stjames 0.0.121__tar.gz → 0.0.122__tar.gz

{stjames-0.0.121/stjames.egg-info → stjames-0.0.122}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: stjames
-Version: 0.0.121
+Version: 0.0.122
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames

{stjames-0.0.121 → stjames-0.0.122}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "stjames"
-version = "0.0.121"
+version = "0.0.122"
 description = "standardized JSON atom/molecule encoding scheme"
 readme = "README.md"
 requires-python = ">=3.11"

{stjames-0.0.121 → stjames-0.0.122}/stjames/workflows/__init__.py

@@ -18,6 +18,7 @@ from .ion_mobility import *
 from .irc import *
 from .macropka import *
 from .molecular_dynamics import *
+from .msa import *
 from .multistage_opt import *
 from .nmr import *
 from .pka import *
@@ -49,6 +50,7 @@ WORKFLOW_NAME = Literal[
     "irc",
     "macropka",
     "molecular_dynamics",
+    "msa",
     "multistage_opt",
     "nmr",
     "pka",
@@ -81,6 +83,7 @@ WORKFLOW_MAPPING: dict[WORKFLOW_NAME, Workflow] = {
     "macropka": MacropKaWorkflow,  # type: ignore [dict-item]
     "molecular_dynamics": MolecularDynamicsWorkflow,  # type: ignore [dict-item]
     "multistage_opt": MultiStageOptWorkflow,  # type: ignore [dict-item]
+    "msa": MSAWorkflow,  # type: ignore [dict-item]
     "nmr": NMRSpectroscopyWorkflow,  # type: ignore [dict-item]
     "pka": pKaWorkflow,  # type: ignore [dict-item]
     "pose_analysis_md": PoseAnalysisMolecularDynamicsWorkflow,  # type: ignore [dict-item]

{stjames-0.0.121 → stjames-0.0.122}/stjames/workflows/conformer_search.py

@@ -3,9 +3,9 @@
 from abc import ABC
 from typing import Annotated, Literal, Self, Sequence, TypeVar
 
-from pydantic import AfterValidator, BaseModel, Field, field_validator, model_validator
+from pydantic import AfterValidator, BaseModel, Field, PositiveInt, field_validator, model_validator
 
-from ..base import LowercaseStrEnum
+from ..base import Base, LowercaseStrEnum
 from ..constraint import Constraint
 from ..method import Method, XTBMethod
 from ..mode import Mode
@@ -41,6 +41,28 @@ class ScreeningSettings(BaseModel):
     max_confs: int | None = None
 
 
+class ConformerClusteringSettings(Base):
+    """
+    Settings for (optionally) clustering conformers based on three-dimensional properties.
+
+    The properties used for clustering are:
+    - Solvent-accessible surface area
+    - Polar solvent-accessible surface area
+    - Radius of gyration
+    - Plane of best fit
+    - Normalized principal moment ratios 1 and 2
+
+    Rowan uses k-means clustering to identify representative conformers.
+    This loosely follows Wilcken and co-workers (10.1007/s10822-020-00337-7).
+
+    :param num_clusters: the number of clusters to include
+    :param conformers_per_cluster: the number of compounds to pick from each cluster
+    """
+
+    num_clusters: PositiveInt = 5
+    conformers_per_cluster: PositiveInt = 3
+
+
 class ConformerGenSettings(BaseModel):
     """
     Conformer generation settings.
@@ -310,6 +332,8 @@ class ConformerGenMixin(BaseModel):
     nci: bool = False
     max_confs: int | None = None
 
+    conformer_clustering_settings: ConformerClusteringSettings | None = None
+
     @model_validator(mode="after")
     def validate_and_build_conf_gen_settings(self) -> Self:
         """Validate and build the ConformerGenSettings."""

stjames-0.0.122/stjames/workflows/msa.py

@@ -0,0 +1,31 @@
+from ..base import LowercaseStrEnum
+from .workflow import ProteinSequenceWorkflow
+
+
+class MSAFormat(LowercaseStrEnum):
+    """Format of the MSA."""
+
+    COLABFOLD_DEFAULT = "colabfold_default"
+    AF3_JSON = "af3_json"
+
+
+class MSAWorkflow(ProteinSequenceWorkflow):
+    """
+    Workflow for generating a MSA from protein sequences.
+
+    Inherited:
+    :param initial_protein_sequences: protein sequences of interest
+
+    New:
+    :param format: the format of the MSA return files
+
+    Results:
+    :param a3m_file: A3M file string
+    :param m8_file: M8 file string
+    :param af3_json_file: AF3 JSON file string
+    """
+
+    format: MSAFormat = MSAFormat.COLABFOLD_DEFAULT
+    a3m_file: str | None = None
+    m8_file: str | None = None
+    af3_json_file: str | None = None

{stjames-0.0.121 → stjames-0.0.122}/stjames/workflows/workflow.py

@@ -95,6 +95,16 @@ class MoleculeWorkflow(Workflow):
         return mode
 
 
+class ProteinSequenceWorkflow(Workflow):
+    """
+    Base class for Workflows that operate on protein sequences.
+
+    :param initial_protein_sequences: protein sequences of interest
+    """
+
+    protein_sequences: list[str]
+
+
 class DBCalculation(Base):
     """Encodes a calculation that's in the database. This isn't terribly useful by itself."""
 

{stjames-0.0.121 → stjames-0.0.122/stjames.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: stjames
-Version: 0.0.121
+Version: 0.0.122
 Summary: standardized JSON atom/molecule encoding scheme
 Author-email: Corin Wagen <corin@rowansci.com>
 Project-URL: Homepage, https://github.com/rowansci/stjames

{stjames-0.0.121 → stjames-0.0.122}/stjames.egg-info/SOURCES.txt

@@ -62,6 +62,7 @@ stjames/workflows/ion_mobility.py
 stjames/workflows/irc.py
 stjames/workflows/macropka.py
 stjames/workflows/molecular_dynamics.py
+stjames/workflows/msa.py
 stjames/workflows/multistage_opt.py
 stjames/workflows/nmr.py
 stjames/workflows/pka.py