stjames 0.0.121__py3-none-any.whl → 0.0.123__py3-none-any.whl

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/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 +41,50 @@ class ScreeningSettings(BaseModel):
     max_confs: int | None = None
 
 
+class ConformerClusteringDescriptor(LowercaseStrEnum):
+    """
+    Potential descriptors to employ in conformer clustering.
+    """
+
+    SOLVENT_ACCESSIBLE_SURFACE_AREA = "solvent_accessible_surface_area"
+    POLAR_SOLVENT_ACCESSIBLE_SURACE_AREA = "polar_solvent_accessible_surface_area"
+    RADIUS_OF_GYRATION = "radius_of_gyration"
+    PLANE_OF_BEST_FIT = "plane_of_best_fit"
+    NORMALIZED_PRINCIPAL_MOMENT_RATIO_1 = "normalized_principal_moment_ratio_1"
+    NORMALIZED_PRINCIPAL_MOMENT_RATIO_2 = "normalized_principal_moment_ratio_2"
+
+
+class ConformerClusteringSettings(Base):
+    """
+    Settings for clustering conformers based on their three-dimensional properties.
+
+    The properties used for clustering by default 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
+    """
+
+    descriptors: list[ConformerClusteringDescriptor] = [
+        ConformerClusteringDescriptor.SOLVENT_ACCESSIBLE_SURFACE_AREA,
+        ConformerClusteringDescriptor.POLAR_SOLVENT_ACCESSIBLE_SURACE_AREA,
+        ConformerClusteringDescriptor.RADIUS_OF_GYRATION,
+        ConformerClusteringDescriptor.PLANE_OF_BEST_FIT,
+        ConformerClusteringDescriptor.NORMALIZED_PRINCIPAL_MOMENT_RATIO_1,
+        ConformerClusteringDescriptor.NORMALIZED_PRINCIPAL_MOMENT_RATIO_2,
+    ]
+
+    num_clusters: PositiveInt = 5
+    conformers_per_cluster: PositiveInt = 3
+
+
 class ConformerGenSettings(BaseModel):
     """
     Conformer generation settings.
@@ -302,6 +346,7 @@ class ConformerGenMixin(BaseModel):
     :param constraints: constraints to add
     :param nci: add a constraining potential for non-covalent interactions
     :param max_confs: maximum number of conformers to keep
+    :param clustering_settings: how to cluster the conformers (if at all)
     """
 
     conf_gen_mode: Mode = Mode.RAPID
@@ -310,6 +355,8 @@ 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/workflows/dna.py

@@ -0,0 +1,13 @@
+"""DNA-related workflow data models."""
+
+from ..base import Base
+
+
+class DNASequence(Base):
+    """
+    DNA sequence metadata.
+
+    :param sequence: nucleotide string
+    """
+
+    sequence: str

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/workflows/protein.py

@@ -0,0 +1,15 @@
+"""Protein-related workflow data models."""
+
+from ..base import Base
+
+
+class ProteinSequence(Base):
+    """
+    Protein sequence metadata including cyclic flag.
+
+    :param sequence: amino-acid sequence string
+    :param cyclic: whether this sequence forms a cyclic peptide (defaults to False)
+    """
+
+    sequence: str
+    cyclic: bool = False

stjames/workflows/protein_cofolding.py

@@ -68,10 +68,14 @@ class AffinityScore(BaseModel):
 
 class ProteinCofoldingWorkflow(FASTAWorkflow):
     """
-    A workflow for predicting structures. Especially protein structures.
+    Workflow for predicting structures.
+
+    Especially protein structures. At least one biological sequence is required.
 
     Inherited:
     :param initial_protein_sequences: protein sequences of interest
+    :param initial_dna_sequences: DNA sequences of interest
+    :param initial_rna_sequences: RNA sequences of interest
     :param initial_smiles_list: SMILES strings of interest
 
     New:

stjames/workflows/rna.py

@@ -0,0 +1,13 @@
+"""RNA-related workflow data models."""
+
+from ..base import Base
+
+
+class RNASequence(Base):
+    """
+    RNA sequence metadata.
+
+    :param sequence: nucleotide string
+    """
+
+    sequence: str

stjames/workflows/workflow.py

@@ -1,5 +1,7 @@
 """Base classes for workflows."""
 
+from typing import Any
+
 from pydantic import field_validator
 
 from ..base import Base
@@ -7,6 +9,9 @@ from ..message import Message
 from ..mode import Mode
 from ..molecule import Molecule
 from ..types import UUID
+from .dna import DNASequence
+from .protein import ProteinSequence
+from .rna import RNASequence
 
 
 class Workflow(Base):
@@ -22,31 +27,30 @@ class Workflow(Base):
         return repr(self)
 
 
-class ProteinSequence(Base):
-    """
-    Protein sequence metadata including cyclic flag.
-
-    :param sequence: amino-acid sequence string
-    :param cyclic: whether this sequence forms a cyclic peptide (defaults to False)
-    """
-
-    sequence: str
-    cyclic: bool = False
-
-
 class FASTAWorkflow(Workflow):
     """
-    Base class for Workflows that operate on protein sequences and SMILES.
+    Base class for Workflows that operate on biological sequences and SMILES.
 
