openprotein-python 0.14.0__tar.gz → 0.14.2__tar.gz

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openprotein-python
-Version: 0.14.0
+Version: 0.14.2
 Summary: OpenProtein Python interface.
 Author-email: Mark Gee <markgee@ne47.bio>, "Timothy Truong Jr." <ttruong@ne47.bio>, Tristan Bepler <tbepler@ne47.bio>
 License-Expression: MIT

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/clustering/api.py

@@ -17,17 +17,17 @@ PATH_PREFIX = "v1/clustering"
 def clustering_list_get(
     session: APISession,
     method: str | None = None,
-    page_size: int | None = None,
-    page_offset: int | None = None,
+    limit: int | None = None,
+    offset: int | None = None,
 ) -> list[ClusteringMetadata]:
     """List clustering jobs, optionally filtered by method."""
     params: dict = {}
     if method is not None:
         params["method"] = method
-    if page_size is not None:
-        params["page_size"] = page_size
-    if page_offset is not None:
-        params["page_offset"] = page_offset
+    if limit is not None:
+        params["limit"] = limit
+    if offset is not None:
+        params["offset"] = offset
     response = session.get(PATH_PREFIX, params=params or None)
     return TypeAdapter(list[ClusteringMetadata]).validate_python(response.json())
 
@@ -80,16 +80,9 @@ def clustering_hierarchical_post(
     assay_id: str | None = None,
     reduction: str | None = None,
     svd_id: str | None = None,
-    force_recompute: bool = False,
     **kwargs,
 ) -> HierarchicalFitJob:
-    """POST to create a hierarchical clustering fit job.
-
-    Parameters
-    ----------
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
-    """
+    """POST to create a hierarchical clustering fit job."""
     body: dict = {
         "model_id": model_id,
         "feature_type": feature_type,
@@ -112,6 +105,5 @@ def clustering_hierarchical_post(
         body["assay_id"] = assay_id
     body.update(**kwargs)
 
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(f"{PATH_PREFIX}/hierarchical", json=body, params=params)
+    response = session.post(f"{PATH_PREFIX}/hierarchical", json=body)
     return HierarchicalFitJob.model_validate(response.json())

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/clustering/clustering.py

@@ -64,9 +64,7 @@ class ClusteringAPI:
         assay_id = (
             assay.assay_id
             if isinstance(assay, AssayMetadata)
-            else assay.id
-            if isinstance(assay, AssayDataset)
-            else assay
+            else assay.id if isinstance(assay, AssayDataset) else assay
         )
         if sequences is not None and assay_id is not None:
             raise InvalidParameterError(
@@ -86,9 +84,7 @@ class ClusteringAPI:
         feature_type = (
             FeatureType.PLM
             if isinstance(model, EmbeddingModel)
-            else FeatureType.SVD
-            if isinstance(model, SVDModel)
-            else feature_type
+            else FeatureType.SVD if isinstance(model, SVDModel) else feature_type
         )
         if feature_type is None:
             raise InvalidParameterError(
@@ -148,9 +144,6 @@ class ClusteringAPI:
             reduction.value if isinstance(reduction, ReductionType) else reduction
         )
 
-        # Advanced flags such as `force_recompute` are accepted via **kwargs
-        # only (intentionally kept out of the typed signature / autocomplete):
-        # they bypass the backend result cache and are easy to misuse.
         job = api.clustering_hierarchical_post(
             session=self.session,
             model_id=model_id,
@@ -175,12 +168,13 @@ class ClusteringAPI:
     def list(
         self,
         method: str | None = None,
-        page_size: int | None = None,
-        page_offset: int | None = None,
+        limit: int | None = None,
+        offset: int | None = None,
     ) -> list[HierarchicalClusteringFuture]:
         """List clustering jobs, optionally filtering by method.
 
