Skip to main content
Glama
taehojo
by taehojo

predict_chromatin_impact

Analyze how genetic variants affect chromatin accessibility using DNase and ATAC-seq data to predict chromatin state changes in regulatory regions.

Instructions

Focus on chromatin accessibility effects only.

Analyzes DNase and ATAC-seq predictions for chromatin state changes.

Perfect for: enhancer variants, regulatory region analysis.

Example: "Analyze chromatin impact of chr2:23456789C>T"

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chromosomeYes
positionYes
refYes
altYes
tissue_typeNo

Implementation Reference

  • Core handler function for the predict_chromatin_impact tool. Specializes variant effect prediction for chromatin accessibility modalities (ATAC-seq and DNase-seq) by setting specific output_types and extracting relevant results.
    def predict_chromatin_impact(client, params: Dict[str, Any]) -> Dict[str, Any]:
        """Focus on chromatin accessibility changes."""
        params['output_types'] = [dna_client.OutputType.ATAC, dna_client.OutputType.DNASE]
        result = predict_variant_effect(client, params)
        return {
            'variant': result['variant'],
            'predictions': result['predictions'],
            'impact_level': result['interpretation']['impact_level']
        }
  • Tool definition including name, description, and input schema (JSON Schema) for parameter validation in the MCP tool 'predict_chromatin_impact'.
    export const PREDICT_CHROMATIN_IMPACT_TOOL: Tool = {
      name: 'predict_chromatin_impact',
      description: `Focus on chromatin accessibility effects only.
    
    Analyzes DNase and ATAC-seq predictions for chromatin state changes.
    
    Perfect for: enhancer variants, regulatory region analysis.
    
    Example: "Analyze chromatin impact of chr2:23456789C>T"`,
      inputSchema: {
        type: 'object',
        properties: {
          chromosome: { type: 'string', pattern: '^chr([1-9]|1[0-9]|2[0-2]|X|Y)$' },
          position: { type: 'number', minimum: 1 },
          ref: { type: 'string', pattern: '^[ATGCatgc]+$' },
          alt: { type: 'string', pattern: '^[ATGCatgc]+$' },
          tissue_type: { type: 'string' },
        },
        required: ['chromosome', 'position', 'ref', 'alt'],
      },
    };
  • Registration of the tool action in the Python bridge's main dispatcher, routing 'predict_chromatin_impact' calls to the handler function.
    elif action == 'predict_chromatin_impact':
        result = predict_chromatin_impact(client, params)
  • src/index.ts:213-219 (registration)
    MCP server request handler case that dispatches 'predict_chromatin_impact' tool calls to the AlphaGenome client.
    case 'predict_chromatin_impact': {
      const params = validateInput(variantPredictionSchema, args) as VariantPredictionParams;
      const result = await getClient().predictChromatinImpact(params);
      return {
        content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
      };
    }
  • TypeScript client method that bridges the MCP tool call to the Python bridge script by spawning the process and passing 'predict_chromatin_impact' action.
    async predictChromatinImpact(params: VariantPredictionParams): Promise<any> {
      try {
        return await this.callPythonBridge('predict_chromatin_impact', params);
      } catch (error) {
        if (error instanceof ApiError) throw error;
        throw new ApiError(`Chromatin impact prediction 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