stjames 0.0.69__tar.gz → 0.0.71__tar.gz

{stjames-0.0.69/stjames.egg-info → stjames-0.0.71}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: stjames
-Version: 0.0.69
+Version: 0.0.71
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames

{stjames-0.0.69 → stjames-0.0.71}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "stjames"
-version = "0.0.69"
+version = "0.0.71"
 description = "standardized JSON atom/molecule encoding scheme"
 readme = "README.md"
 requires-python = ">=3.11"

{stjames-0.0.69 → stjames-0.0.71}/stjames/atomium_stjames/mmcif.py

@@ -425,7 +425,7 @@ def update_models_list(mmcif_dict: dict[str, Any], data_dict: dict[str, Any]) ->
 
     data_dict["models"] = []
     types = {e["id"]: e["type"] for e in mmcif_dict.get("entity", {})}
-    names = {e["id"]: e["name"] for e in mmcif_dict.get("chem_comp", {}) if e["mon_nstd_flag"] != "y"}
+    names = {e["id"]: e["name"] for e in mmcif_dict.get("chem_comp", {}) if e.get("mon_nstd_flag", "n") != "y"}
     entities = {m["id"]: m["entity_id"] for m in mmcif_dict.get("struct_asym", [])}
 
     # sequences = make_sequences(mmcif_dict)

{stjames-0.0.69 → stjames-0.0.71}/stjames/opt_settings.py

@@ -9,6 +9,7 @@ from .constraint import Constraint
 class OptimizationSettings(Base):
     max_steps: PositiveInt = 250
     transition_state: bool = False
+    recalc_hess_every: int = 0  # Recalculate the hessian every `n` steps (or never with 0)
 
     # when are we converged? (Hartree and Hartree/Å)
     max_gradient_threshold: PositiveFloat = 7e-4

{stjames-0.0.69 → stjames-0.0.71}/stjames/workflows/__init__.py

@@ -18,6 +18,7 @@ from .macropka import *
 from .molecular_dynamics import *
 from .multistage_opt import *
 from .pka import *
+from .protein_cofolding import *
 from .redox_potential import *
 from .scan import *
 from .solubility import *
@@ -42,6 +43,7 @@ WORKFLOW_NAME = Literal[
     "molecular_dynamics",
     "multistage_opt",
     "pka",
+    "protein_cofolding",
     "redox_potential",
     "scan",
     "solubility",
@@ -70,5 +72,6 @@ WORKFLOW_MAPPING: dict[WORKFLOW_NAME, Workflow] = {
     "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-0.0.69 → stjames-0.0.71}/stjames/workflows/macropka.py

@@ -45,24 +45,35 @@ class MacropKaWorkflow(SMILESWorkflow):
     :param initial_smiles:
 
     New:
-    :param temperature: the temperature, in K
-    :param min_pH: for precomputed microstate weights
-    :param max_pH: for precomputed microstate weights
+    :param min_pH: for precomputed microstate weights, logD, etc
+    :param max_pH: for precomputed microstate weights, logD, etc
+    :param max_charge: max charge to consider for microstates
+    :param min_charge: min charge to consider for microstates
+    :param compute_aqueous_solubility: whether or not to compute aqueous solubility
+    :param compute_solvation_energy: whether to run a csearch + compute the solvation energy (for Kpuu)
 
     Results:
     :param microstates: microstates
     :param pKa_values: macroscopic pKa values
-    :param microstate_weights_by_pH: precompute the % of different microstates
+    :param isoelectric_point: the isoelectric point (in pH units)
+    :param solvation_energy: the solvation energy, in kcal/mol
+    :param microstate_weights_by_pH: the % of different microstates by pH
+    :param logD_by_pH: the distribution constant (water/octanol) by pH
+    :param aqueous_solubility_by_pH: the log(S)/L of the compound in water, by pH
     """
 
     min_pH: Annotated[float, AfterValidator(round_float(3))] = 0.0
     max_pH: Annotated[float, AfterValidator(round_float(3))] = 14.0
-
     max_charge: int = 2
     min_charge: int = -2
+    compute_aqueous_solubility: bool = False
+    compute_solvation_energy: bool = True
 
     microstates: list[MacropKaMicrostate] = []
     pKa_values: list[MacropKaValue] = []
+    isoelectric_point: Annotated[Optional[float], AfterValidator(round_float(3))] = None
+    solvation_energy: Annotated[Optional[float], AfterValidator(round_float(3))] = None
+
     microstate_weights_by_pH: list[
         tuple[
             Annotated[float, AfterValidator(round_float(3))],
@@ -70,8 +81,6 @@ class MacropKaWorkflow(SMILESWorkflow):
         ]
     ] = []
 
-    isoelectric_point: Annotated[Optional[float], AfterValidator(round_float(3))] = None
-
     logD_by_pH: list[
         tuple[
             Annotated[float, AfterValidator(round_float(3))],
@@ -79,6 +88,13 @@ class MacropKaWorkflow(SMILESWorkflow):
         ]
     ] = []
 
+    aqueous_solubility_by_pH: list[
+        tuple[
+            Annotated[float, AfterValidator(round_float(3))],
+            Annotated[float, AfterValidator(round_float(3))],
+        ]
+    ] = []
+
     @model_validator(mode="after")
     def check_weights(self) -> Self:
         for _, weights in self.microstate_weights_by_pH:

stjames-0.0.71/stjames/workflows/protein_cofolding.py

@@ -0,0 +1,31 @@
+"""Protein Cofolding Workflow."""
+
+from pydantic import BaseModel
+
+from ..types import UUID
+from .workflow import FASTAWorkflow
+
+
+class CofoldingScores(BaseModel):
+    confidence_score: float
+    ptm: float  # predicted template modelling score
+    iptm: float  # interface predicted template modelling score
+
+
+class ProteinCofoldingWorkflow(FASTAWorkflow):
+    """
+    A workflow for predicting structures. Especially protein structures.
+
+    Inherited:
+    :param initial_fasta: fasta string of interest
+
+    New:
+    :param use_msa_server: whether to use the MSA server
+    :param use_templates_server: whether to use the templates server
+    :param predicted_structure_uuid: UUID of the predicted structure
+    """
+
+    use_msa_server: bool = False
+    use_templates_server: bool = False
+    predicted_structure_uuid: UUID | None = None
+    scores: CofoldingScores | None = None

{stjames-0.0.69 → stjames-0.0.71}/stjames/workflows/workflow.py

@@ -22,6 +22,19 @@ class Workflow(Base):
         return repr(self)
 
 
+class FASTAWorkflow(Workflow):
+    """
+    Base class for Workflows that operate on a fasta string.
+
+    :param initial_fasta: fasta string of interest
+    """
+
+    initial_fasta: str
+
+    def __repr__(self) -> str:
+        return f"<{type(self).__name__} {self.initial_fasta}>"
+
+
 class SMILESWorkflow(Workflow):
     """
     Base class for Workflows that operate on a single SMILES string.

{stjames-0.0.69 → stjames-0.0.71/stjames.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: stjames
-Version: 0.0.69
+Version: 0.0.71
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames

{stjames-0.0.69 → stjames-0.0.71}/stjames.egg-info/SOURCES.txt

@@ -62,6 +62,7 @@ stjames/workflows/macropka.py
 stjames/workflows/molecular_dynamics.py
 stjames/workflows/multistage_opt.py
 stjames/workflows/pka.py
+stjames/workflows/protein_cofolding.py
 stjames/workflows/redox_potential.py
 stjames/workflows/scan.py
 stjames/workflows/solubility.py