stjames 0.0.47__tar.gz → 0.0.48__tar.gz

{stjames-0.0.47/stjames.egg-info → stjames-0.0.48}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: stjames
-Version: 0.0.47
+Version: 0.0.48
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames
@@ -8,6 +8,7 @@ Project-URL: Bug Tracker, https://github.com/rowansci/stjames/issues
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: atomium<2,>=1
 Requires-Dist: pydantic>=2.4
 Requires-Dist: numpy
 

{stjames-0.0.47 → stjames-0.0.48}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "stjames"
-version = "0.0.47"
+version = "0.0.48"
 description = "standardized JSON atom/molecule encoding scheme"
 readme = "README.md"
 requires-python = ">=3.11"
@@ -9,6 +9,7 @@ authors = [
 ]
 
 dependencies = [
+    "atomium>=1,<2",
     "pydantic>=2.4",
     "numpy",
 ]
@@ -48,10 +49,11 @@ ignore = ["E741"]
 
 [tool.pytest.ini_options]
 testpaths = ["stjames", "tests"]
-addopts = "--doctest-modules"
+addopts = "--doctest-modules --durations=5 -m 'not regression'"
 doctest_optionflags = "NORMALIZE_WHITESPACE"
 markers = [
-  "smoke: sanity tests to reveal simple failures"
+  "smoke: sanity tests to reveal simple failures",
+  "regression: tests to make sure bugs stay closed",
 ]
 
 [tool.mypy]

{stjames-0.0.47 → stjames-0.0.48}/stjames/method.py

@@ -32,8 +32,10 @@ class Method(LowercaseStrEnum):
 
     AIMNET2_WB97MD3 = "aimnet2_wb97md3"
     MACE_MP_0 = "mace_mp_0"
+    MACE_MP_0B2_L = "mace_mp_0b2_l"
     OCP24_S = "ocp24_s"
     OCP24_L = "ocp24_l"
+    ORB_V2 = "orb_v2"
 
     GFN_FF = "gfn_ff"
     GFN0_XTB = "gfn0_xtb"
@@ -46,8 +48,14 @@ class Method(LowercaseStrEnum):
     OFF_SAGE_2_2_1 = "off_sage_2_2_1"
 
 
-NNPMethod = Literal[Method.AIMNET2_WB97MD3]
-NNP_METHODS = [Method.AIMNET2_WB97MD3]
+PrepackagedNNPMethod = Literal[Method.AIMNET2_WB97MD3, Method.OCP24_S, Method.OCP24_L]
+PREPACKAGED_NNP_METHODS = [Method.AIMNET2_WB97MD3, Method.OCP24_S, Method.OCP24_L]
+
+CorrectableNNPMethod = Literal[Method.MACE_MP_0B2_L, Method.ORB_V2]
+CORRECTABLE_NNP_METHODS = [Method.MACE_MP_0B2_L, Method.ORB_V2]
+
+NNPMethod = PrepackagedNNPMethod | CorrectableNNPMethod
+NNP_METHODS = [*PREPACKAGED_NNP_METHODS, *CORRECTABLE_NNP_METHODS]
 
 XTBMethod = Literal[Method.GFN_FF, Method.GFN0_XTB, Method.GFN1_XTB, Method.GFN2_XTB]
 XTB_METHODS = [Method.GFN_FF, Method.GFN0_XTB, Method.GFN1_XTB, Method.GFN2_XTB]
@@ -58,8 +66,8 @@ COMPOSITE_METHODS = [Method.HF3C, Method.B973C, Method.R2SCAN3C, Method.WB97X3C]
 FFMethod = Literal[Method.OFF_SAGE_2_2_1]
 FF_METHODS = [Method.OFF_SAGE_2_2_1]
 
