predict_expression_impact

Analyze how genetic variants affect gene expression using RNA-seq and CAGE data. Supports eQTL analysis and expression-related variant studies.

Instructions

Focus on gene expression effects only.

Analyzes RNA-seq and CAGE predictions for expression changes.

Perfect for: eQTL analysis, expression-related variants.

Example: "Analyze expression impact of rs744373"

Input Schema

TableJSON Schema

Name	Required	Description	Default
`chromosome`	Yes
`position`	Yes
`ref`	Yes
`alt`	Yes
`tissue_type`	No

Implementation Reference

scripts/alphagenome_bridge.py:371-387 (handler)

Core handler function that executes the predict_expression_impact tool logic by setting specific output types for RNA-seq and CAGE, calling the base variant effect predictor, and returning expression-focused results.

def predict_expression_impact(client, params: Dict[str, Any]) -> Dict[str, Any]:
    """
    Focus on gene expression effects only.
    """
    params['output_types'] = [
        dna_client.OutputType.RNA_SEQ,
        dna_client.OutputType.CAGE
    ]

    result = predict_variant_effect(client, params)

    return {
        'variant': result['variant'],
        'expression_predictions': result['predictions'].get('rna_seq', {}),
        'fold_change': result['predictions'].get('rna_seq', {}).get('fold_change', 0),
        'impact_level': result['interpretation']['impact_level']
    }

src/tools.ts:312-332 (schema)

Defines the tool schema including name, description, and input validation schema for variant parameters.

export const PREDICT_EXPRESSION_IMPACT_TOOL: Tool = {
  name: 'predict_expression_impact',
  description: `Focus on gene expression effects only.

Analyzes RNA-seq and CAGE predictions for expression changes.

Perfect for: eQTL analysis, expression-related variants.

Example: "Analyze expression impact of rs744373"`,
  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'],
  },
};

src/index.ts:176-182 (registration)

MCP server tool call handler that routes 'predict_expression_impact' requests, validates input, calls the client bridge, and formats the response.

case 'predict_expression_impact': {
  const params = validateInput(variantPredictionSchema, args) as VariantPredictionParams;
  const result = await getClient().predictExpressionImpact(params);
  return {
    content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
  };
}

src/alphagenome-client.ts:298-311 (helper)

TypeScript client method that bridges the tool call to the Python backend by invoking callPythonBridge with the 'predict_expression_impact' action.

async predictExpressionImpact(params: VariantPredictionParams): Promise<any> {
  try {
    return await this.callPythonBridge('predict_expression_impact', {
      chromosome: params.chromosome,
      position: params.position,
      ref: params.ref,
      alt: params.alt,
      tissue_type: params.tissue_type,
    });
  } catch (error) {
    if (error instanceof ApiError) throw error;
    throw new ApiError(`Expression impact prediction failed: ${error}`, 500);
  }
}

scripts/alphagenome_bridge.py:812-813 (registration)
Backend Python dispatch logic in main() that registers and routes the 'predict_expression_impact' action to the handler function.
```
elif action == 'predict_expression_impact':
    result = predict_expression_impact(client, params)
```

AlphaGenome MCP Server