-    :param initial_protein_sequences: proteins to evaluate, either plain sequence strings or ProteinSequence objects with cyclic flags
+    :param initial_protein_sequences: protein sequences to evaluate, either plain sequence strings or ProteinSequence objects with metadata
+    :param initial_dna_sequences: DNA sequences to evaluate, either plain sequence strings or DNASequence objects with metadata
+    :param initial_rna_sequences: RNA sequences to evaluate, either plain sequence strings or RNASequence objects with metadata
     :param initial_smiles_list: SMILES strings of interest
     :param ligand_binding_affinity_index: optional index selecting which ligand affinity to evaluate
+    :raises ValueError: if none of the sequence lists are provided
     """
 
-    initial_protein_sequences: list[ProteinSequence] | list[str]
-    initial_smiles_list: list[str] | None = None
+    initial_protein_sequences: list[ProteinSequence] | list[str] = []
+    initial_dna_sequences: list[DNASequence] = []
+    initial_rna_sequences: list[RNASequence] = []
+    initial_smiles_list: list[str] = []
     ligand_binding_affinity_index: int | None = None
 
+    def model_post_init(self, __context: Any) -> None:
+        if not (self.initial_protein_sequences or self.initial_dna_sequences or self.initial_rna_sequences):
+            raise ValueError(
+                "Provide at least one of `initial_protein_sequences`, `initial_dna_sequences`, or `initial_rna_sequences`.",
+            )
+
 
 class SMILESWorkflow(Workflow):
     """
@@ -95,6 +99,16 @@ class MoleculeWorkflow(Workflow):
         return mode
 
 
+class ProteinSequenceWorkflow(Workflow):
+    """
+    Base class for Workflows that operate on protein sequences.
+
+    :param initial_protein_sequences: protein sequences to evaluate, either plain sequence strings or ProteinSequence objects with metadata
+    """
+
+    initial_protein_sequences: list[ProteinSequence] | list[str] = []
+
+
 class DBCalculation(Base):
     """Encodes a calculation that's in the database. This isn't terribly useful by itself."""
 

{stjames-0.0.121.dist-info → stjames-0.0.123.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: stjames
-Version: 0.0.121
+Version: 0.0.123
 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.dist-info → stjames-0.0.123.dist-info}/RECORD