-        Pass `page_size` / `page_offset` to paginate."""
+        Pass `limit` / `offset` to paginate (the clustering list endpoint
+        uses `limit`/`offset`, unlike the `jobs` endpoint's page_size/page_offset)."""
         # Single-method dispatch today; when new methods are added,
         # branch on metadata.method to pick the concrete future type.
         return [
@@ -188,7 +182,7 @@ class ClusteringAPI:
             for md in api.clustering_list_get(
                 self.session,
                 method=method,
-                page_size=page_size,
-                page_offset=page_offset,
+                limit=limit,
+                offset=offset,
             )
         ]

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/embeddings/api.py

@@ -265,7 +265,6 @@ def request_post(
     model_id: str,
     sequences: list[bytes] | list[str],
     reduction: str | None = "MEAN",
-    force_recompute: bool = False,
     **kwargs,
 ) -> EmbeddingsJob:
     """
@@ -282,8 +281,6 @@ def request_post(
         sequences to request results for
     reduction : str | None
         reduction to apply to the embeddings. options are None, "MEAN", or "SUM". defaul: "MEAN"
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs:
         Optional parameters for models, e.g. prompt_id for PoET
 
@@ -309,8 +306,7 @@ def request_post(
             ]
     if kwargs.get("decoder_type"):
         body["decoder_type"] = kwargs["decoder_type"]
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return EmbeddingsJob.model_validate(response.json())
 
 
@@ -318,7 +314,6 @@ def request_logits_post(
     session: APISession,
     model_id: str,
     sequences: list[bytes] | list[str],
-    force_recompute: bool = False,
     **kwargs,
 ) -> LogitsJob:
     """
@@ -333,8 +328,6 @@ def request_logits_post(
         model ID to request results from
     sequences : List[bytes]
         sequences to request results for
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs:
         Optional parameters for models, e.g. prompt_id for PoET
 
@@ -358,8 +351,7 @@ def request_logits_post(
             ]
     if kwargs.get("decoder_type"):
         body["decoder_type"] = kwargs["decoder_type"]
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return LogitsJob.model_validate(response.json())
 
 
@@ -367,7 +359,6 @@ def request_attn_post(
     session: APISession,
     model_id: str,
     sequences: list[bytes] | list[str],
-    force_recompute: bool = False,
     **kwargs,
 ) -> AttnJob:
     """
@@ -383,8 +374,6 @@ def request_attn_post(
         model ID to request results from
     sequences : List[bytes]
         sequences to request results for
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs:
         Optional parameters for models, e.g. prompt_id for PoET
 
@@ -406,8 +395,7 @@ def request_attn_post(
             body["use_query_structure_in_decoder"] = kwargs[
                 "use_query_structure_in_decoder"
             ]
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return AttnJob.model_validate(response.json())
 
 
@@ -415,7 +403,6 @@ def request_score_post(
     session: APISession,
     model_id: str,
     sequences: list[bytes] | list[str],
-    force_recompute: bool = False,
     **kwargs,
 ) -> ScoreJob:
     """
@@ -431,8 +418,6 @@ def request_score_post(
         model ID to request results from
     sequences : List[bytes]
         sequences to request results for
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
 
     Returns
     -------
@@ -453,8 +438,7 @@ def request_score_post(
             ]
     if kwargs.get("decoder_type"):
         body["decoder_type"] = kwargs["decoder_type"]
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return ScoreJob.model_validate(response.json())
 
 
@@ -464,7 +448,6 @@ def request_score_indel_post(
     base_sequence: bytes | str,
     insert: str | None = None,
     delete: list[int] | None = None,
-    force_recompute: bool = False,
     **kwargs,
 ) -> ScoreIndelJob:
     """
@@ -484,8 +467,6 @@ def request_score_indel_post(
         Insertion fragment at each site.
     delete: int | None
         Range of size of fragment to delete at each site.
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs:
         Optional parameters for models, e.g. prompt_id for PoET
 
@@ -516,8 +497,7 @@ def request_score_indel_post(
             ]
     if kwargs.get("decoder_type"):
         body["decoder_type"] = kwargs["decoder_type"]
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return ScoreIndelJob.model_validate(response.json())
 
 
@@ -525,7 +505,6 @@ def request_score_single_site_post(
     session: APISession,
     model_id: str,
     base_sequence: bytes | str,
-    force_recompute: bool = False,
     **kwargs,
 ) -> ScoreSingleSiteJob:
     """
@@ -541,8 +520,6 @@ def request_score_single_site_post(
         model ID to request results from
     sequences : List[bytes]
         sequences to request results for
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs:
         Optional parameters for models, e.g. prompt_id for PoET
 
