SCMCP

Instructions

Implementation Reference

• src/scmcp/tool/tl.py:164-177 (handler)

  Generic handler function for tl tools, including embedding_density, that dispatches to sc.tl.embedding_density with inspected parameters and logs the operation.
  def run_tl_func(ads, func, arguments): adata = ads.adata_dic[ads.active] if func not in tl_func: raise ValueError(f"Unsupported function: {func}") run_func = tl_func[func] parameters = inspect.signature(run_func).parameters kwargs = {k: arguments.get(k) for k in parameters if k in arguments} try: res = run_func(adata, **kwargs) add_op_log(adata, run_func, kwargs) except Exception as e: logger.error(f"Error running function {func}: {e}") raise return
• src/scmcp/schema/tl.py:239-265 (schema)

  Pydantic input schema model for the embedding_density computation tool (sc.tl.embedding_density).
  class EmbeddingDensityModel(JSONParsingModel): """Input schema for the embedding density calculation tool.""" basis: str = Field( default='umap', description="The embedding over which the density will be calculated. This embedded representation should be found in `adata.obsm['X_[basis]']`." ) groupby: Optional[str] = Field( default=None, description="Key for categorical observation/cell annotation for which densities are calculated per category." ) key_added: Optional[str] = Field( default=None, description="Name of the `.obs` covariate that will be added with the density estimates." ) components: Optional[Union[str, List[str]]] = Field( default=None, description="The embedding dimensions over which the density should be calculated. This is limited to two components." ) @field_validator('components') def validate_components(cls, v: Optional[Union[str, List[str]]]) -> Optional[Union[str, List[str]]]: """Validate that components are limited to two dimensions""" if v is not None and isinstance(v, list) and len(v) > 2: raise ValueError("components is limited to two dimensions") return v
• src/scmcp/tool/tl.py:40-150 (registration)

  Registration of the embedding_density tool for computation (tl), including tool object creation, function mapping in tl_func, and inclusion in tl_tools dictionary.
  # Add embedding_density tool embedding_density_tool = types.Tool( name="embedding_density", description="Calculate the density of cells in an embedding", inputSchema=EmbeddingDensityModel.model_json_schema(), ) # Add leiden tool leiden_tool = types.Tool( name="leiden", description="Leiden clustering algorithm for community detection", inputSchema=LeidenModel.model_json_schema(), ) # Add louvain tool louvain_tool = types.Tool( name="louvain", description="Louvain clustering algorithm for community detection", inputSchema=LouvainModel.model_json_schema(), ) # Add dendrogram tool dendrogram_tool = types.Tool( name="dendrogram", description="Hierarchical clustering dendrogram", inputSchema=DendrogramModel.model_json_schema(), ) # Add dpt tool dpt_tool = types.Tool( name="dpt", description="Diffusion Pseudotime (DPT) analysis", inputSchema=DPTModel.model_json_schema(), ) # Add paga tool paga_tool = types.Tool( name="paga", description="Partition-based graph abstraction", inputSchema=PAGAModel.model_json_schema(), ) # Add ingest tool ingest_tool = types.Tool( name="ingest", description="Map labels and embeddings from reference data to new data", inputSchema=IngestModel.model_json_schema(), ) # Add rank_genes_groups tool rank_genes_groups_tool = types.Tool( name="rank_genes_groups", description="Rank genes for characterizing groups, perform differentially expressison analysis", inputSchema=RankGenesGroupsModel.model_json_schema(), ) # Add filter_rank_genes_groups tool filter_rank_genes_groups_tool = types.Tool( name="filter_rank_genes_groups", description="Filter out genes based on fold change and fraction of genes", inputSchema=FilterRankGenesGroupsModel.model_json_schema(), ) # Add marker_gene_overlap tool marker_gene_overlap_tool = types.Tool( name="marker_gene_overlap", description="Calculate overlap between data-derived marker genes and reference markers", inputSchema=MarkerGeneOverlapModel.model_json_schema(), ) # Add score_genes tool score_genes_tool = types.Tool( name="score_genes", description="Score a set of genes based on their average expression", inputSchema=ScoreGenesModel.model_json_schema(), ) # Add score_genes_cell_cycle tool score_genes_cell_cycle_tool = types.Tool( name="score_genes_cell_cycle", description="Score cell cycle genes and assign cell cycle phases", inputSchema=ScoreGenesCellCycleModel.model_json_schema(), ) # Dictionary mapping tool names to scanpy functions tl_func = { "tsne": sc.tl.tsne, "umap": sc.tl.umap, "draw_graph": sc.tl.draw_graph, "diffmap": sc.tl.diffmap, "embedding_density": sc.tl.embedding_density, "leiden": sc.tl.leiden, "louvain": sc.tl.louvain, "dendrogram": sc.tl.dendrogram, "dpt": sc.tl.dpt, "paga": sc.tl.paga, "ingest": sc.tl.ingest, "rank_genes_groups": sc.tl.rank_genes_groups, "filter_rank_genes_groups": sc.tl.filter_rank_genes_groups, "marker_gene_overlap": sc.tl.marker_gene_overlap, "score_genes": sc.tl.score_genes, "score_genes_cell_cycle": sc.tl.score_genes_cell_cycle, } # Dictionary mapping tool names to tool objects tl_tools = { "tsne": tsne_tool, "umap": umap_tool, "draw_graph": draw_graph_tool, "diffmap": diffmap_tool, "embedding_density": embedding_density_tool,
• src/scmcp/tool/pl.py:179-216 (handler)

  Generic handler function for pl tools, including embedding_density plot, that calls sc.pl.embedding_density, saves figure, and logs.
  def run_pl_func(ads, func, arguments): """ Execute a Scanpy plotting function with the given arguments. Parameters ---------- adata : AnnData Annotated data matrix. func : str Name of the plotting function to execute. arguments : dict Arguments to pass to the plotting function. Returns ------- The result of the plotting function. """ adata = ads.adata_dic[ads.active] if func not in pl_func: raise ValueError(f"Unsupported function: {func}") run_func = pl_func[func] parameters = inspect.signature(run_func).parameters kwargs = {k: arguments.get(k) for k in parameters if k in arguments} if "title" not in parameters: kwargs.pop("title", False) kwargs.pop("return_fig", True) kwargs["show"] = False kwargs["save"] = ".png" try: fig = run_func(adata, **kwargs) fig_path = set_fig_path(func, **kwargs) add_op_log(adata, run_func, kwargs) return fig_path except Exception as e: raise e return fig_path
• src/scmcp/schema/pl.py:718-749 (schema)

  Pydantic input schema model for the embedding_density plotting tool (sc.pl.embedding_density), extending BaseEmbeddingModel.
  class EmbeddingDensityModel(BaseEmbeddingModel): """Input schema for the embedding_density plotting tool.""" basis: str = Field( ..., # Required field description="Basis to use for embedding." ) key: Optional[str] = Field( default=None, description="Key for annotation of observations/cells or variables/genes." ) convolve: Optional[float] = Field( default=None, description="Sigma for Gaussian kernel used for convolution." ) alpha: float = Field( default=0.5, description="Alpha value for the plot.", ge=0, le=1 ) @field_validator('alpha') def validate_alpha(cls, v: float) -> float: """Validate alpha is between 0 and 1""" if v < 0 or v > 1: raise ValueError("alpha must be between 0 and 1") return v