stjames 0.0.83__py3-none-any.whl → 0.0.85__py3-none-any.whl

stjames/method.py

@@ -43,6 +43,7 @@ class Method(LowercaseStrEnum):
     GFN0_XTB = "gfn0_xtb"
     GFN1_XTB = "gfn1_xtb"
     GFN2_XTB = "gfn2_xtb"
+    G_XTB = "g_xtb"
 
     # this was going to be removed, but Jonathon wrote such a nice basis set test... it's off the front end.
     BP86 = "bp86"
@@ -86,8 +87,8 @@ 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]
+XTBMethod = Literal[Method.GFN_FF, Method.GFN0_XTB, Method.GFN1_XTB, Method.GFN2_XTB, Method.G_XTB]
+XTB_METHODS = [Method.GFN_FF, Method.GFN0_XTB, Method.GFN1_XTB, Method.GFN2_XTB, Method.G_XTB]
 
 CompositeMethod = Literal[Method.HF3C, Method.B973C, Method.R2SCAN3C, Method.WB97X3C]
 COMPOSITE_METHODS = [Method.HF3C, Method.B973C, Method.R2SCAN3C, Method.WB97X3C]

stjames/pdb.py

@@ -228,7 +228,7 @@ def pdb_object_to_pdb_filestring(
     keyword: bool = False,
     seqres: bool = True,
     hetnam: bool = True,
-    remark: bool = True,
+    remark: bool = False,
     crystallography: bool = False,
 ) -> str:
     pdb_lines: list[str] = []

stjames/workflows/__init__.py

@@ -18,6 +18,7 @@ from .macropka import *
 from .molecular_dynamics import *
 from .multistage_opt import *
 from .pka import *
+from .pose_analysis_md import *
 from .protein_cofolding import *
 from .redox_potential import *
 from .scan import *
@@ -43,6 +44,7 @@ WORKFLOW_NAME = Literal[
     "molecular_dynamics",
     "multistage_opt",
     "pka",
+    "pose_analysis_md",
     "protein_cofolding",
     "redox_potential",
     "scan",
@@ -68,10 +70,11 @@ WORKFLOW_MAPPING: dict[WORKFLOW_NAME, Workflow] = {
     "molecular_dynamics": MolecularDynamicsWorkflow,  # type: ignore [dict-item]
     "multistage_opt": MultiStageOptWorkflow,  # type: ignore [dict-item]
     "pka": pKaWorkflow,  # type: ignore [dict-item]
+    "pose_analysis_md": PoseAnalysisMolecularDynamicsWorkflow,  # type: ignore [dict-item]
+    "protein_cofolding": ProteinCofoldingWorkflow,  # type: ignore [dict-item]
     "redox_potential": RedoxPotentialWorkflow,  # type: ignore [dict-item]
     "scan": ScanWorkflow,  # type: ignore [dict-item]
     "solubility": SolubilityWorkflow,  # type: ignore [dict-item]
     "spin_states": SpinStatesWorkflow,  # type: ignore [dict-item]
-    "protein_cofolding": ProteinCofoldingWorkflow,  # type: ignore [dict-item]
     "tautomers": TautomerWorkflow,  # type: ignore [dict-item]
 }

