Machine learning revealed molecular classification of colorectal cancer with negative lymph node metastasis

Abstract

Purpose: Accurate preoperative staging directly affects the treatment decision of patients with rectal cancer. However, our understanding of the immune subclasses of CRC without lymph node metastasis is still incomplete. Materials and methods: Here, we first analyzed the subclasses of CRC without lymph node metastasis on the Cancer Genome Atlas (TCGA) and verified its stability in the GSE39582 dataset. Four immune subclasses (C1–C4) were identified and verified by non-negative matrix factorization (NMF) of gene expression profiles. Then, ICI scores of six genes were constructed to characterize subclasses. Results: There were significant differences in metabolic and progression-associated signatures, immune characteristics, and clinical characteristics among subclasses. C3 represented a good prognosis with high TMB. C4 showed unique immune characteristics. We believe that C3 is the initial stage of CRC. After the C1 and C2 stages, it progresses to the C4 stage, and finally, lymph node metastasis occurs. Conclusions: This work may help to provide a basis for immunotherapy decision-making in early CRC and may guide personalized methods of cancer immunotherapy.