scmcp-shared 0.1.0__tar.gz → 0.2.0__tar.gz

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scmcp_shared
-Version: 0.1.0
+Version: 0.2.0
 Summary: A shared function libray for scmcphub
 Author-email: shuang <hsh-me@outlook.com>
 License: BSD 3-Clause License
@@ -33,7 +33,7 @@ License: BSD 3-Clause License
         OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 License-File: LICENSE
 Requires-Python: >=3.10
-Requires-Dist: fastmcp>=2.3.0
+Requires-Dist: fastmcp>=2.3.4
 Requires-Dist: mcp>=1.8.0
 Requires-Dist: pydantic
 Requires-Dist: scanpy

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/pyproject.toml

@@ -11,7 +11,7 @@ requires-python = ">=3.10"
 dependencies = [
     "scanpy",
     "mcp>=1.8.0",
-    "fastmcp>=2.3.0",
+    "fastmcp>=2.3.4",
     "pydantic",
 ]
 

scmcp_shared-0.2.0/src/scmcp_shared/__init__.py

@@ -0,0 +1,3 @@
+
+__version__ = "0.2.0"
+

scmcp_shared-0.2.0/src/scmcp_shared/schema/__init__.py

@@ -0,0 +1 @@
+from .base import AdataModel

scmcp_shared-0.2.0/src/scmcp_shared/schema/base.py

@@ -0,0 +1,11 @@
+from pydantic import Field, BaseModel,ConfigDict
+
+
+class AdataModel(BaseModel):
+    """Input schema for the adata tool."""
+    sampleid: str = Field(default=None, description="adata sampleid")
+    adtype: str = Field(default="exp", description="adata.X data type")
+
+    model_config = ConfigDict(
+        extra="ignore"
+    )

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/src/scmcp_shared/schema/io.py

@@ -1,16 +1,13 @@
 from pydantic import (
     Field,
-    ValidationInfo,
-    computed_field,
     field_validator,
     model_validator,
-    BaseModel
 )
-from typing import Optional, Union, Literal, Any, Sequence, Dict
+from typing import Optional, Literal
+from .base import AdataModel
 
 
-
-class ReadModel(BaseModel):
+class ReadModel(AdataModel):
     """Input schema for the read tool."""
     filename: str = Field(
         ...,
@@ -89,7 +86,7 @@ class ReadModel(BaseModel):
         return v
 
 
-class WriteModel(BaseModel):
+class WriteModel(AdataModel):
     """Input schema for the write tool."""
     filename: str = Field(
         description="Path to save the file. If no extension is provided, the default format will be used."
@@ -113,7 +110,7 @@ class WriteModel(BaseModel):
         return v
     
     @model_validator(mode='after')
-    def validate_extension_compression(self) -> 'WriteInput':
+    def validate_extension_compression(self) -> 'WriteModel':
         # If ext is provided and not h5, compression should be None
         if self.ext is not None and self.ext != 'h5' and self.compression is not None:
             raise ValueError("Compression can only be used with h5 files")

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/src/scmcp_shared/schema/pl.py

@@ -7,7 +7,7 @@ from pydantic import (
     model_validator,
     BaseModel
 )
-
+from .base import AdataModel
 
 # 创建 Mixin 类处理特定功能
 class LegendMixin:
@@ -73,7 +73,7 @@ class FigureSizeMixin:
 
 
 # 基础可视化模型，包含所有可视化工具共享的字段
-class BaseVisualizationModel(BaseModel, LegendMixin, ColorMappingMixin, FigureSizeMixin):
+class BaseVisualizationModel(AdataModel, LegendMixin, ColorMappingMixin, FigureSizeMixin):
     """基础可视化模型，包含所有可视化工具共享的字段"""    
     pass
 
@@ -632,7 +632,7 @@ class RankGenesGroupsModel(BaseVisualizationModel):
 
 
 # 重构 ClusterMapModel
-class ClusterMapModel(BaseModel):
+class ClusterMapModel(AdataModel):
     """Input schema for the clustermap plotting tool."""
 
     obs_keys: Optional[str] = Field(

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/src/scmcp_shared/schema/pp.py

@@ -4,14 +4,14 @@ from pydantic import (
     computed_field,
     field_validator,
     model_validator,
-    BaseModel
 )
+from .base import AdataModel
 from typing import Optional, Union, List, Dict, Any
 from typing import Literal
 import numpy as np
 