stjames/workflows/pose_analysis_md.py

@@ -0,0 +1,104 @@
+from typing import Annotated, Self
+
+from pydantic import AfterValidator, PositiveFloat, PositiveInt, model_validator
+
+from ..base import Base, round_float
+from ..pdb import PDB
+from ..types import UUID, round_list
+from .workflow import MoleculeWorkflow
+
+
+class BindingPoseContact(Base):
+    """
+    A single protein–ligand contact from an MD trajectory.
+
+    :param protein_atom_index: the index of the protein atom
+    :param ligand_atom_index: the index of the ligand atom
+    :occupancy: the probability of seeing this interaction in a frame, between 0 and 1
+    """
+
+    protein_atom_index: int
+    ligand_atom_index: int
+    occupancy: Annotated[float, AfterValidator(round_float(3))]
+
+
+class BindingPoseTrajectory(Base):
+    """
+    Represents a single trajectory looking at a binding pose.
+
+    :param uuid: the UUID of the trajectory
+    :param ligand_rmsd: the RMSD of the ligand vs. starting pose (aligning the protein)
+    :param contacts: the conserved binding-pose contacts
+    """
+
+    uuid: UUID
+    ligand_rmsd: Annotated[list[float], AfterValidator(round_list(3))] = []
+    contacts: list[BindingPoseContact] = []
+
+
+class PoseAnalysisMolecularDynamicsWorkflow(MoleculeWorkflow):
+    """
+    Pose analysis molecular dynamics workflow.
+
+    Note that the protein can be supplied either by UUID or raw PDB object.
+    We anticipate that the former will dominate deployed usage, but the latter is handy for isolated testing.
+    If, for whatever reason, the workflow is initialized with both a `target_uuid` and a `target`, the UUID will be ignored.
+
+    Inherited:
+    :param initial_molecule: Molecule of interest
+    :param mode: Mode for workflow (currently unused)
+
+    New:
+    :param protein: PDB of the protein.
+    :param protein_uuid: UUID of the protein.
+    :param num_trajectories: how many trajectories to run
+    :param equilibration_time_ns: how long to equilibrate trajectories for, in nanoseconds
+    :param simulation_time_ns: how long to run trajectories for, in nanoseconds
+    :param temperature: the temperature, in K
+    :param pressure_atm: the pressure, in atm
+    :param langevin_timescale_ps: the timescale for the Langevin integrator, in inverse picoseconds
+    :param timestep_fs: the timestep, in femtoseconds
+    :param constrain_hydrogens: whether or not to use SHAKE to freeze bonds to hydrogen
+    :param nonbonded_cutoff: the nonbonded cutoff for particle-mesh Ewald, in Å
+    :param protein_prune_cutoff: the cutoff past which residues will be deleted, in Å
+    :param protein_restraint_cutoff: the cutoff past which alpha-carbons will be constrained, in Å
+    :param protein_restraint_constant: the force constant for backbone restraints, in kcal/mol/Å**2
+    :param ionic_strength_M: the ionic strength of the solution, in M (molar)
+    :param water_buffer: the amount of water to add around the protein, in Å
+
+    Results:
+    :param trajectories: for each replicate, a UUID and the corresponding analysis results
+    :param minimized_protein_uuid: UUID of final system PDB
+    """
+
+    protein: PDB | None = None
+    protein_uuid: UUID | None = None
+
+    num_trajectories: PositiveInt = 4
+    equilibration_time_ns: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 5
+    simulation_time_ns: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 10
+
+    temperature: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 300
+    pressure_atm: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 1.0
+    langevin_timescale_ps: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 1.0
+
+    timestep_fs: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 2
+    constrain_hydrogens: bool = True
+    nonbonded_cutoff: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 8.0
+
+    protein_prune_cutoff: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 9.0
+    protein_restraint_cutoff: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 7.0
+    protein_restraint_constant: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 100
+
+    ionic_strength_M: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 0.10
+    water_buffer: Annotated[PositiveFloat, AfterValidator(round_float(3))] = 6.0
+
+    minimized_protein_uuid: UUID | None = None
+    trajectories: list[BindingPoseTrajectory] = []
+
+    @model_validator(mode="after")
+    def check_cutoff_sanity(self) -> Self:
+        """Check if protein is provided."""
+        if self.protein_prune_cutoff < self.protein_restraint_cutoff:
+            raise ValueError("Pruning cutoff must be larger than restraint cutoff")
+        return self

{stjames-0.0.83.dist-info → stjames-0.0.85.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: stjames
-Version: 0.0.83
+Version: 0.0.85
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames

