This project aims to identify and analyze cell-to-cell interactions in various cancers by integrating multi-omics data from TCGA with single-cell RNA sequencing (scRNA-seq) data from the Single Cell RNA-seq Atlas provided by the Weizmann Institute. Using advanced neural network models, we will process and analyze these data sources along with clinical data to construct personalized interaction networks within the tumor microenvironment. By leveraging neural networks, we will identify gene signatures and their associated omics and clinical variables, such as BMI, age, and lifestyle habits. Cancer is characterized by heterogeneous cell populations and complex interactions, which traditional bulk RNA sequencing cannot fully capture. By combining bulk multi-omics, single-cell data, and clinical information, we aim to provide insights into tumor progression, metastasis, and treatment responses, ultimately identifying potential therapeutic targets and biomarkers