RegNetAgents: A Multi-Agent Framework for Cross-Network Regulatory Driver Identification in Cancer Genomics

RegNetAgents：用于癌症基因组学跨网络调控驱动因子识别的多智能体框架

Abstract: We introduce RegNetAgents, an AI-oriented multi-agent framework for structured, query-driven regulatory candidate identification across heterogeneous gene regulatory networks. The system enables unified analysis of bulk tumor and single-cell-derived ARACNe networks by integrating TCGA-derived cancer networks with large-scale single-cell regulatory networks from the GREmLN project.

摘要： 我们介绍了 RegNetAgents，这是一个面向人工智能的多智能体框架，用于在异构基因调控网络中进行结构化、查询驱动的调控候选因子识别。该系统通过整合源自 TCGA 的癌症网络与来自 GREmLN 项目的大规模单细胞调控网络，实现了对大块肿瘤（bulk tumor）和单细胞衍生 ARACNe 网络的统一分析。

For a given focal gene, the framework performs dual-network classification, cancer gene filtering using OncoKB annotations, and mode-of-action (MoA) assignment for tumor-derived regulatory relationships. Candidates are ranked by evidence consistency across networks (Both, TCGA-only, GREmLN-only).

对于给定的焦点基因，该框架执行双网络分类、使用 OncoKB 注释进行癌症基因过滤，并为肿瘤衍生的调控关系分配作用模式（MoA）。候选因子根据跨网络的证据一致性（两者共有、仅 TCGA、仅 GREmLN）进行排序。

The system is implemented as a multi-agent LangGraph DAG workflow, accessible through a unified Python API and Model Context Protocol (MCP) client, operating as a downstream analytical layer over precomputed regulatory networks rather than a network inference method.

该系统实现为多智能体 LangGraph DAG 工作流，可通过统一的 Python API 和模型上下文协议（MCP）客户端访问。它作为预计算调控网络的下游分析层运行，而非一种网络推理方法。

Across eleven breast cancer (BRCA) and twelve colorectal cancer (COAD) focal genes, RegNetAgents identifies candidate regulators significantly enriched for OncoKB-annotated cancer genes. TCGA-derived candidates show strong enrichment (Stouffer Z = 6.69 for BRCA and 6.95 for COAD), while GREmLN-derived candidates also demonstrate significant enrichment (Z = 5.51 for BRCA and 7.06 for COAD; all p < 0.0001). No enrichment is observed in housekeeping or non-driver control gene sets, supporting signal specificity.

在 11 个乳腺癌（BRCA）和 12 个结直肠癌（COAD）焦点基因中，RegNetAgents 识别出的候选调控因子在 OncoKB 注释的癌症基因中表现出显著富集。源自 TCGA 的候选因子显示出强富集（BRCA 的 Stouffer Z = 6.69，COAD 为 6.95），而源自 GREmLN 的候选因子也表现出显著富集（BRCA 的 Z = 5.51，COAD 为 7.06；所有 p < 0.0001）。在管家基因或非驱动基因对照组中未观察到富集，这支持了信号的特异性。

An extended module enables structured evaluation of oncogenic potential, druggability, clinical relevance, and network vulnerability, supporting end-to-end interpretation from candidate identification to biological hypothesis generation. RegNetAgents establishes an interpretable AI framework for cross-network regulatory candidate identification in cancer genomics.

一个扩展模块支持对致癌潜力、药物成药性、临床相关性和网络脆弱性进行结构化评估，从而支持从候选因子识别到生物学假设生成的端到端解读。RegNetAgents 为癌症基因组学中的跨网络调控候选因子识别建立了一个可解释的 AI 框架。