bc_search_pride_proteins
Find proteins in specific PRIDE mass spectrometry projects using project accession and optional keywords. Retrieve and sort results for targeted proteomics research.
Instructions
Search proteins identified in a specific PRIDE project.
This function searches for proteins identified in a specific PRIDE mass spectrometry project. Useful for finding specific proteins of interest in proteomics datasets.
Args: project_accession (str): The PRIDE project accession to search in. keyword (str, optional): Search keyword for protein names or accessions. page_size (int, optional): Number of results (max 100). Defaults to 20. sort_field (str, optional): Sort field. Defaults to "accession". sort_direction (str, optional): Sort direction. Defaults to "ASC".
Returns: dict: Search results with proteins found in the specified project
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| keyword | No | Search keyword for protein names or accessions | |
| page_size | No | Number of results to return (max 100) | |
| project_accession | Yes | The PRIDE project accession to search proteins in | |
| sort_direction | No | Sort direction: ASC or DESC | ASC |
| sort_field | No | Field to sort by: accession, proteinName, gene | accession |
Implementation Reference
- The handler function `search_pride_proteins` decorated with `@core_mcp.tool()`, implementing the logic to query the PRIDE API for proteins in a project, process results, handle errors, and return formatted data. Tool name becomes 'bc_search_pride_proteins' due to server prefix.@core_mcp.tool() def search_pride_proteins( project_accession: Annotated[ str, Field(description="PRIDE project accession to search proteins in"), ], keyword: Annotated[ Optional[str], Field(description="Search keyword for protein names or accessions"), ] = None, page_size: Annotated[ int, Field(description="Number of results to return (max 100)"), ] = 20, sort_field: Annotated[ str, Field(description="Sort field: accession, proteinName, or gene"), ] = "accession", sort_direction: Annotated[ str, Field(description="Sort direction: ASC or DESC"), ] = "ASC", ) -> dict: """Search for proteins identified in a specific PRIDE mass spectrometry project. Useful for finding specific proteins in proteomics datasets. Returns: dict: Proteins list with accessions, names, genes, sequences, modifications, associated projects or error message. """ base_url = "https://www.ebi.ac.uk/pride/ws/archive/v3/pride-ap/search/proteins" # Build query parameters params: dict[str, str | int] = {"projectAccession": project_accession} if page_size > 100: page_size = 100 params["pageSize"] = page_size params["page"] = 0 # Add keyword search if keyword: params["keyword"] = keyword # Validate and set sort parameters valid_sort_fields = ["accession", "proteinName", "gene"] if sort_field not in valid_sort_fields: sort_field = "accession" params["sortField"] = sort_field valid_sort_directions = ["ASC", "DESC"] if sort_direction.upper() not in valid_sort_directions: sort_direction = "ASC" params["sortDirection"] = sort_direction.upper() try: response = requests.get(base_url, params=params) response.raise_for_status() search_results = response.json() if not search_results: return {"results": [], "count": 0, "message": f"No proteins found in PRIDE project {project_accession}"} # Process results to include key information processed_results = [] for protein in search_results: processed_protein = { "protein_accession": protein.get("proteinAccession"), "protein_name": protein.get("proteinName"), "gene": protein.get("gene"), "project_count": protein.get("projectCount", 0), } processed_results.append(processed_protein) return { "results": processed_results, "count": len(processed_results), "project_accession": project_accession, "search_criteria": {"keyword": keyword, "sort_field": sort_field, "sort_direction": sort_direction}, } except requests.exceptions.HTTPError as e: if e.response.status_code == 404: return {"error": f"PRIDE project {project_accession} not found or has no protein data"} return {"error": f"HTTP error: {e}"} except Exception as e: return {"error": f"Exception occurred: {e!s}"}
- Pydantic schema defined via Annotated Field descriptions for input validation of the tool parameters.def search_pride_proteins( project_accession: Annotated[ str, Field(description="PRIDE project accession to search proteins in"), ], keyword: Annotated[ Optional[str], Field(description="Search keyword for protein names or accessions"), ] = None, page_size: Annotated[ int, Field(description="Number of results to return (max 100)"), ] = 20, sort_field: Annotated[ str, Field(description="Sort field: accession, proteinName, or gene"), ] = "accession", sort_direction: Annotated[ str, Field(description="Sort direction: ASC or DESC"), ] = "ASC", ) -> dict:
- src/biocontext_kb/core/_server.py:1-6 (registration)Defines the core_mcp FastMCP server instance named 'BC', which prefixes all its tools with 'bc_' when imported.from fastmcp import FastMCP core_mcp = FastMCP( # type: ignore "BC", instructions="Provides access to biomedical knowledge bases.", )
- src/biocontext_kb/core/__init__.py:16-16 (registration)Imports all from pride module, including search_pride_proteins, making it available on core_mcp.from .pride import *
- src/biocontext_kb/core/pride/__init__.py:1-3 (registration)Re-exports the search_pride_proteins function from its implementation file.from ._get_pride_project import get_pride_project from ._search_pride_projects import search_pride_projects from ._search_pride_proteins import search_pride_proteins
- src/biocontext_kb/app.py:35-39 (registration)Registers the core_mcp server (containing the tool) into the main FastMCP app with prefix slugify('BC')='bc', resulting in tool name 'bc_search_pride_proteins'.for mcp in [core_mcp, *(await get_openapi_mcps())]: await mcp_app.import_server( mcp, slugify(mcp.name), )