Objective:

To develop an integrated framework that combines text mining and knowledge graph modeling for biopharmaceutical process optimization.

Key Findings:

• The knowledge graph enables users to query and explore associations between process parameters and outcomes.
• Case examples in monoclonal antibody manufacturing demonstrated the framework's utility in identifying relationships.
• Each extracted relationship is linked to its original reference for transparency.

Interpretation:

The framework supports literature review, hypothesis generation, and experimental planning in biopharmaceutical process development.

Limitations:

• System performance is dependent on the consistency and completeness of published data.
• Variability in terminology may affect entity recognition and relationship mapping.
• The framework does not replace the need for experimental validation.

Conclusion:

Further evaluation is needed to integrate this system into routine process optimization workflows and regulatory documentation.