-PrepackagedMethod = XTBMethod | CompositeMethod | NNPMethod | FFMethod
-PREPACKAGED_METHODS = [*XTB_METHODS, *COMPOSITE_METHODS, *NNP_METHODS, *FF_METHODS]
+PrepackagedMethod = XTBMethod | CompositeMethod | PrepackagedNNPMethod | FFMethod
+PREPACKAGED_METHODS = [*XTB_METHODS, *COMPOSITE_METHODS, *PREPACKAGED_NNP_METHODS, *FF_METHODS]
 
 MethodWithCorrection = Literal[Method.WB97XD3, Method.WB97XV, Method.WB97MV, Method.WB97MD3BJ, Method.DSDBLYPD3BJ]
 METHODS_WITH_CORRECTION = [Method.WB97XD3, Method.WB97XV, Method.WB97MV, Method.WB97MD3BJ, Method.DSDBLYPD3BJ, Method.B97D3BJ]

stjames-0.0.48/stjames/pdb.py

@@ -0,0 +1,197 @@
+from datetime import date
+from pathlib import Path
+from typing import Any, Literal
+
+import atomium  # type: ignore [import-untyped]
+from atomium.pdb import pdb_dict_to_data_dict, pdb_string_to_pdb_dict  # type: ignore [import-untyped]
+from pydantic import BaseModel, ConfigDict, Field
+
+from stjames.types import Matrix3x3, Vector3D
+
+# Mostly for testing purposes
+EXTRA: Literal["allow", "ignore", "forbid"] = "allow"
+
+
+class PDBAtom(BaseModel):
+    """An atom within a residue."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    x: float
+    y: float
+    z: float
+    element: str
+    name: str
+    charge: float
+    occupancy: float
+    alt_loc: str | None
+    anisotropy: list[float]
+    bvalue: float
+    is_hetatm: bool
+
+
+class PDBWater(BaseModel):
+    """A water molecule."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    name: str | None
+    full_name: str | None
+    atoms: dict[int, PDBAtom] = {}
+    internal_id: str | None
+    polymer: str
+
+
+class PDBResidue(BaseModel):
+    """A structure."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    name: str | None
+    full_name: str | None = None
+    atoms: dict[int, PDBAtom] = {}
+    number: int
+
+
+class PDBPolymer(BaseModel):
+    """A polymer chain."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    internal_id: str
+    helices: list[list[str]] = []
+    residues: dict[str, PDBResidue] = {}
+    sequence: str | None
+    strands: list[list[str]] = []
+
+
+class PDBNonPolymer(BaseModel):
+    """Non-polymeric molecules/atoms (e.g. ions and ligands)."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    name: str
+    full_name: str | None = None
+    atoms: dict[int, PDBAtom]
+    internal_id: str
+    polymer: str
+
+
+class PDBModel(BaseModel):
+    """Structure data."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    polymer: dict[str, PDBPolymer] = {}
+    non_polymer: dict[str, PDBNonPolymer] = Field(alias="non-polymer", default_factory=dict)
+    branched: dict[str, Any] = {}
+    water: dict[str, PDBWater] = {}
+
+
+class PDBTransformations(BaseModel):
+    """Transformations applied to the structure."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    chains: list[str]
+    matrix: Matrix3x3
+    vector: Vector3D
+
+
+class PDBAssembly(BaseModel):
+    """How the structure was assembled."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    transformations: list[PDBTransformations]
+    software: str | None
+    buried_surface_area: float | None
+    surface_area: float | None
+    delta_energy: float | None
+    id: int
+
+
+class PDBCrystallography(BaseModel):
+    """Crystallography related information."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    space_group: str | None = None
+    unit_cell: list[float] | None = None
+
+
+class PDBGeometry(BaseModel):
+    """Details of the geometry."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    assemblies: list[PDBAssembly] = []
+    crystallography: PDBCrystallography = Field(default_factory=PDBCrystallography)
+
+
+class PDBQuality(BaseModel):
+    """Quality metrics."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    resolution: float | None = None
+    rfree: float | None = None
+    rvalue: float | None = None
+
+
+class PDBMissingResidue(BaseModel):
+    model_config = ConfigDict(extra=EXTRA)
+
+    name: str
+    id: str
+
+
+class PDBExperiment(BaseModel):
+    """Details of the experiment."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    expression_system: str | None
+    missing_residues: list[PDBMissingResidue] = []
+    source_organism: str | None
+    technique: str | None
+
+
+class PDBDescription(BaseModel):
+    """A description of the molecule."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    code: str | None
+    title: str | None
+    authors: list[str] = []
+    classification: str | None
+    deposition_date: date | None
+    keywords: list[str] = []
+
+
+class PDB(BaseModel):
+    """A PDB formatted file."""
+
+    model_config = ConfigDict(extra=EXTRA)
+
+    description: PDBDescription
+    experiment: PDBExperiment
+    geometry: PDBGeometry
+    models: list[PDBModel] = []
+    quality: PDBQuality = Field(default_factory=PDBQuality)
+
+
+def read_pdb(path: Path | str) -> PDB:
+    """Read a pdb located at path."""
+    return PDB.model_validate(atomium.open(str(path), data_dict=True))
+
+
+def fetch_pdb(code: str) -> PDB:
+    """Fetch a pdb from the Protein Data Bank."""
+    return PDB.model_validate(atomium.fetch(code, data_dict=True))
+
+
+def pdb_from_string(pdb: str) -> PDB:
+    """Read a PDB from a string."""
+    return PDB.model_validate(pdb_dict_to_data_dict(pdb_string_to_pdb_dict(pdb)))