{stjames-0.0.83.dist-info → stjames-0.0.85.dist-info}/RECORD

@@ -11,11 +11,11 @@ stjames/diis_settings.py,sha256=4m1EQQWBlpHhMnWopix8qOqJv7QCluvdnV9jSKJDFtE,552
 stjames/grid_settings.py,sha256=WrSNGc-8_f87YBZYt9Hh7RbhM4MweADoVzwBMcSqcsE,640
 stjames/int_settings.py,sha256=5HXp8opt5ZyY1UpmfaK7NVloWVLM5jkG0elEEqpVLUo,896
 stjames/message.py,sha256=Rq6QqmHZKecWxYH8fVyXmuoCCPZv8YinvgykSeorXSU,216
-stjames/method.py,sha256=k7WtNvD_0OyXWWDjukmVXFFYfIO-Wg4vY1W58o99-gQ,2821
+stjames/method.py,sha256=xurVdREwRfn_eR3P2dB5p1zUlksO2zwXksN5hvsdKhs,2869
 stjames/mode.py,sha256=xw46Cc7f3eTS8i35qECi-8DocAlANhayK3w4akD4HBU,496
 stjames/molecule.py,sha256=l4S6prH1xflnZtbwidSF2THsiHaSJtRiy1rmUbH366Q,20631
 stjames/opt_settings.py,sha256=LEwGXUEKq5TfU5rr60Z4QQBhCqiw1Ch5w0M_lXawWo8,642
-stjames/pdb.py,sha256=_pIdJCMhIzS4t2HWQa_susDWjZEl0oLn4Njb1QoKvKw,26460
+stjames/pdb.py,sha256=NtNB3M_OXq8raQA5ivjFKcIxOGemBvpGDIlCeb-s80E,26461
 stjames/periodic_cell.py,sha256=eV_mArsY_MPEFSrFEsTC-CyCc6V8ITAXdk7yhjjNI7M,1080
 stjames/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 stjames/scf_settings.py,sha256=WotVgVrayQ_8PUHP39zVtG7iLT9PV41lpzruttFACP8,2356
@@ -37,7 +37,7 @@ stjames/data/isotopes.json,sha256=5ba8QnLrHD_Ypv2xekv2cIRwYrX3MQ19-1FOFtt0RuU,83
 stjames/data/nist_isotopes.json,sha256=d5DNk1dX0iB1waEYIRR6JMHuA7AuYwSBEgBvb4EKyhM,14300
 stjames/data/read_nist_isotopes.py,sha256=y10FNjW43QpC45qib7VHsIghEwT7GG5rsNwHdc9osRI,3309
 stjames/data/symbol_element.json,sha256=vl_buFusTqBd-muYQtMLtTDLy2OtBI6KkBeqkaWRQrg,1186
-stjames/workflows/__init__.py,sha256=rC4KfLzrOKr5FlS4uT3UW1s36-y32vp20VGCw0iHQp0,2649
+stjames/workflows/__init__.py,sha256=S5Z8bOWvvh9-TYV2VgfSpfvvfN1ceShTo5Dro5tmlP0,2796
 stjames/workflows/admet.py,sha256=h8ph6oeRCxU3-_jqRRWPg3RZcheu9JzCHiWqSC9VYKY,1296
 stjames/workflows/basic_calculation.py,sha256=ZX3KwhfyyCTjc2ougQIL4If7gtwZP9WjqpL45mBquW0,573
 stjames/workflows/bde.py,sha256=hdTjwma5L9SrU5F5r6dB1ruB_B6buBUtZHf2sanNW2k,9802
@@ -54,6 +54,7 @@ stjames/workflows/macropka.py,sha256=KRIyk4gsSYL3eqyzCDndStGLwjWSo60cgCAzvAoD1Nk
 stjames/workflows/molecular_dynamics.py,sha256=kxugE73Ntzpj-xpJSoQ1EwGzXXdvi_NTyeP4913EVwE,3173
 stjames/workflows/multistage_opt.py,sha256=P8rxMUhKXMmDi7Id95IOTEmM0xN1ErsKcDJfgY08vjc,16538
 stjames/workflows/pka.py,sha256=j3vBh2YM3nJzJ1XJKPsmYahRCeaU9n3P-G-u9_moaFw,2065
+stjames/workflows/pose_analysis_md.py,sha256=LAn6IXcQIUCt9M54kDzwWkmoCH0r1H99_APFu55skQc,4619
 stjames/workflows/protein_cofolding.py,sha256=_05DCzzKGZFtns9HARAMjcWxVrJU9DPb3VNVWSgwWR8,2173
 stjames/workflows/redox_potential.py,sha256=7S18t9Y3eynSnA3lZbRlvLfdbgeBopdiigLzt1zxg5c,3871
 stjames/workflows/scan.py,sha256=DXQBpa2t2PowAtOwmdgpxaSLq--fEShljzAGSb8Nf5U,2993
@@ -61,8 +62,8 @@ stjames/workflows/solubility.py,sha256=kGfVyPPGDLRpf2j6dSY7woCkfsoXSbUzdSImA4mcM
 stjames/workflows/spin_states.py,sha256=0degmE-frovgoXweshZyjfjqL7nkbaFoO9YoJhvQnaI,4748
 stjames/workflows/tautomer.py,sha256=7eYKziGPg8Km6lfowTzSkgJfJ4SHUPrAmnTf8Bi-SB0,1164
 stjames/workflows/workflow.py,sha256=OE05pt2ZOd8TzTOlBngXCVg9wv_553ZR60VNRPlq0f8,1953
-stjames-0.0.83.dist-info/licenses/LICENSE,sha256=i7ehYBS-6gGmbTcgU4mgk28pyOx2kScJ0kcx8n7bWLM,1084
-stjames-0.0.83.dist-info/METADATA,sha256=VP76r_F2ZWrUka-zckR7MDspo1hne_PKD9xz1xKdNoo,1724
-stjames-0.0.83.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-stjames-0.0.83.dist-info/top_level.txt,sha256=FYCwxl6quhYOAgG-mnPQcCK8vsVM7B8rIUrO-WrQ_PI,8
-stjames-0.0.83.dist-info/RECORD,,
+stjames-0.0.85.dist-info/licenses/LICENSE,sha256=i7ehYBS-6gGmbTcgU4mgk28pyOx2kScJ0kcx8n7bWLM,1084
+stjames-0.0.85.dist-info/METADATA,sha256=NfOJ2u6ZnG8pX0AlUyLJHQXR9SuzaH8IqQERw0Yz5Sg,1724
+stjames-0.0.85.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+stjames-0.0.85.dist-info/top_level.txt,sha256=FYCwxl6quhYOAgG-mnPQcCK8vsVM7B8rIUrO-WrQ_PI,8
+stjames-0.0.85.dist-info/RECORD,,