@@ -37,14 +37,15 @@ stjames/data/read_nist_isotopes.py,sha256=y10FNjW43QpC45qib7VHsIghEwT7GG5rsNwHdc
 stjames/data/symbol_element.json,sha256=vl_buFusTqBd-muYQtMLtTDLy2OtBI6KkBeqkaWRQrg,1186
 stjames/optimization/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 stjames/optimization/freezing_string_method.py,sha256=eEQBqbYHgJH9gVRLDIFtGuPcsHHMLAAt1hF3jtq70lo,2285
-stjames/workflows/__init__.py,sha256=GiSXuBCA2tE5eXHnVYJvjtoqX_zvCn8t0wpkvK1HEls,3438
+stjames/workflows/__init__.py,sha256=wzLBi71MgMxlxRXw3N7feazCym6qNRJ8e4pRk3UXPHM,3520
 stjames/workflows/admet.py,sha256=qFUpCFiLW-3gzuEjCMNBJ6DEG_vquJcPAsN4SVZRfdE,1289
 stjames/workflows/basic_calculation.py,sha256=wIiq2lFRN4nxN0__X_JbPSeaUeJ4tKUyg6NaB1xqoEY,1079
 stjames/workflows/batch_docking.py,sha256=o-t5FkfLlbe60jX1_ZeqWSJJ5vsjEIbTa5GLN3ny_tk,1590
 stjames/workflows/bde.py,sha256=g_In-caftXiimrhfdptHjpfrYQUs3vF58qYmRnaTN8g,10825
 stjames/workflows/conformer.py,sha256=18aO6ngMBeGAmQkBdLGCCHr398RIYr1v2hD2IT1u4cc,3005
-stjames/workflows/conformer_search.py,sha256=1kBUT0yCcTPTCtxg1tlTKHRRXkfNYNqzla_89lDEL9k,15696
+stjames/workflows/conformer_search.py,sha256=TaDI3unNjaxBKj4YHASwSaNQHlVSwuZDZdTIxk7MC4Y,17638
 stjames/workflows/descriptors.py,sha256=T4tc7xdtBdxESGO86KR323jPQ2pgwxBqgV0khA6MEgQ,584
+stjames/workflows/dna.py,sha256=_M79WikFujCsUWr4YaEdOoeDDKPV_DhKptWt0ptktko,194
 stjames/workflows/docking.py,sha256=t30kqeFXQ0yrlqvN6Jdwt0SdfnJLDsfK-7yFi0gwNbY,4753
 stjames/workflows/double_ended_ts_search.py,sha256=ovJgEVFc6c3mijCE3TKAY70YvqNmAZ5Y4XgV4-tIxBI,3127
 stjames/workflows/electronic_properties.py,sha256=GT3-NC7w-dbcOJ-3AzJ7LgzH6frTbiH2Iyb9BCa-SvY,4112
@@ -54,21 +55,24 @@ stjames/workflows/ion_mobility.py,sha256=5vUjEYCnF9sN3dTqqEgWAq0jAfdoFvkLubemoXE
 stjames/workflows/irc.py,sha256=ZP7icylW8rgo_Uh7h3bmyumn0ru1IyF-61nP5Jnmq3M,3402
 stjames/workflows/macropka.py,sha256=Krj0xXuB-u57Kqlf4bbRiHDUWCpliFr6YPiYqPmYaWk,3803
 stjames/workflows/molecular_dynamics.py,sha256=cgjede9TWf-eXRFeUcM59cyVQAhSduL6L0J0oMrX3xc,3543
+stjames/workflows/msa.py,sha256=nK3KmPQv9Sr7yRjNfDWSXIgBrk3PnhvDYHnsVoqoS-M,773
 stjames/workflows/multistage_opt.py,sha256=UN-4WLsT2WEjO5KqDPrcCkb708Co-ZScHx3g2bto768,16597
 stjames/workflows/nmr.py,sha256=1QEF4SB6dWIr-jzLEZ7V972UnRUOTufOJSHwIGyV3dM,2681
 stjames/workflows/pka.py,sha256=i-jzl2lN0yRWc0tgrWSBCplITEByfRyEQrlUhjnzcBc,4580
 stjames/workflows/pose_analysis_md.py,sha256=dpWVKC-8fPdw6ExIXk9xbeVBDUMUYQECpixb-oFa23I,4803
+stjames/workflows/protein.py,sha256=MfwJ3qn24cCoUEczMH7A2NyBlI9t_VcwOowohTPDtYM,346
 stjames/workflows/protein_binder_design.py,sha256=KnPKQJTMrSO5xfw64Bh7T0wHck1NtysVwkVgHs1cGws,12013
-stjames/workflows/protein_cofolding.py,sha256=w7Sg_ttU4bcJb7wlVcI_AAsLM9WVAJcU5ucbNb5Iyzw,4326
+stjames/workflows/protein_cofolding.py,sha256=5rs6wgksW5zKpcEkv0_B4Clt9dSQ-42oKF8fJtSRoaY,4495
 stjames/workflows/redox_potential.py,sha256=7S18t9Y3eynSnA3lZbRlvLfdbgeBopdiigLzt1zxg5c,3871
+stjames/workflows/rna.py,sha256=FZO3UkRhgG3EnGXsQ70eAZTbeEY2P9u60oLD6JuPPMc,194
 stjames/workflows/scan.py,sha256=lgpvrrFG03GWQj2tWeBqPQVYSCGLgYdnQsU9bAUZQok,3317
 stjames/workflows/solubility.py,sha256=lfCVvJjqEaddLUpK6WBxjB7u12Sci-K95A5_qIMkIRM,3028
 stjames/workflows/spin_states.py,sha256=0degmE-frovgoXweshZyjfjqL7nkbaFoO9YoJhvQnaI,4748
 stjames/workflows/strain.py,sha256=paYxDDQTB1eYP_c2kLVz1-QX7Vpw0LLb3ujnFin_SOM,1834
 stjames/workflows/tautomer.py,sha256=7eYKziGPg8Km6lfowTzSkgJfJ4SHUPrAmnTf8Bi-SB0,1164
-stjames/workflows/workflow.py,sha256=cYNP_tK1afJTscXJzYv5VGe8n2Est6PpthS268oRi1U,2494
-stjames-0.0.121.dist-info/licenses/LICENSE,sha256=i05z7xEhyrg6f8j0lR3XYjShnF-MJGFQ-DnpsZ8yiVI,1084
-stjames-0.0.121.dist-info/METADATA,sha256=TeYRvGYD3m3c1KxoQa197eGf6oJ9KvyNkJ0gLN4kEJ0,1725
-stjames-0.0.121.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-stjames-0.0.121.dist-info/top_level.txt,sha256=FYCwxl6quhYOAgG-mnPQcCK8vsVM7B8rIUrO-WrQ_PI,8
-stjames-0.0.121.dist-info/RECORD,,
+stjames/workflows/workflow.py,sha256=dJYK9hY8FqNsD-foQsTI7Mpk2aTY87ASjMFgerx6gtQ,3432
+stjames-0.0.123.dist-info/licenses/LICENSE,sha256=i05z7xEhyrg6f8j0lR3XYjShnF-MJGFQ-DnpsZ8yiVI,1084
+stjames-0.0.123.dist-info/METADATA,sha256=r1v4SR_lfdasc-yuQRdmxI7nJXSnVKvbjQiMz4mwW54,1725
+stjames-0.0.123.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+stjames-0.0.123.dist-info/top_level.txt,sha256=FYCwxl6quhYOAgG-mnPQcCK8vsVM7B8rIUrO-WrQ_PI,8
+stjames-0.0.123.dist-info/RECORD,,