{stjames-0.0.47 → stjames-0.0.48}/stjames/settings.py

@@ -5,7 +5,7 @@ from pydantic import computed_field, field_validator, model_validator
 from .base import Base, UniqueList
 from .basis_set import BasisSet
 from .correction import Correction
-from .method import METHODS_WITH_CORRECTION, PREPACKAGED_METHODS, Method
+from .method import CORRECTABLE_NNP_METHODS, METHODS_WITH_CORRECTION, PREPACKAGED_METHODS, Method
 from .mode import Mode
 from .opt_settings import OptimizationSettings
 from .scf_settings import SCFSettings
@@ -38,12 +38,14 @@ class Settings(Base):
     def level_of_theory(self) -> str:
         corrections = list(filter(lambda x: x not in (None, ""), self.corrections))
 
-        if self.method in PREPACKAGED_METHODS or self.basis_set is None:
+        if self.method in CORRECTABLE_NNP_METHODS:
+            method = self.method.value if not corrections else f"{self.method.value}-{'-'.join(c.value for c in corrections)}"
+        elif self.method in PREPACKAGED_METHODS or self.basis_set is None:
             method = self.method.value
-        elif self.method in METHODS_WITH_CORRECTION or len(corrections) == 0:
+        elif self.method in METHODS_WITH_CORRECTION or not corrections:
             method = f"{self.method.value}/{self.basis_set.name.lower()}"
         else:
-            method = f"{self.method.value}-{'-'.join([c.value for c in corrections])}/{self.basis_set.name.lower()}"
+            method = f"{self.method.value}-{'-'.join(c.value for c in corrections)}/{self.basis_set.name.lower()}"
 
         if self.solvent_settings is not None:
             method += f"/{self.solvent_settings.model.value}({self.solvent_settings.solvent.value})"

{stjames-0.0.47 → stjames-0.0.48}/stjames/workflows/hydrogen_bond_basicity.py

@@ -11,6 +11,9 @@ class HydrogenBondAcceptorSite(Base):
 
 
 class HydrogenBondBasicityWorkflow(Workflow):
+    do_csearch: bool = True
+    do_optimization: bool = True
+
     # UUID of optimization
     optimization: UUID | None = None
 

{stjames-0.0.47 → stjames-0.0.48/stjames.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: stjames
-Version: 0.0.47
+Version: 0.0.48
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames
@@ -8,6 +8,7 @@ Project-URL: Bug Tracker, https://github.com/rowansci/stjames/issues
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: atomium<2,>=1
 Requires-Dist: pydantic>=2.4
 Requires-Dist: numpy
 