 
-class FilterCells(BaseModel):
+class FilterCells(AdataModel):
     """Input schema for the filter_cells preprocessing tool."""
     
     min_counts: Optional[int] = Field(
@@ -42,7 +42,7 @@ class FilterCells(BaseModel):
         return v
 
 
-class FilterGenes(BaseModel):
+class FilterGenes(AdataModel):
     """Input schema for the filter_genes preprocessing tool."""
     
     min_counts: Optional[int] = Field(
@@ -73,7 +73,7 @@ class FilterGenes(BaseModel):
         return v
 
 
-class SubsetCellModel(BaseModel):
+class SubsetCellModel(AdataModel):
     """Input schema for subsetting AnnData objects based on various criteria."""
     obs_key: Optional[str] = Field(
         default=None,
@@ -109,7 +109,7 @@ class SubsetCellModel(BaseModel):
     )
 
 
-class SubsetGeneModel(BaseModel):
+class SubsetGeneModel(AdataModel):
     """Input schema for subsetting AnnData objects based on various criteria."""
     min_counts: Optional[int] = Field(
         default=None,
@@ -145,7 +145,7 @@ class SubsetGeneModel(BaseModel):
     )
 
 
-class CalculateQCMetrics(BaseModel):
+class CalculateQCMetrics(AdataModel):
     """Input schema for the calculate_qc_metrics preprocessing tool."""
     
     expr_type: str = Field(
@@ -196,7 +196,7 @@ class CalculateQCMetrics(BaseModel):
     
 
 
-class Log1PModel(BaseModel):
+class Log1PModel(AdataModel):
     """Input schema for the log1p preprocessing tool."""
     
     base: Optional[Union[int, float]] = Field(
@@ -232,64 +232,8 @@ class Log1PModel(BaseModel):
         return v
 
 
-class PCAModel(BaseModel):
-    """Input schema for the PCA preprocessing tool."""
-    
-    n_comps: Optional[int] = Field(
-        default=None,
-        description="Number of principal components to compute. Defaults to 50 or 1 - minimum dimension size.",
-        gt=0
-    )
-    
-    layer: Optional[str] = Field(
-        default=None,
-        description="If provided, which element of layers to use for PCA."
-    )
-    
-    zero_center: Optional[bool] = Field(
-        default=True,
-        description="If True, compute standard PCA from covariance matrix."
-    )
-    
-    svd_solver: Optional[Literal["arpack", "randomized", "auto", "lobpcg", "tsqr"]] = Field(
-        default=None,
-        description="SVD solver to use."
-    )
-    mask_var: Optional[Union[str, bool]] = Field(
-        default=None,
-        description="Boolean mask or string referring to var column for subsetting genes."
-    )
-    dtype: str = Field(
-        default="float32",
-        description="Numpy data type string for the result."
-    )
-    chunked: bool = Field(
-        default=False,
-        description="If True, perform an incremental PCA on segments."
-    )
-    
-    chunk_size: Optional[int] = Field(
-        default=None,
-        description="Number of observations to include in each chunk.",
-        gt=0
-    )
-    
-    @field_validator('n_comps', 'chunk_size')
-    def validate_positive_integers(cls, v: Optional[int]) -> Optional[int]:
-        """Validate positive integers"""
-        if v is not None and v <= 0:
-            raise ValueError("must be a positive integer")
-        return v
-    
-    @field_validator('dtype')
-    def validate_dtype(cls, v: str) -> str:
-        """Validate numpy dtype"""
-        if v not in ["float32", "float64"]:
-            raise ValueError("dtype must be either 'float32' or 'float64'")
-        return v
-
 
-class HighlyVariableGenesModel(BaseModel):
+class HighlyVariableGenesModel(AdataModel):
     """Input schema for the highly_variable_genes preprocessing tool."""
     
     layer: Optional[str] = Field(
@@ -363,7 +307,7 @@ class HighlyVariableGenesModel(BaseModel):
         return v
 
 
-class RegressOutModel(BaseModel):
+class RegressOutModel(AdataModel):
     """Input schema for the regress_out preprocessing tool."""
     
     keys: Union[str, List[str]] = Field(
@@ -396,7 +340,7 @@ class RegressOutModel(BaseModel):
         raise ValueError("keys must be a string or list of strings")
 
