Release v0.8.2

- release rfdiffusion interface
- fixes problems with refactored fit umap, svd, predictor
- a lot of docstrings updated

Author: markgeejw

anaconda_build/meta.yaml

@@ -1,6 +1,6 @@
 package:
   name: openprotein-python
-  version: "0.8.0"
+  version: "0.8.2"
 
 source:
   path: ../
@@ -14,10 +14,12 @@ requirements:
   build:
     - python >=3.10,<3.13
     - hatchling >=1.25.0,<2
+    - hatch-vcs >=0.5.0,<1
   host:
     - python >=3.10,<3.13
     - pip
     - hatchling >=1.25.0,<2
+    - hatch-vcs >=0.5.0,<1
   run:
     - python >=3.10,<3.13
     - requests >=2.32.3,<3

openprotein/__init__.py

@@ -17,6 +17,7 @@
 from openprotein.prompt import PromptAPI
 from openprotein.embeddings import EmbeddingsAPI
 from openprotein.fold import FoldAPI
+from openprotein.models import ModelsAPI
 from openprotein.svd import SVDAPI
 from openprotein.umap import UMAPAPI
 from openprotein.predictor import PredictorAPI
@@ -40,6 +41,7 @@ class OpenProtein(APISession):
     _fold = None
     _predictor = None
     _design = None
+    _models = None
 
     def wait(self, future: Future, *args, **kwargs):
         return future.wait(*args, **kwargs)
@@ -149,5 +151,14 @@ def fold(self) -> FoldAPI:
             self._fold = FoldAPI(self)
         return self._fold
 
+    @property
+    def models(self) -> "ModelsAPI":
+        """
+        The models submodule provides a unified entry point to all protein models.
+        """
+        if self._models is None:
+            self._models = ModelsAPI(self)
+        return self._models
+
 
 connect = OpenProtein

openprotein/_version.py

@@ -1,9 +1,48 @@
-try:
+"""Compute the version number and store it in the `__version__` variable.
+
+Based on <https://github.com/maresb/hatch-vcs-footgun-example>.
+"""
+
+
+def _get_hatch_version():
+    """Compute the most up-to-date version number in a development environment.
+
+    Returns `None` if Hatchling is not installed, e.g. in a production environment.
+
+    For more details, see <https://github.com/maresb/hatch-vcs-footgun-example/>.
+    """
+    import os
+
+    try:
+        from hatchling.metadata.core import ProjectMetadata
+        from hatchling.plugin.manager import PluginManager
+        from hatchling.utils.fs import locate_file
+    except ImportError:
+        # Hatchling is not installed, so probably we are not in
+        # a development environment.
+        return None
+
+    pyproject_toml = locate_file(__file__, "pyproject.toml")
+    if pyproject_toml is None:
+        raise RuntimeError("pyproject.toml not found although hatchling is installed")
+    root = os.path.dirname(pyproject_toml)
+    metadata = ProjectMetadata(root=root, plugin_manager=PluginManager())
+    # Version can be either statically set in pyproject.toml or computed dynamically:
+    return metadata.core.version or metadata.hatch.version.cached
+
+
+def _get_importlib_metadata_version():
+    """Compute the version number using importlib.metadata.
+
+    This is the official Pythonic way to get the version number of an installed
+    package. However, it is only updated when a package is installed. Thus, if a
+    package is installed in editable mode, and a different version is checked out,
+    then the version number will not be updated.
+    """
     from importlib.metadata import version
-except ModuleNotFoundError:
-    from importlib_metadata import version  # type: ignore - py37
 
