Skip to main content
Glama
taehojo
by taehojo

analyze_gwas_locus

Analyze GWAS locus variants to rank them by regulatory impact for fine-mapping and causal variant identification.

Instructions

Analyze all variants in a GWAS locus.

Ranks variants by regulatory impact for fine-mapping and causal variant identification.

Perfect for: GWAS follow-up, fine-mapping, identifying causal variants.

Example: "Analyze GWAS locus with 10 variants"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
variantsYes
chromosomeNo
startNo
endNo

Implementation Reference

  • MCP CallTool request handler case for 'analyze_gwas_locus': validates input (implicitly via schema), calls AlphaGenomeClient.analyzeGwasLocus, and returns JSON-formatted result.
    case 'analyze_gwas_locus': {
      const result = await getClient().analyzeGwasLocus(args);
      return {
        content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
      };
    }
  • Tool schema and definition: specifies name, description, input schema with variants array (required), optional chromosome/start/end for locus.
    export const ANALYZE_GWAS_LOCUS_TOOL: Tool = {
      name: 'analyze_gwas_locus',
      description: `Analyze all variants in a GWAS locus.
    
    Ranks variants by regulatory impact for fine-mapping and causal variant identification.
    
    Perfect for: GWAS follow-up, fine-mapping, identifying causal variants.
    
    Example: "Analyze GWAS locus with 10 variants"`,
      inputSchema: {
        type: 'object',
        properties: {
          variants: {
            type: 'array',
            items: {
              type: 'object',
              properties: {
                chromosome: { type: 'string' },
                position: { type: 'number' },
                ref: { type: 'string' },
                alt: { type: 'string' },
              },
              required: ['chromosome', 'position', 'ref', 'alt'],
            },
            minItems: 1,
          },
          chromosome: { type: 'string' },
          start: { type: 'number' },
          end: { type: 'number' },
        },
        required: ['variants'],
      },
    };
  • src/index.ts:99-101 (registration)
    MCP ListTools request handler that registers and exposes all tools, including analyze_gwas_locus via ALL_TOOLS import.
    server.setRequestHandler(ListToolsRequestSchema, async () => {
      return { tools: ALL_TOOLS };
    });
  • src/tools.ts:709-730 (registration)
    Central registration array ALL_TOOLS that includes ANALYZE_GWAS_LOCUS_TOOL for exposure via MCP ListTools.
    export const ALL_TOOLS: Tool[] = [
      PREDICT_VARIANT_TOOL,
      BATCH_SCORE_TOOL,
      ASSESS_PATHOGENICITY_TOOL,
      PREDICT_TISSUE_SPECIFIC_TOOL,
      COMPARE_VARIANTS_TOOL,
      PREDICT_SPLICE_IMPACT_TOOL,
      PREDICT_EXPRESSION_IMPACT_TOOL,
      ANALYZE_GWAS_LOCUS_TOOL,
      COMPARE_ALLELES_TOOL,
      BATCH_TISSUE_COMPARISON_TOOL,
      PREDICT_TF_BINDING_IMPACT_TOOL,
      PREDICT_CHROMATIN_IMPACT_TOOL,
      COMPARE_PROTECTIVE_RISK_TOOL,
      BATCH_PATHOGENICITY_FILTER_TOOL,
      COMPARE_VARIANTS_SAME_GENE_TOOL,
      PREDICT_ALLELE_SPECIFIC_EFFECTS_TOOL,
      ANNOTATE_REGULATORY_CONTEXT_TOOL,
      BATCH_MODALITY_SCREEN_TOOL,
      GENERATE_VARIANT_REPORT_TOOL,
      EXPLAIN_VARIANT_IMPACT_TOOL,
    ];
  • AlphaGenomeClient helper method that bridges to Python subprocess for 'analyze_gwas_locus' action.
    async analyzeGwasLocus(params: any): Promise<any> {
      try {
        return await this.callPythonBridge('analyze_gwas_locus', params);
      } catch (error) {
        if (error instanceof ApiError) throw error;
        throw new ApiError(`GWAS locus analysis failed: ${error}`, 500);
      }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/taehojo/alphagenome-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server