marker_gene_overlap

Instructions

Implementation Reference

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

  Handler function that executes the marker_gene_overlap tool (and other tl tools) by retrieving the corresponding scanpy function from tl_func mapping and calling it on the active AnnData object with validated arguments.

  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:752-821 (schema)

  Pydantic model defining the input schema and validators for the marker_gene_overlap tool parameters.

  class MarkerGeneOverlapModel(JSONParsingModel):
      """Input schema for the marker gene overlap tool."""
      
      key: str = Field(
          default='rank_genes_groups',
          description="The key in adata.uns where the rank_genes_groups output is stored."
      )
      
      method: str = Field(
          default='overlap_count',
          description="Method to calculate marker gene overlap: 'overlap_count', 'overlap_coef', or 'jaccard'."
      )
      
      normalize: Optional[Literal['reference', 'data']] = Field(
          default=None,
          description="Normalization option for the marker gene overlap output. Only applicable when method is 'overlap_count'."
      )
      
      top_n_markers: Optional[int] = Field(
          default=None,
          description="The number of top data-derived marker genes to use. By default the top 100 marker genes are used.",
          gt=0
      )
      
      adj_pval_threshold: Optional[float] = Field(
          default=None,
          description="A significance threshold on the adjusted p-values to select marker genes.",
          gt=0,
          le=1.0
      )
      
      key_added: str = Field(
          default='marker_gene_overlap',
          description="Name of the .uns field that will contain the marker overlap scores."
      )
      
      @field_validator('method')
      def validate_method(cls, v: str) -> str:
          """Validate method is supported"""
          valid_methods = ['overlap_count', 'overlap_coef', 'jaccard']
          if v not in valid_methods:
              raise ValueError(f"method must be one of {valid_methods}")
          return v
      
      @field_validator('normalize')
      def validate_normalize(cls, v: Optional[str], info: ValidationInfo) -> Optional[str]:
          """Validate normalize is only used with overlap_count method"""
          if v is not None:
              if v not in ['reference', 'data']:
                  raise ValueError("normalize must be either 'reference' or 'data'")
              
              values = info.data
              if 'method' in values and values['method'] != 'overlap_count':
                  raise ValueError("normalize can only be used when method is 'overlap_count'")
          return v
      
      @field_validator('top_n_markers')
      def validate_top_n_markers(cls, v: Optional[int]) -> Optional[int]:
          """Validate top_n_markers is positive"""
          if v is not None and v <= 0:
              raise ValueError("top_n_markers must be a positive integer")
          return v
      
      @field_validator('adj_pval_threshold')
      def validate_adj_pval_threshold(cls, v: Optional[float]) -> Optional[float]:
          """Validate adj_pval_threshold is between 0 and 1"""
          if v is not None and (v <= 0 or v > 1):
              raise ValueError("adj_pval_threshold must be between 0 and 1")
          return v

• src/scmcp/tool/tl.py:103-108 (registration)

  Registers the marker_gene_overlap tool as an MCP Tool object with name, description, and input schema from MarkerGeneOverlapModel.

  # 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(),
  )

• src/scmcp/tool/tl.py:124-142 (registration)

  Maps the tool name 'marker_gene_overlap' to the underlying scanpy.tl.marker_gene_overlap function for execution.

  # 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,
  }

• src/scmcp/tool/tl.py:144-162 (registration)

  Adds the marker_gene_overlap_tool to the dictionary of tl tools, which is used by the server for listing and dispatching.

  # 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,
      "leiden": leiden_tool,
      "louvain": louvain_tool,
      "dendrogram": dendrogram_tool,
      "dpt": dpt_tool,
      "paga": paga_tool,
      "ingest": ingest_tool,
      "rank_genes_groups": rank_genes_groups_tool,
      "filter_rank_genes_groups": filter_rank_genes_groups_tool,
      "marker_gene_overlap": marker_gene_overlap_tool,
      "score_genes": score_genes_tool,
      "score_genes_cell_cycle": score_genes_cell_cycle_tool,
  }