Unsupervised Metabolomic Analysis for Detecting Early-warning Signals during Progression of Colorectal Cancer

Colorectal cancer (CRC) affects over 2.5 million people globally each year, with the majority of cases originating from the development of adenomatous polyps, which progress from intramucosal carcinoma to malignant tumors. Identifying the critical point (pre-disease state) and detecting early-stage cancer for endoscopic resection are primary objectives in cancer control. However, these tasks present significant challenges due to the extremely subtle or negligible differences in gross signs between the pre-disease and healthy states. In this study, inspired by the dynamic network biomarker (DNB) theory, we propose E-DNB, an unsupervised graph-based model, to detect pre-disease state of CRC deterioration before the onset of malignant tumors using metabolize data. Two stages are involved in the E-DNB model: network construction and graph similarity learning. In the network construction stage, individual networks based on Pearson correlation coefficients are constructed for subjects at different stages of CRC using metabolomics data. Subsequently, individual networks are compared to baseline networks to measure their similarity based on squared Euclidean distance in the graph similarity learning stage, to generate DNB for identifying the pre-disease state of CRCs. Experiments on 220 subjects at various stages of CRC demonstrate that E-DNB achieves an AUC of 71% in detecting pre-disease state of CRCs, which exceeds the current DNB and popular supervised methods, demonstrating the performance of the proposed E-DNB. Our findings offer novel insights into the early diagnosis of CRCs and may contribute to advancements in addressing complex diseases.