Katz Kernel Based Stratification of Breast Cancer Patients
Abstract
The integration of mechanistic signaling networks into clinical research has become a cornerstone of precision oncology. By capturing the complex biochemical interactions within a cell, these networks provide a functional map of disease progression that goes beyond simple genomic mutations. Consequently, the development of specific signaling models of patients has significant relevance, allowing for a more granular representation of individual disease profiles. In this setting, there is a growing need for robust methodologies capable of comparing graph based pathway structures to identify similarities and differences across patient cohorts. Such comparisons are essential for the identification of clinically meaningful subgroups, and the discovery of novel biomarkers. Standard graph kernels, while mathematically rigorous, often remain too generic for this purpose. They frequently fail to capture features specific to gene signaling networks, resulting in suboptimal clustering performance. In this paper, we present a domain specific graph kernel designed for mechanistic signaling networks. Unlike generic approaches, our method explicitly incorporates biological constraints and gene interaction patterns into the kernel formulation, enabling a more accurate characterization of both topological structure and functional behavior. We assess its performance on breast cancer datasets, focusing on its ability to support disease subtyping. Our results suggest that our approach can effectively contribute to patient stratification.
Related
- Effects of myofascial release on clinical outcomes and muscle viscoelastic properties in patients with breast cancer: A randomized controlled trial
- Which quality of life issues are important to patients with metastatic breast cancer: Phase 1 and 2 development of European Organisation for Research and Treatment of Cancer metastatic breast cancer module (EORTC QLQ-MBR)
- An integrated geometric quantification and shape analysis framework for axillary lymph node metastasis in breast cancer patients
- Awareness of hereditary breast cancer and readiness for genetic testing among newly diagnosed patients with breast cancer in Nigeria: a multicentre study.
- Preferences and reasons for clothing colors in women patients and survivors of breast cancer in Korea
BibTeX
@misc{cellitti2026katz,
title = {{Katz Kernel Based Stratification of Breast Cancer Patients}},
author = {Francesco Cellitti and Lorenzo Di Rocco and Livia Perfetto and Veronica Lombardo and Umberto Ferraro Petrillo},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.14540},
eprint = {2611.14540},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.14540},
}
RIS
TY - UNPB
TI - Katz Kernel Based Stratification of Breast Cancer Patients
AU - Francesco Cellitti
AU - Lorenzo Di Rocco
AU - Livia Perfetto
AU - Veronica Lombardo
AU - Umberto Ferraro Petrillo
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.14540
UR - https://arxiv.org/abs/2611.14540
AB - The integration of mechanistic signaling networks into clinical research has become a cornerstone of precision oncology. By capturing the complex biochemical interactions within a cell, these networks provide a functional map of disease progression that goes beyond simple genomic mutations. Consequently, the development of specific signaling models of patients has significant relevance, allowing for a more granular representation of individual disease profiles. In this setting, there is a growing need for robust methodologies capable of comparing graph based pathway structures to identify similarities and differences across patient cohorts. Such comparisons are essential for the identification of clinically meaningful subgroups, and the discovery of novel biomarkers. Standard graph kernels, while mathematically rigorous, often remain too generic for this purpose. They frequently fail to capture features specific to gene signaling networks, resulting in suboptimal clustering performance. In this paper, we present a domain specific graph kernel designed for mechanistic signaling networks. Unlike generic approaches, our method explicitly incorporates biological constraints and gene interaction patterns into the kernel formulation, enabling a more accurate characterization of both topological structure and functional behavior. We assess its performance on breast cancer datasets, focusing on its ability to support disease subtyping. Our results suggest that our approach can effectively contribute to patient stratification.
ER -