Machine Learning-Driven Dissection of the Obesity-ccRCC Interface: FCGR2A Emerges as a Central Coordinator of Tumor-Immune Crosstalk

Zhongyuan He¹Zheng Wang¹Shang Lai¹Xunfei Yin¹Dawang Zheng¹Shuai Liu²Wenjie Liu³Guiying Guo^1*

• ¹First Affiliated Hospital of Harbin Medical University, Harbin, China
• ²The Third Affiliated Hospital of Qiqihar Medical University, Qiqihar, China
• ³Nehe City People's Hospital, harbin, China

Obesity is a well-established risk modifier for clear cell renal cell carcinoma (ccRCC), yet the molecular mechanisms underlying their epidemiological association remain unclear. To address this knowledge gap, we developed a dual-disease analytical framework integrating transcriptomic profiling with machine learning to identify shared pathobiological signatures. Five ccRCC datasets (n=876) and obesity-related adipose tissue profiles were harmonized through advanced batch correction, revealing 130 co-dysregulated genes enriched in myeloid immune functions. Network topology analysis prioritized FCGR2A as the central hub gene, exhibiting robust diagnostic performance (AUC=0.998) for distinguishing tumor stages and significant overexpression in ccRCC cell lines (3.1-fold vs. normal epithelium, p=0.002). The optimized machine learning model identified a parsimonious 14-gene signature demonstrating exceptional cross-cohort validation accuracy (mean AUC=0.991), with kinase inhibitors and immunomodulators emerging as promising therapeutic candidates targeting this shared axis.Single-cell transcriptomics localized FCGR2A to M2-polarized macrophages, revealing direct interaction with peritumoral adipocytes.Our results reveal immune dysregulation as a central mechanism connecting metabolic dysfunction with ccRCC progression, with FCGR2A-mediated myeloid reprogramming serving as both a prognostic biomarker and potential therapeutic target. This study establishes a paradigm for dual-disease modeling in oncology, providing actionable insights for precision management of obesity-associated malignancies.