GRASP: Graph Reasoning Agents for Systems Pharmacology with Human-in-the-Loop
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsSimilar Papers 제목 키워드 기반
TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology
Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions. We in…
Drug DiscoveryGRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering
Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these systems with knowledge graphs for structured traversal, but this combi…
Multi-hop Question AnsweringPassage RetrievalKnowledge GraphsGraSP: Graph-Structured Skill Compositions for LLM Agents
Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve performance -- focused sets of 2-3 skills outperform comprehensive do…
A multi-agent ontologies-based clinical decision support system
Clinical decision support systems combine knowledge and data from a variety of sources, represented by quantitative models based on stochastic methods, or qualitative based rather on expert heuristics and deductive reaso…
Clinical KnowledgeOptimizing Life Sciences Agents in Real-Time using Reinforcement Learning
Generative AI agents in life sciences face a critical challenge: determining the optimal approach for diverse queries ranging from simple factoid questions to complex mechanistic reasoning. Traditional methods rely on fi…
Reinforcement Learning