A cell-cell interaction network based method for identifying lymph node metastasis and characterizing lung cancer progression

Lymph node metastasis is an important decision-making basis for lung cancer staging and clinical treatment, and will also significantly affect the prognosis of patients. At present, there is no research to identify lymph node metastasis in non-small cell lung cancer (NSCLC) using cell-cell interaction network (CCIN). We believe that utilizing the characteristics of CCIN can not only distinguish whether different patients have lymph node metastasis, but also help reveal the development process of lung cancer from the perspective of molecular interaction networks. This study utilized graph embedding technology and Fisher's exact test to analyze CCIN, and then combined with a classifier for identifying subtypes and lymph node metastasis of NSCLC. The experimental results showed that the performance of our method is similar to that of image-based methods, and the CCINs at each stage of adenocarcinoma of the lung (LUAD) and lung squamous cell carcinoma (LUSC) were analyzed to identify the differential biological pathways, and further characterized the lymph node metastasis development profile with significant interaction pairs. It is worth noting that the interaction pair features identified by the our method highly were enriched in some known pathways related to the development of lung cancer, thus proving the effectiveness of our method.