@@ -569,8 +546,7 @@ def request_score_single_site_post(
             ]
     if kwargs.get("decoder_type"):
         body["decoder_type"] = kwargs["decoder_type"]
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return ScoreSingleSiteJob.model_validate(response.json())
 
 
@@ -583,7 +559,6 @@ def request_generate_post(
     topp: float | None = None,
     max_length: int = 1000,
     random_seed: int | None = None,
-    force_recompute: bool = False,
     **kwargs,
 ) -> GenerateJob:
     """
@@ -597,8 +572,6 @@ def request_generate_post(
         Session object for API communication.
     model_id : str
         model ID to request results from
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs:
         Optional parameters for models, e.g. prompt_id for PoET
 
@@ -638,11 +611,7 @@ def request_generate_post(
     query_id = kwargs.get("query_id")
     if query_id is not None:
         assert model_id != "poet", f"Model with id {model_id} does not support query"
-        body["query_id"] = (
-            list(query_id)
-            if isinstance(query_id, list)
-            else query_id
-        )
+        body["query_id"] = list(query_id) if isinstance(query_id, list) else query_id
         if "use_query_structure_in_decoder" in kwargs:
             body["use_query_structure_in_decoder"] = kwargs[
                 "use_query_structure_in_decoder"
@@ -657,6 +626,5 @@ def request_generate_post(
             model_id != "poet"
         ), f"Model with id {model_id} does not support ensemble_method parameter"
         body["ensemble_method"] = ensemble_method
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return GenerateJob.model_validate(response.json())

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/embeddings/poet2.py

@@ -59,19 +59,20 @@ class PoET2Model(PoETModel, EmbeddingModel):
 
     def embed(
         self,
-        sequences: list[bytes],
+        sequences: list[bytes] | list[str],
         reduction: ReductionType | None = ReductionType.MEAN,
         prompt: str | Prompt | None = None,
         query: str | bytes | Protein | Complex | Query | None = None,
         use_query_structure_in_decoder: bool = True,
         decoder_type: Literal["mlm", "clm"] | None = None,
+        **kwargs,
     ) -> EmbeddingsResultFuture:
         """
         Embed sequences using this model.
 
         Parameters
         ----------
-        sequences : list of bytes
+        sequences : list of bytes or list of str
             Sequences to embed.
         reduction : ReductionType or None, optional
             Embeddings reduction to use (e.g. mean). Default is ReductionType.MEAN.
@@ -83,6 +84,8 @@ class PoET2Model(PoETModel, EmbeddingModel):
             Whether to use query structure in decoder. Default is True.
         decoder_type : {'mlm', 'clm'} or None, optional
             Decoder type. Default is None.
+        **kwargs
+            Additional keyword arguments.
 
         Returns
         -------
@@ -105,22 +108,24 @@ class PoET2Model(PoETModel, EmbeddingModel):
             query_id=query_id,
             use_query_structure_in_decoder=use_query_structure_in_decoder,
             decoder_type=decoder_type,
+            **kwargs,
         )
 
     def logits(
         self,
-        sequences: list[bytes],
+        sequences: list[bytes] | list[str],
         prompt: str | Prompt | None = None,
         query: str | bytes | Protein | Complex | Query | None = None,
         use_query_structure_in_decoder: bool = True,
         decoder_type: Literal["mlm", "clm"] | None = None,
+        **kwargs,
     ) -> EmbeddingsResultFuture:
         """
         Compute logit embeddings for sequences using this model.
 
         Parameters
         ----------
-        sequences : list of bytes
+        sequences : list of bytes or list of str
             Sequences to analyze.
         prompt : str or Prompt or None, optional
             Prompt or prompt_id or prompt from an align workflow to condition PoET model.
@@ -130,6 +135,8 @@ class PoET2Model(PoETModel, EmbeddingModel):
             Whether to use query structure in decoder. Default is True.
         decoder_type : {'mlm', 'clm'} or None, optional
             Decoder type. Default is None.
+        **kwargs
+            Additional keyword arguments.
 