 
-class ScaleModel(BaseModel):
+class ScaleModel(AdataModel):
     """Input schema for the scale preprocessing tool."""
     
     zero_center: bool = Field(
@@ -432,7 +376,7 @@ class ScaleModel(BaseModel):
         return v
 
 
-class CombatModel(BaseModel):
+class CombatModel(AdataModel):
     """Input schema for the combat batch effect correction tool."""
     
     key: str = Field(
@@ -461,7 +405,7 @@ class CombatModel(BaseModel):
         return v
 
 
-class ScrubletModel(BaseModel):
+class ScrubletModel(AdataModel):
     """Input schema for the scrublet doublet prediction tool."""
     
     adata_sim: Optional[str] = Field(
@@ -567,7 +511,7 @@ class ScrubletModel(BaseModel):
         return v.lower()
 
 
-class NeighborsModel(BaseModel):
+class NeighborsModel(AdataModel):
     """Input schema for the neighbors graph construction tool."""
     
     n_neighbors: int = Field(
@@ -645,7 +589,7 @@ class NeighborsModel(BaseModel):
         return v
 
 
-class NormalizeTotalModel(BaseModel):
+class NormalizeTotalModel(AdataModel):
     """Input schema for the normalize_total preprocessing tool."""
     
     target_sum: Optional[float] = Field(

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/src/scmcp_shared/schema/tl.py

@@ -1,9 +1,9 @@
-from pydantic import BaseModel, Field, field_validator, ValidationInfo
+from pydantic import  Field, field_validator, ValidationInfo
 from typing import Optional, Union, List, Dict, Any, Tuple, Literal, Mapping
 
+from .base import AdataModel
 
-
-class TSNEModel(BaseModel):
+class TSNEModel(AdataModel):
     """Input schema for the t-SNE dimensionality reduction tool."""
     n_pcs: Optional[int] = Field(
         default=None,
@@ -60,7 +60,7 @@ class TSNEModel(BaseModel):
         return v.lower()
 
 
-class UMAPModel(BaseModel):
+class UMAPModel(AdataModel):
     """Input schema for the UMAP dimensionality reduction tool."""
     
     min_dist: Optional[float] = Field(
@@ -146,7 +146,7 @@ class UMAPModel(BaseModel):
         return v.lower()
 
 
-class DrawGraphModel(BaseModel):
+class DrawGraphModel(AdataModel):
     """Input schema for the force-directed graph drawing tool."""
     
     layout: str = Field(
@@ -200,7 +200,7 @@ class DrawGraphModel(BaseModel):
         return v
 
 
-class DiffMapModel(BaseModel):
+class DiffMapModel(AdataModel):
     """Input schema for the Diffusion Maps dimensionality reduction tool."""
     
     n_comps: int = Field(
@@ -230,7 +230,7 @@ class DiffMapModel(BaseModel):
         return v
 
 
-class EmbeddingDensityModel(BaseModel):
+class EmbeddingDensityModel(AdataModel):
     """Input schema for the embedding density calculation tool."""
     
     basis: str = Field(
@@ -258,7 +258,7 @@ class EmbeddingDensityModel(BaseModel):
         return v
 
 
-class LeidenModel(BaseModel):
+class LeidenModel(AdataModel):
     """Input schema for the Leiden clustering algorithm."""
     
     resolution: Optional[float] = Field(
@@ -330,7 +330,7 @@ class LeidenModel(BaseModel):
         return v
 
 
-class LouvainModel(BaseModel):
+class LouvainModel(AdataModel):
     """Input schema for the Louvain clustering algorithm."""
     
     resolution: Optional[float] = Field(
@@ -402,7 +402,7 @@ class LouvainModel(BaseModel):
         return v
 
 
-class DendrogramModel(BaseModel):
+class DendrogramModel(AdataModel):
     """Input schema for the hierarchical clustering dendrogram tool."""
     
     groupby: str = Field(
@@ -467,7 +467,7 @@ class DendrogramModel(BaseModel):
         return v
 
 
-class DPTModel(BaseModel):
+class DPTModel(AdataModel):
     """Input schema for the Diffusion Pseudotime (DPT) tool."""
     
     n_dcs: int = Field(
@@ -516,7 +516,7 @@ class DPTModel(BaseModel):
             raise ValueError("min_group_size must be between 0 and 1")
         return v
 