{stjames-0.0.47 → stjames-0.0.48}/stjames.egg-info/SOURCES.txt

@@ -17,6 +17,7 @@ stjames/method.py
 stjames/mode.py
 stjames/molecule.py
 stjames/opt_settings.py
+stjames/pdb.py
 stjames/periodic_cell.py
 stjames/py.typed
 stjames/scf_settings.py
@@ -59,4 +60,5 @@ stjames/workflows/workflow.py
 tests/test_constraints.py
 tests/test_from_extxyz.py
 tests/test_molecule.py
+tests/test_pdb.py
 tests/test_settings.py

{stjames-0.0.47 → stjames-0.0.48}/stjames.egg-info/requires.txt

@@ -1,2 +1,3 @@
+atomium<2,>=1
 pydantic>=2.4
 numpy

stjames-0.0.48/tests/test_pdb.py

@@ -0,0 +1,44 @@
+from pytest import mark
+
+from stjames.pdb import fetch_pdb, pdb_from_string
+
+
+def test_1ema() -> None:
+    """Green fluorescent protein."""
+    fetch_pdb("1EMA")
+
+
+def test_read_pdb() -> None:
+    """Rest reading of a pdb string."""
+    with open("tests/data/1ema.pdb") as f:
+        data = f.read()
+    pdb = pdb_from_string(data)
+    assert pdb.description.code == "1EMA"
+
+
+# fmt: off
+@mark.regression
+@mark.parametrize(
+    "code",
+    [
+        # Codes from molecules of the month August 2024–January 2025
+        "7S6B", "8UCS", "8UPL", "7CGO", "2ZVY", "1F4V", "6YKM", "6E10", "6E11",
+        "3VCM", "2X0B", "6OS0", "1N9U", "1O86", "2V0Z", "6KI1", "6KI2", "7YYO",
+        "6TJV", "7EGL", "7CYF", "7EGK", "7ZCG", "3FRT", "6AP1",
+        # Codes created by o1
+        "1CRN", "1MBN", "4HHB", "1HHO", "1BNA", "1CAG", "2JHO", "1EVV", "3ZOJ",
+        "4AGG", "2Y69", "6R1V", "6ND2", "7NZ6", "1S72", "3G5U", "7DFT", "6AI0",
+        "6NG2", "1A0I", "1B7C", "1C8R", "1D4T", "1E7O", "1F9J", "1G5K", "1H8L",
+        "1I2M", "1J3N", "1K4P", "1M7R", "1N8S", "1O9T", "1P0U", "1Q1V", "1R2W",
+        "1S3X", "1T4Y", "1U5Z", "1V6A", "1W7B", "1X8C", "1Y9D", "1Z0E", "2A1F",
+        "2B2G", "2C3H", "2D4I", "2E5J", "2F6K", "2G7L", "2H8M", "2I9N", "2J0O",
+        "2K1P", "2L2Q", "2N4S", "2O5T", "2P6U", "2Q7V", "2R8W", "2V2A", "2W3B",
+        "2X4C", "2Y5D", "2Z6E", "3A7F", "3B8G", "3C9H", "3D0I", "3E1J", "3F2K",
+        "3G3L", "3H4M", "3I5N", "3J6O", "3K7P", "3L8Q", "3N0S", "3O1T", "3P2U",
+        "3Q3V", "3S5X", "3T6Y", "3U7Z", "3V8A", "3W9B", "3X0C", "4A3F", "4B4G",
+        "4C5H", "4D6I", "4E7J", "4F8K", "4G9L", "4H0M", "4I1N", "4J2O", "4K3P",
+        "4L4Q", "4M5R", "4N6S", "4O7T", "4P8U", "4Q9V", "4R0W", "4S1X",
+    ]
+)  # fmt: on
+def test_pdb(code: str) -> None:
+    fetch_pdb(code)