         Returns
         -------
@@ -151,6 +158,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
             query_id=query_id,
             use_query_structure_in_decoder=use_query_structure_in_decoder,
             decoder_type=decoder_type,
+            **kwargs,
         )
 
     def score(
@@ -160,6 +168,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
         query: str | bytes | Protein | Complex | Query | None = None,
         use_query_structure_in_decoder: bool = True,
         decoder_type: Literal["mlm", "clm"] | None = None,
+        **kwargs,
     ) -> EmbeddingsScoreFuture:
         """
         Score query sequences using the specified prompt.
@@ -176,6 +185,8 @@ class PoET2Model(PoETModel, EmbeddingModel):
             Whether to use query structure in decoder. Default is True.
         decoder_type : {'mlm', 'clm'} or None, optional
             Decoder type. Default is None.
+        **kwargs
+            Additional keyword arguments.
 
         Returns
         -------
@@ -191,6 +202,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
             query_id=query_id,
             use_query_structure_in_decoder=use_query_structure_in_decoder,
             decoder_type=decoder_type,
+            **kwargs,
         )
 
     def indel(
@@ -247,6 +259,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
             decoder_type=decoder_type,
             insert=insert,
             delete=delete,
+            **kwargs,
         )
 
     def single_site(
@@ -256,6 +269,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
         query: str | bytes | Protein | Complex | Query | None = None,
         use_query_structure_in_decoder: bool = True,
         decoder_type: Literal["mlm", "clm"] | None = None,
+        **kwargs,
     ) -> EmbeddingsScoreSingleSiteFuture:
         """
         Score all single substitutions of the query sequence using the specified prompt.
@@ -272,6 +286,8 @@ class PoET2Model(PoETModel, EmbeddingModel):
             Whether to use query structure in decoder. Default is True.
         decoder_type : {'mlm', 'clm'} or None, optional
             Decoder type. Default is None.
+        **kwargs
+            Additional keyword arguments.
 
         Returns
         -------
@@ -287,6 +303,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
             query_id=query_id,
             use_query_structure_in_decoder=use_query_structure_in_decoder,
             decoder_type=decoder_type,
+            **kwargs,
         )
 
     def generate(
@@ -311,6 +328,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
         seed: int | None = None,
         ensemble_weights: Sequence[float] | None = None,
         ensemble_method: Literal["arithmetic", "geometric"] | None = None,
+        **kwargs,
     ) -> EmbeddingsGenerateFuture:
         """
         Generate protein sequences conditioned on a prompt.
@@ -345,6 +363,8 @@ class PoET2Model(PoETModel, EmbeddingModel):
             If "arithmetic", the weighted mean is used; if "geometric", the weighted
             geometric mean is used. If None (default), the method defaults to
             "arithmetic", but this behavior may change in the future.
+        **kwargs
+            Additional keyword arguments.
 
         Returns
         -------
@@ -384,6 +404,7 @@ class PoET2Model(PoETModel, EmbeddingModel):
             use_query_structure_in_decoder=use_query_structure_in_decoder,
             ensemble_weights=ensemble_weights,
             ensemble_method=ensemble_method,
+            **kwargs,
         )
 
     def fit_svd(

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/fold/api.py

@@ -211,15 +211,18 @@ def fold_get_extra_result(
 
         def formatter(response):
             return np.load(io.BytesIO(response.content))
+
     elif key in {"confidence", "affinity"}:
 
         def formatter(response):
             return response.json()
+
     elif key in {"score", "metrics"}:
         import pandas as pd
 
         def formatter(response):
             return pd.read_csv(io.StringIO(response.content.decode()))
+
     else:
         raise ValueError(f"Unexpected key: {key}")
     endpoint = PATH_PREFIX + f"/{job_id}/{sequence_or_index}/{key}"
@@ -295,10 +298,12 @@ def fold_get_batch_extra_result(
 
         def formatter(response):
             return np.load(io.BytesIO(response.content))
+
     elif key in {"confidence", "affinity"}:
 
         def formatter(response):
             return response.json()
+
     else:
         raise ValueError(f"Unexpected key: {key}")
     endpoint = PATH_PREFIX + f"/{job_id}/results/{key}"
@@ -315,7 +320,6 @@ def fold_models_post(
     session: APISession,
     model_id: str,
     sequences: Sequence[Sequence[Mapping[str, Any]]],
-    force_recompute: bool = False,
     **kwargs,
 ) -> FoldJob:
     """
@@ -335,8 +339,6 @@ def fold_models_post(
         The outer list represents the batch of requests, and the inner
         list represents the complex, with each item in the list being
         an entity in that complex. A monomer would thus be a single item.
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     **kwargs
         Additional keyword arguments to be sent with POST body.
 
