New mol key and compression #43

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

Joseph-Ellaway merged 29 commits into main from new-mol-key-and-compression

Mar 10, 2026

.gitignore

-Original file line number
+Diff line change
@@ Expand Up / @@ -136,3 +136,4 @@ tests/data/actual_output/ @@
     tests/data/actual_output/*
     pisa_cfg_tmp
     tmp_example_data/
+    scratch/

pisa_utils/models/data_models.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -36,6 +36,7 @@ @@
         COMPLEX_TYPE,
         COMPLEXES_IN_ASU,
         COMPLEXES_IN_PQS_SET,
+        COMPONENT_ID,
         COMPONENT_NUMBER,
         COMPONENT_TOTAL_ATOMS,
         COMPONENT_TOTAL_RESIDUES,
@@ Expand Down Expand Up @@
     class Molecule(StrictModel):
         mol_id: int = Field(..., validation_alias="id")
+        component_id: str = Field(
+            ...,
+            description=COMPONENT_ID,
+            examples=["Protein"],
+        )
         auth_asym_id: str = Field(
             ...,
             description=AUTH_ASYM_ID,
@@ Expand Down Expand Up / @@ -1536,6 +1542,11 @@ class Component(StrictModel): @@
         molecule_type_id: int = Field(
             ..., description=COMPONENT_TYPE_ID, examples=[1], validation_alias="monomer_id"
         )
+        component_id: str = Field(
+            ...,
+            description=COMPONENT_ID,
+            examples=["A", "[NA]A:301", "o7", "[GOL]A:302"],
+        )
         auth_asym_id: str = Field(
             ...,
             description=AUTH_ASYM_ID,
@@ Expand Down Expand Up / @@ -1618,6 +1629,7 @@ class Components(StrictModel): @@
                     Component(
                         serial_number=1,
                         monomer_id=1,
+                        component_id="A",
                         chain_id="A",
                         monomer_class="Protein",
                         total_atoms=1846,
@@ Expand All / @@ -1630,6 +1642,7 @@ class Components(StrictModel): @@
                     Component(
                         serial_number=2,
                         monomer_id=2,
+                        component_id="B",
                         chain_id="B",
                         monomer_class="Protein",
                         total_atoms=1500,
@@ Expand All / @@ -1639,6 +1652,19 @@ class Components(StrictModel): @@
                         area=9500.3,
                         delta_g=-180.5,
                     ),
+                    Component(
+                        serial_number=3,
+                        monomer_id=3,
+                        component_id="[NA]A:301",
+                        chain_id="A",
+                        monomer_class="Ligand",
+                        total_atoms=10,
+                        total_residues=1,
+                        surface_atoms=5,
+                        surface_residues=1,
+                        area=50.2,
+                        delta_g=-5.0,
+                    ),
                 ]
             ],
         )
@@ Expand Down @@

pisa_utils/models/labels.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -220,6 +220,9 @@ @@
     VISUAL_ID = """PISA-defined chain ID used in the 'formula' field. Chains with
     sufficiently similar structural similarity are assigned the same visual ID."""
+    COMPONENT_ID = """Component identifier. For macromolecular components, this is the
+    auth_asym_id. For ligands, this is the CCD, auth_asym_id and sequence IDs."""
     COMPONENT_NUMBER = """Unique ID corresponding to component instance in the (crystal)
     structure"""
@@ Expand Down @@

pisa_utils/models/models.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -11,3 +11,27 @@ class DataModes(str, Enum): @@
         ASSEMBLIES = "assemblies"
         INTERFACES = "interfaces"
         MONOMERS = "monomers"
+    class OutputFormats(str, Enum):
+        JSON = ".json"
+        JSON_GZ = ".json.gz"
+        XML = ".xml"
+        XML_GZ = ".xml.gz"
+    class AllowedModelFileFormats(str, Enum):
+        # Text-based formats
+        CIF = ".cif"
+        PDB = ".pdb"
+        MMCIF = ".mmcif"
+        ENT = ".ent"
+        # Binary formats
+        BCIF = ".bcif"
+        # Compressed formats
+        CIF_GZ = ".cif.gz"
+        PDB_GZ = ".pdb.gz"
+        MMCIF_GZ = ".mmcif.gz"
+        ENT_GZ = ".ent.gz"

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

New mol key and compression #43

Uh oh!

Diff view

Diff view

There are no files selected for viewing

Uh oh!