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

arXiv cs.AI · 6 hours ago

RegNetAgents is a multi-agent AI framework for identifying regulatory genes involved in cancer by analyzing gene regulatory networks from bulk tumor and single-cell data. The system identified regulatory candidates with Stouffer Z-scores of 6.69-7.06 across breast and colorectal cancer datasets, showing significant enrichment for known cancer genes while avoiding false positives in control gene sets. This enables researchers to prioritize candidate genes for downstream validation and therapeutic targeting in cancer genomics studies.