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

TL;DR

GRASP is a multi-agent framework that uses graph reasoning and human interaction to streamline and improve the development of quantitative systems pharmacology models, making it more accessible and accurate.

Contribution

It introduces a novel graph-reasoning multi-agent system with a human-in-the-loop interface for efficient QSP model development and validation.

Findings

Outperforms baseline methods in biological plausibility and code quality

Achieves high dependency discovery accuracy (F1=0.95)

Enables natural language specification without losing biomedical fidelity

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 \textbf{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 MATLAB/SimBiology code while preserving units, mass balance, and physiological constraints. A two-phase workflow -- \textsc{Understanding} (graph reconstruction of legacy code) and \textsc{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 correctness, structural fidelity, and code quality (\(\approx\)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.