GRASP: Graph Reasoning Agents for Systems Pharmacology with Human-in-the-Loop

Omid Bazgir, Mohammad Jafarnejad, Vineeth Manthapuri, Ilia Rattsev

Keywords: Graph, Agent, Reasoning, LLM, Drug Development, Systems Pharmacology

Abstract:

Quantitative Systems Pharmacology (QSP) modeling is essential for drug development but it requires significant time investment that limits the throughput of domain experts. We present GRASP—a multi-agent, graph-reasoning framework with a human-in-the-loop conversational interface—that encodes QSP models as typed biological knowledge graphs and compiles them to executable MAT
LAB/SimBiology code while preserving units, mass balance, and physiological constraints. A two-phase workflow—UNDERSTANDING (graph reconstruction of legacy code) and ACTION (constraint-checked, language-driven modification)—is orchestrated by a state machine with iterative validation. GRASP performs breadth-first parameter-alignment around new entities to surface dependent quantities and propose biologically plausible defaults, and it runs automatic execution/diagnostics until convergence. In head-to-head evaluations using LLM-as-judge, GRASP outperforms SME guided CoT and ToT baselines across biological plausibility, mathematical correct
ness, structural fidelity, and code quality (≈9–10/10 vs. 5–7/10). BFS alignment achieves F1 = 0.95 for dependency discovery, units, and range. These results demonstrate that graph-structured, agentic workflows can make QSP model development both accessible and rigorous, enabling domain experts to specify mechanisms in natural language without sacrificing biomedical fidelity.

Submission Number: 141