Identification of subtypes in digestive system tumors based on multi-omics data and graph convolutional network

Accurately predicting the molecular subtype of cancer patients is of great significance for personalized diagnosis and treatment of cancer. The progress of a large amount of multi-omics data and data-driven methods is expected to promote the molecular subtyping of cancer. Existing methods are limited by their ability to deal with high-dimensional data and the influence of misleading and unrelated factors, resulting in ambiguous and overlapping subtypes. This article proposes a method called Multi-Omics Subtypes of Digestive System Tumors (MSDST), which is used for subtype identification of digestive system tumors. The method learns a new representation of the relationship between samples from multi-omics data, and uses a self-encoding model composed of omics-specific graph convolutional networks to learn the high-level representation of each omics data feature while considering the prognosis prediction results. Finally, k-means algorithm is used to cluster samples for analysis. Compared with other state-of-the-art methods, our proposed method performs better in identifying digestive system tumor subtypes. Subsequent clinical data analysis and functional enrichment analysis further confirm the specific biological characteristics and functional differences of the identified subtypes. This research provides new ideas and methods for precision medicine, and is expected to promote personalized treatment and improve the prognosis of digestive system tumors.