-class PAGAModel(BaseModel):
+class PAGAModel(AdataModel):
     """Input schema for the Partition-based Graph Abstraction (PAGA) tool."""
     
     groups: Optional[str] = Field(
@@ -544,7 +544,7 @@ class PAGAModel(BaseModel):
         return v
 
 
-class IngestModel(BaseModel):
+class IngestModel(AdataModel):
     """Input schema for the ingest tool that maps labels and embeddings from reference data to new data."""
     
     obs: Optional[Union[str, List[str]]] = Field(
@@ -593,7 +593,7 @@ class IngestModel(BaseModel):
         return v.lower()
 
 
-class RankGenesGroupsModel(BaseModel):
+class RankGenesGroupsModel(AdataModel):
     """Input schema for the rank_genes_groups tool."""
     
     groupby: str = Field(
@@ -675,7 +675,7 @@ class RankGenesGroupsModel(BaseModel):
         return v
 
 
-class FilterRankGenesGroupsModel(BaseModel):
+class FilterRankGenesGroupsModel(AdataModel):
     """Input schema for filtering ranked genes groups."""
     
     key: Optional[str] = Field(
@@ -738,7 +738,7 @@ class FilterRankGenesGroupsModel(BaseModel):
         return v
 
 
-class MarkerGeneOverlapModel(BaseModel):
+class MarkerGeneOverlapModel(AdataModel):
     """Input schema for the marker gene overlap tool."""
     
     key: str = Field(
@@ -809,7 +809,7 @@ class MarkerGeneOverlapModel(BaseModel):
         return v
 
 
-class ScoreGenesModel(BaseModel):
+class ScoreGenesModel(AdataModel):
     """Input schema for the score_genes tool that calculates gene scores based on average expression."""
     
     ctrl_size: int = Field(
@@ -852,7 +852,7 @@ class ScoreGenesModel(BaseModel):
         return v
 
 
-class ScoreGenesCellCycleModel(BaseModel):
+class ScoreGenesCellCycleModel(AdataModel):
     """Input schema for the score_genes_cell_cycle tool that scores cell cycle genes."""
     
     s_genes: List[str] = Field(
@@ -900,3 +900,54 @@ class ScoreGenesCellCycleModel(BaseModel):
         return v
 
 
+
+
+class PCAModel(AdataModel):
+    """Input schema for the PCA preprocessing tool."""
+    
+    n_comps: Optional[int] = Field(
+        default=None,
+        description="Number of principal components to compute. Defaults to 50 or 1 - minimum dimension size.",
+        gt=0
+    )
+    
+    layer: Optional[str] = Field(
+        default=None,
+        description="If provided, which element of layers to use for PCA."
+    )
+    
+    zero_center: Optional[bool] = Field(
+        default=True,
+        description="If True, compute standard PCA from covariance matrix."
+    )
+    
+    svd_solver: Optional[Literal["arpack", "randomized", "auto", "lobpcg", "tsqr"]] = Field(
+        default=None,
+        description="SVD solver to use."
+    )
+    mask_var: Optional[Union[str, bool]] = Field(
+        default=None,
+        description="Boolean mask or string referring to var column for subsetting genes."
+    )
+    # dtype: str = Field(
+    #     default="float32",
+    #     description="Numpy data type string for the result."
+    # )
+    chunked: bool = Field(
+        default=False,
+        description="If True, perform an incremental PCA on segments."
+    )
+    
+    chunk_size: Optional[int] = Field(
+        default=None,
+        description="Number of observations to include in each chunk.",
+        gt=0
+    )
+    
+    @field_validator('n_comps', 'chunk_size')
+    def validate_positive_integers(cls, v: Optional[int]) -> Optional[int]:
+        """Validate positive integers"""
+        if v is not None and v <= 0:
+            raise ValueError("must be a positive integer")
+        return v
+    

{scmcp_shared-0.1.0 → scmcp_shared-0.2.0}/src/scmcp_shared/schema/util.py

@@ -1,6 +1,5 @@
 
 from pydantic import (
-    BaseModel,
     Field,
     ValidationInfo,
     computed_field,
@@ -8,10 +7,10 @@ from pydantic import (
     model_validator,
 )
 from typing import Optional, Union, List, Dict, Any, Callable, Collection, Literal
+from .base import AdataModel
 
