assess_drug_likeness

Evaluate compound drug-likeness using Lipinski's Rule of Five and other pharmaceutical metrics to predict oral bioavailability potential.

Instructions

Assess drug-likeness using Lipinski Rule of Five and other metrics

Input Schema

TableJSON Schema

Name	Required	Description	Default
`chembl_id`	No	ChEMBL compound ID
`smiles`	No	SMILES string (alternative to ChEMBL ID)

Implementation Reference

src/index.ts:672-683 (registration)

Tool registration in the ListToolsRequestSchema response, including name, description, and input schema definition.

{
  name: 'assess_drug_likeness',
  description: 'Assess drug-likeness using Lipinski Rule of Five and other metrics',
  inputSchema: {
    type: 'object',
    properties: {
      chembl_id: { type: 'string', description: 'ChEMBL compound ID' },
      smiles: { type: 'string', description: 'SMILES string (alternative to ChEMBL ID)' },
    },
    required: [],
  },
},

src/index.ts:793-794 (registration)
Tool handler dispatch in the CallToolRequestSchema switch statement.
```
case 'assess_drug_likeness':
  return await this.handleAssessDrugLikeness(args);
```

src/index.ts:1688-1775 (handler)

The primary handler function that implements the assess_drug_likeness tool logic: fetches ChEMBL compound data, computes Lipinski Rule of Five violations, Veber rules compliance, and generates comprehensive drug-likeness assessment.

private async handleAssessDrugLikeness(args: any) {
  if (!args || (!args.chembl_id && !args.smiles)) {
    throw new McpError(ErrorCode.InvalidParams, 'Invalid drug-likeness assessment arguments');
  }

  try {
    let molecule;
    if (args.chembl_id) {
      const response = await this.apiClient.get(`/molecule/${args.chembl_id}.json`);
      molecule = response.data;
    } else {
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              message: 'SMILES-based drug-likeness assessment requires ChEMBL ID',
              smiles: args.smiles,
            }, null, 2),
          },
        ],
      };
    }

    const props = molecule.molecule_properties || {};

    // Lipinski Rule of Five
    const mw = props.full_mwt || props.molecular_weight || 0;
    const logp = props.alogp || 0;
    const hbd = props.hbd || 0;
    const hba = props.hba || 0;

    const lipinskiViolations = [
      mw > 500 ? 'Molecular weight > 500 Da' : null,
      logp > 5 ? 'LogP > 5' : null,
      hbd > 5 ? 'H-bond donors > 5' : null,
      hba > 10 ? 'H-bond acceptors > 10' : null,
    ].filter(v => v !== null);

    // Veber rules
    const rtb = props.rtb || 0;
    const psa = props.psa || 0;
    const veberPass = rtb <= 10 && psa <= 140;

    // Overall assessment
    const drugLikenessAssessment = {
      chembl_id: molecule.molecule_chembl_id,
      lipinski_rule_of_five: {
        violations: lipinskiViolations.length,
        details: lipinskiViolations.length > 0 ? lipinskiViolations : ['All criteria met'],
        pass: lipinskiViolations.length === 0,
        criteria: {
          molecular_weight: { value: mw, limit: 500, pass: mw <= 500 },
          logp: { value: logp, limit: 5, pass: logp <= 5 },
          hbd: { value: hbd, limit: 5, pass: hbd <= 5 },
          hba: { value: hba, limit: 10, pass: hba <= 10 },
        },
      },
      veber_rules: {
        pass: veberPass,
        criteria: {
          rotatable_bonds: { value: rtb, limit: 10, pass: rtb <= 10 },
          psa: { value: psa, limit: 140, pass: psa <= 140 },
        },
      },
      overall_assessment: {
        drug_likeness: lipinskiViolations.length === 0 ? 'Excellent' : lipinskiViolations.length === 1 ? 'Good' : 'Poor',
        oral_bioavailability: veberPass && lipinskiViolations.length <= 1 ? 'Likely' : 'Uncertain',
        recommendation: this.getDrugLikenessRecommendation(lipinskiViolations.length, veberPass),
      },
      molecular_properties: props,
    };

    return {
      content: [
        {
          type: 'text',
          text: JSON.stringify(drugLikenessAssessment, null, 2),
        },
      ],
    };
  } catch (error) {
    throw new McpError(
      ErrorCode.InternalError,
      `Failed to assess drug-likeness: ${error instanceof Error ? error.message : 'Unknown error'}`
    );
  }
}

src/index.ts:1777-1786 (helper)

Supporting helper function called by the handler to provide textual recommendation based on the number of Lipinski violations and Veber rule compliance.

private getDrugLikenessRecommendation(violations: number, veberPass: boolean): string {
  if (violations === 0 && veberPass) {
    return 'Excellent drug-like properties - suitable for oral administration';
  } else if (violations <= 1 && veberPass) {
    return 'Good drug-like properties - likely suitable for development';
  } else if (violations <= 2) {
    return 'Moderate drug-like properties - may require optimization';
  }
  return 'Poor drug-like properties - significant optimization needed';
}

ChEMBL MCP Server