@@ -355,6 +357,5 @@ def fold_models_post(
         if v is not None:
             body[k] = v
 
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     return FoldJob.model_validate(response.json())

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/prompt/api.py

@@ -426,7 +426,12 @@ def create_query(
                 "chemical/x-mmcif",
             )
         else:
-            qf, filename, typ = query.make_fasta_bytes(), "query.fasta", "text/x-fasta"
+            name = query.name or "query"
+            qf, filename, typ = (
+                b">" + name.encode() + b"\n" + query.sequence + b"\n",
+                "query.fasta",
+                "text/x-fasta",
+            )
     elif isinstance(query, Complex):
         _assert_protein_only(query)
         has_structure = any(p.has_structure for p in query.get_proteins().values())

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/svd/api.py

@@ -127,7 +127,6 @@ def svd_fit_post(
     assay_id: str | None = None,
     n_components: int = 1024,
     reduction: str | None = None,
-    force_recompute: bool = False,
     **kwargs,
 ) -> SVDFitJob:
     """
@@ -151,8 +150,6 @@ def svd_fit_post(
         Type of embedding reduction to use for computing features.
         E.g. "MEAN" or "SUM". Useful when dealing with variable length
         sequence. Defaults to None.
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     kwargs:
         Additional keyword arguments to be passed to foundational models, e.g. prompt_id for PoET models.
 
@@ -183,8 +180,7 @@ def svd_fit_post(
     # add kwargs for embeddings kwargs
     body.update(**kwargs)
 
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     # return job for metadata
     return SVDFitJob.model_validate(response.json())
 
@@ -193,7 +189,7 @@ def svd_embed_post(
     session: APISession,
     svd_id: str,
     sequences: list[bytes] | list[str],
-    force_recompute: bool = False,
+    **kwargs,
 ) -> SVDEmbeddingsJob:
     """
     POST a request for embeddings from the given SVD model.
@@ -206,8 +202,6 @@ def svd_embed_post(
         SVD model to use
     sequences : List[bytes]
         sequences to SVD
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
 
     Returns
     -------
@@ -219,7 +213,6 @@ def svd_embed_post(
     body = {
         "sequences": sequences_unicode,
     }
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
 
     return SVDEmbeddingsJob.model_validate(response.json())

{openprotein_python-0.14.0 → openprotein_python-0.14.2}/openprotein/umap/api.py

@@ -172,7 +172,6 @@ def umap_fit_post(
     n_neighbors: int = 15,
     min_dist: float = 0.1,
     reduction: str | None = None,
-    force_recompute: bool = False,
     **kwargs,
 ) -> UMAPFitJob:
     """
@@ -201,8 +200,6 @@ def umap_fit_post(
         Minimum distance in UMAP fitting. Defaults to 0.1.
     reduction : str | None
         Embedding reduction to use for fitting the UMAP. Defaults to None.
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
     kwargs:
         Additional keyword arguments to be passed to foundational models, e.g. prompt_id for PoET models.
 
@@ -236,8 +233,7 @@ def umap_fit_post(
     # add kwargs for embeddings kwargs
     body.update(**kwargs)
 
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
     # return job for metadata
     return UMAPFitJob.model_validate(response.json())
 
@@ -246,7 +242,7 @@ def umap_embed_post(
     session: APISession,
     umap_id: str,
     sequences: list[bytes] | list[str],
-    force_recompute: bool = False,
+    **kwargs,
 ) -> UMAPEmbeddingsJob:
     """
     POST a request for embeddings from the given UMAP model.
@@ -259,8 +255,6 @@ def umap_embed_post(
         UMAP model to use
     sequences : List[bytes]
         sequences to UMAP
-    force_recompute : bool
-        If True, send ?force=true so the backend bypasses the result cache and recomputes. Default: False.
 
     Returns
     -------
@@ -272,7 +266,6 @@ def umap_embed_post(
     body = {
         "sequences": sequences_unicode,
     }
-    params = {"force": "true"} if force_recompute else None
-    response = session.post(endpoint, json=body, params=params)
+    response = session.post(endpoint, json=body)
 
     return UMAPEmbeddingsJob.model_validate(response.json())