-try:
-    __version__ = version("openprotein-python")
-except:
-    __version__ = "None"
+    __version__ = version(__package__)  # type: ignore
+    return __version__
+
+
+__version__ = _get_hatch_version() or _get_importlib_metadata_version()

openprotein/align/msa.py

@@ -22,33 +22,6 @@
 class MSAFuture(AlignFuture, Future):
     """
     Represents a future for MSA (Multiple Sequence Alignment) results.
-
-    Parameters
-    ----------
-    session : APISession
-        An instance of APISession for API interactions.
-    job : MSAJob
-        The MSA job.
-    page_size : int, optional
-        The number of results to fetch in a single page. Defaults to config.POET_PAGE_SIZE.
-
-    Attributes
-    ----------
-    session : APISession
-        An instance of APISession for API interactions.
-    job : MSAJob | MafftJob | ClustalOJob | AbNumberJob
-        The MSA job.
-    page_size : int
-        The number of results to fetch in a single page.
-    msa_id : str
-        The job ID for the MSA.
-
-    Methods
-    -------
-    get(verbose=False)
-        Retrieve the MSA of the job as an iterator over CSV rows.
-    sample_prompt(...)
-        Create a protein sequence prompt from the linked MSA for PoET Jobs.
     """
 
     job: MSAJob | MafftJob | ClustalOJob | AbNumberJob

openprotein/base.py

@@ -27,7 +27,7 @@ def __init__(self, token):
         self.token = token
 
     def __call__(self, r):
-        r.headers["authorization"] = "Bearer " + self.token
+        r.headers["Authorization"] = "Bearer " + self.token
         return r
 
 

openprotein/embeddings/embeddings.py

@@ -43,23 +43,32 @@ class EmbeddingsAPI:
 
     # added for static typing, eg pylance, for autocomplete
     # at init these are all overwritten.
+
+    #: PoET-2 model
+    poet2: PoET2Model
+    #: PoET model
+    poet: PoETModel
+    #: Prot-seq model
     prot_seq: OpenProteinModel
+    #: Rotaprot model trained on UniRef50
     rotaprot_large_uniref50w: OpenProteinModel
+    #: Rotaprot model trained on UniRef90
     rotaprot_large_uniref90_ft: OpenProteinModel
-    poet: PoETModel
     poet_2: PoET2Model
-    poet2: PoET2Model
 
+    #: ESM1b model
     esm1b: ESMModel  # alias
     esm1b_t33_650M_UR50S: ESMModel
 
+    #: ESM1v model
     esm1v: ESMModel  # alias
     esm1v_t33_650M_UR90S_1: ESMModel
     esm1v_t33_650M_UR90S_2: ESMModel
     esm1v_t33_650M_UR90S_3: ESMModel
     esm1v_t33_650M_UR90S_4: ESMModel
     esm1v_t33_650M_UR90S_5: ESMModel
 
+    #: ESM2 model
     esm2: ESMModel  # alias
     esm2_t12_35M_UR50D: ESMModel
     esm2_t30_150M_UR50D: ESMModel

openprotein/embeddings/esm.py

@@ -1,9 +1,9 @@
 """Community-based ESM models."""
 
-from .models import EmbeddingModel
+from .models import AttnModel, EmbeddingModel
 
 
-class ESMModel(EmbeddingModel):
+class ESMModel(AttnModel, EmbeddingModel):
     """
     Class providing inference endpoints for Facebook's ESM protein language models.
 
@@ -13,9 +13,9 @@ class ESMModel(EmbeddingModel):
 
     .. code-block:: python
 
-    >>> import openprotein
-    >>> session = openprotein.connect(username="user", password="password")
-    >>> session.embedding.esm2_t12_35M_UR50D?
+        >>> import openprotein
+        >>> session = openprotein.connect(username="user", password="password")
+        >>> session.embedding.esm2_t12_35M_UR50D?
     """
 
     model_id = [

openprotein/embeddings/future.py

@@ -63,7 +63,15 @@ def sequences(self) -> list[bytes] | list[str]:
     def id(self):
         return self.job.job_id
 
-    def keys(self):
+    def __keys__(self):
+        """
+        Get the list of sequences submitted for the embed request.
+
+        Returns
+        -------
+        list of bytes
+            List of sequences.
+        """
         return self.sequences
 
     def get_item(self, sequence: bytes) -> np.ndarray: