bc_get_pride_project

Instructions

Implementation Reference

• src/biocontext_kb/core/pride/_get_pride_project.py:9-80 (handler)

  The main tool handler for get_pride_project. Decorated with @core_mcp.tool(), it retrieves detailed information about a PRIDE mass spectrometry proteomics project via the EBI PRIDE Archive API. Accepts project_accession (required), include_files, and include_similar_projects (optional) parameters. Returns project metadata and optionally files or similar projects.

  @core_mcp.tool()
  def get_pride_project(
      project_accession: Annotated[
          str,
          Field(description="PRIDE project accession (e.g., 'PRD000001')"),
      ],
      include_files: Annotated[
          bool,
          Field(description="Include file information (limited to first 20 files)"),
      ] = False,
      include_similar_projects: Annotated[
          bool,
          Field(description="Include similar projects based on metadata (limited to 10)"),
      ] = False,
  ) -> dict:
      """Retrieve detailed information about a specific PRIDE mass spectrometry proteomics project. Returns metadata and experimental details.
  
      Returns:
          dict: Project details with accession, title, description, organisms, instruments, publications, optionally files/similar_projects or error message.
      """
      base_url = "https://www.ebi.ac.uk/pride/ws/archive/v3"
  
      try:
          # Get basic project information
          project_url = f"{base_url}/projects/{project_accession}"
          response = requests.get(project_url)
          response.raise_for_status()
  
          project_data = response.json()
  
          if not project_data:
              return {"error": f"No data found for PRIDE project {project_accession}"}
  
          result = project_data
  
          # Optionally include file information
          if include_files:
              try:
                  files_url = f"{base_url}/projects/{project_accession}/files"
                  files_response = requests.get(files_url, params={"pageSize": 20})
                  if files_response.status_code == 200:
                      files_data = files_response.json()
                      result["files"] = files_data[:20]  # Limit to first 20 files
  
                      # Get file count
                      count_url = f"{base_url}/projects/{project_accession}/files/count"
                      count_response = requests.get(count_url)
                      if count_response.status_code == 200:
                          result["total_files"] = count_response.json()
  
              except Exception:
                  result["files"] = {"error": "Could not fetch file information"}
  
          # Optionally include similar projects
          if include_similar_projects:
              try:
                  similar_url = f"{base_url}/projects/{project_accession}/similarProjects"
                  similar_response = requests.get(similar_url, params={"pageSize": 10})
                  if similar_response.status_code == 200:
                      similar_data = similar_response.json()
                      result["similar_projects"] = similar_data[:10]  # Limit to first 10
              except Exception:
                  result["similar_projects"] = {"error": "Could not fetch similar projects"}
  
          return result
  
      except requests.exceptions.HTTPError as e:
          if e.response.status_code == 404:
              return {"error": f"PRIDE project {project_accession} not found"}
          return {"error": f"HTTP error: {e}"}
      except Exception as e:
          return {"error": f"Exception occurred: {e!s}"}

• src/biocontext_kb/core/pride/_get_pride_project.py:10-23 (schema)

  Tool function signature with Pydantic Field descriptions defining the input schema: project_accession (str), include_files (bool, default False), include_similar_projects (bool, default False).

  def get_pride_project(
      project_accession: Annotated[
          str,
          Field(description="PRIDE project accession (e.g., 'PRD000001')"),
      ],
      include_files: Annotated[
          bool,
          Field(description="Include file information (limited to first 20 files)"),
      ] = False,
      include_similar_projects: Annotated[
          bool,
          Field(description="Include similar projects based on metadata (limited to 10)"),
      ] = False,
  ) -> dict:

• src/biocontext_kb/core/pride/_get_pride_project.py:9-10 (registration)

  Tool registration via the @core_mcp.tool() decorator on the get_pride_project function. core_mcp is a FastMCP instance defined in src/biocontext_kb/core/_server.py.

  @core_mcp.tool()
  def get_pride_project(

• src/biocontext_kb/core/pride/__init__.py:1-7 (registration)

  The pride package's __init__.py re-exports get_pride_project from the implementation module, making it accessible via from .pride import * in the core __init__.py.

  from ._get_pride_project import get_pride_project
  from ._search_pride_projects import search_pride_projects
  from ._search_pride_proteins import search_pride_proteins
  
  __all__ = [
      "get_pride_project",
      "search_pride_projects",

• src/biocontext_kb/core/_server.py:1-6 (helper)

  The core_mcp FastMCP server instance that provides the .tool() decorator used to register get_pride_project as an MCP tool.

  from fastmcp import FastMCP
  
  core_mcp = FastMCP(  # type: ignore
      "BC",
      instructions="Provides access to biomedical knowledge bases.",
  )