 
-
-class MarkVarModel(BaseModel):
+class MarkVarModel(AdataModel):
     """Determine or mark if each gene meets specific conditions and store results in adata.var as boolean values"""
     
     var_name: str = Field(
@@ -33,15 +32,15 @@ class MarkVarModel(BaseModel):
     )
 
 
-class ListVarModel(BaseModel):
+class ListVarModel(AdataModel):
     """ListVarModel"""    
     pass
 
-class ListObsModel(BaseModel):
+class ListObsModel(AdataModel):
     """ListObsModel"""    
     pass    
 
-class VarNamesModel(BaseModel):
+class VarNamesModel(AdataModel):
     """ListObsModel"""    
     var_names: List[str] = Field(
             default=None,
@@ -49,7 +48,7 @@ class VarNamesModel(BaseModel):
         )
 
 
-class ConcatAdataModel(BaseModel):
+class ConcatAdataModel(AdataModel):
     """Model for concatenating AnnData objects"""
     
     axis: Literal['obs', 0, 'var', 1] = Field(
@@ -90,7 +89,7 @@ class ConcatAdataModel(BaseModel):
     )
 
 
-class DPTIROOTModel(BaseModel):
+class DPTIROOTModel(AdataModel):
     """Input schema for setting the root cell for diffusion pseudotime."""
     diffmap_key: str = Field(
         default="X_diffmap",
@@ -104,7 +103,7 @@ class DPTIROOTModel(BaseModel):
     )
 
 
-class CelltypeMapCellTypeModel(BaseModel):
+class CelltypeMapCellTypeModel(AdataModel):
     """Input schema for mapping cluster IDs to cell type names."""
     cluster_key: str = Field(
         description="Key in adata.obs containing cluster IDs."
@@ -123,9 +122,17 @@ class CelltypeMapCellTypeModel(BaseModel):
     
 
 
-class AddLayerModel(BaseModel):
+class AddLayerModel(AdataModel):
     """Input schema for adding a layer to AnnData object."""
     layer_name: str = Field(
         description="Name of the layer to add to adata.layers."
     )
- 
+ 
+
+class QueryOpLogModel(AdataModel):
+    """QueryOpLogModel"""    
+    n: int = Field(
+        default=10,
+        description="Number of operations to return."
+    )
+    

scmcp_shared-0.2.0/src/scmcp_shared/server/__init__.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+from collections.abc import Iterable
+from typing import Any
+
+from .io import io_mcp
+from .util import ul_mcp
+from .pl import pl_mcp
+from .pp import pp_mcp
+from .tl import tl_mcp
+
+
+
+class AdataState:
+    def __init__(self, add_adtypes=None):
+        self.adata_dic = {"exp": {}, "activity": {}, "cnv": {}, "splicing": {}}
+        if isinstance(add_adtypes, str):
+            self.adata_dic[add_adtypes] = {}
+        elif isinstance(add_adtypes, Iterable):
+            self.adata_dic.update({adtype: {} for adtype in add_adtypes})
+        self.active_id = None
+        self.metadatWa = {}
+        self.cr_kernel = {}
+        self.cr_estimator = {}
+        
+    def get_adata(self, sampleid=None, adtype="exp", request=None):
+        if request is not None:
+            kwargs = request.model_dump()
+            sampleid = kwargs.get("sampleid", None)
+            adtype = kwargs.get("adtype", "exp")
+        try:
+            if self.active_id is None:
+                return None
+            sampleid = sampleid or self.active_id
+            return self.adata_dic[adtype][sampleid]
+        except KeyError as e:
+            raise KeyError(f"Key {e} not found in adata_dic[{adtype}].Please check the sampleid or adtype.")
+        except Exception as e:
+            raise Exception(f"fuck {e} {type(e)}")
+    
+    def set_adata(self, adata, sampleid=None, sdtype="exp", request=None):
+        if request is not None:
+            kwargs = request.model_dump()
+            sampleid = kwargs.get("sampleid", None)
+            sdtype = kwargs.get("adtype", "exp")
+        sampleid = sampleid or self.active_id
+        if sdtype not in self.adata_dic:
+            self.adata_dic[sdtype] = {}
+        self.adata_dic[sdtype][sampleid] = adata
+                          
+