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

Short summary

RegNetAgents is a multi-agent AI framework for identifying regulatory driver candidates across heterogeneous gene regulatory networks in cancer genomics. Built as a LangGraph DAG workflow with MCP client support, it integrates TCGA bulk tumor and single-cell networks, performing dual-network classification, cancer gene filtering, and mode-of-action assignment. Across 23 breast and colorectal cancer focal genes, candidates show significant enrichment for annotated cancer genes, with no enrichment in control sets, demonstrating signal specificity.

• •Multi-agent LangGraph framework for cross-network regulatory driver identification in cancer
• •Integrates TCGA and single-cell regulatory networks with OncoKB annotation filtering
• •Significant enrichment for cancer genes across BRCA and COAD with signal specificity confirmed

Generated with AI, which can make mistakes.