)
+mL:
+    Stem(1) -> meso  (N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O)
+    Stem(2) -> meso  (N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O)
+    Stem(3) -> meso  (N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O)
+    Stem(4) -> meso  (N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O)
+    Stem(5) -> meso  (N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O)
+    Lateral -> meso  (N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O)

crates/muropeptide/src/snapshots/muropeptide__smiles_database__tests__dump_isomer_smiles.snap

@@ -55,3 +55,4 @@ Z(D): N[C@H]([C@@H](O)CC(=O)O)C(O)=O
 Z(D-iso): N[C@@H](C(=O)O)[C@@H](O)CC(O)=O
 g(β-D): O[C@H]([C@H](O1)CO)[C@H](O)[C@@H](NC(=O)C)[C@@H]1O
 m(β-D): O[C@H]([C@H](O1)CO)[C@H](O[C@H](C)C(O)=O)[C@@H](NC(=O)C)[C@@H]1O
+mL(meso): N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O

crates/muropeptide/src/snapshots/muropeptide__smiles_database__tests__parse_smiles_database.snap

@@ -484,6 +484,56 @@ SmilesDatabaseKdl {
                 ],
                 template_values: [],
             },
+            ResidueKdl {
+                kind: "AminoAcid",
+                abbr: "mL",
+                isomers: [
+                    IsomerKdl {
+                        name: Some(
+                            "meso",
+                        ),
+                        smiles: "N[C@@H](CSC[C@@H](N)C(O)=O)C(O)=O",
+                    },
+                ],
+                stem: [],
+                lateral: None,
+                bond_sites: [
+                    BondSitesKdl {
+                        bond: "NToC",
+                        donor: Some(
+                            "(\\(O\\))=O\\)",
+                        ),
+                        acceptor: None,
+                    },
+                    BondSitesKdl {
+                        bond: "CToN",
+                        donor: None,
+                        acceptor: Some(
+                            "\\(N()\\)",
+                        ),
+                    },
+                    BondSitesKdl {
+                        bond: "Link",
+                        donor: None,
+                        acceptor: Some(
+                            "\\(N()\\)",
+                        ),
+                    },
+                ],
+                modifications: [
+                    ModificationKdl {
+                        abbr: "Am",
+                        replace: Some(
+                            "O\\)=O\\)",
+                        ),
+                        with: Some(
+                            "N)=O)",
+                        ),
+                        replacements: [],
+                    },
+                ],
+                template_values: [],
+            },
             ResidueKdl {
                 kind: "AminoAcid",
                 abbr: "K",