br develop a novel TME
develop a novel TME-related prognostic model to improve predic-tive accuracy and identify patients for whom chemo- and immuno-therapies may be more beneficial.
Added value of this study
We developed a robust prognostic panel utilising the machine learning method based on TME-relevant Veratridine for stage I–III colon cancer patients, designated as the “tumour microenviron-ment risk score (TMRS)”. This panel not only accurately predicted relapse-free survival and overall survival among colon cancer pa-tients, but also served as a biomarker for identifying patients that could potentially benefit from adjuvant chemotherapy. In ad-dition to colon cancer, the TMRS panel was also revealed to be a reliable tool for prognostic prediction and chemotherapeutic decision-making in gastric cancer. Furthermore, we also found that the TMRS panel enabled prediction of anti-PD-L1 and anti-PD-1 immunotherapy outcomes in urothelial carcinoma patients and melanoma patients.
Implications of all the available evidence
The TMRS gene panel represents a potentially robust tool for sur-vival prediction and treatment guidance in patients with stage I–III colon cancer and may also be applicable to other types of cancers.
the immunoscore system was found to be limited. A multi-central study conducted by Galon et al.  indicated that the c-indexes of the immunoscore for relapse-free survival (RFS) and overall survival (OS) were 0·62 and 0·58, respectively. Therefore, a novel TME-related prog-nostic model may be needed to improve predictive accuracy and iden-tify patients, for whom chemo- and immunotherapies may be more beneficial.
Recent advances in high-throughput gene testing technology have provided an opportunity to define the genetic landscape of colon cancer and led to the development of many molecular signatures for prognosis prediction and personalisation of treatment paradigms [8–11]. How-ever, some of these signatures were frequently ill-defined, having been generated from unspecified genetic backgrounds. To the best of our knowledge, prognostic signatures based on TME-relevant genes in colon cancer have not yet been proposed. The objective of the current study was to develop a robust prognostic gene panel utilising the ma-chine learning method, designated as the “tumour microenvironment
risk score (TMRS)”, to improve the risk stratification of patients with stage I–III colon cancer. Furthermore, we assessed the ability of this panel to predict patient response to chemotherapy and immune-checkpoint inhibitors.
2. Materials and methods
2.1. Transcriptome data acquisition and pre-processing
The Gene Expression Omnibus (GEO; http://www.ncbi.nlm.nih.gov/ geo/) was searched for eligible colon cancer datasets that fulfilled the following criteria: samples were hybridised to the Affymetrix HG-U133 Plus 2·0 (GEO accession number GPL570) platforms; N50 stage I–III colon cancer patients were included in each dataset; and informa-tion on the TNM stage was available. In order to explore the role of our model in gastric cancer, we downloaded the “GSE62254” dataset, si-multaneously containing RFS and OS information generated via the GPL570 platform. Finally, for the immunotherapeutic efficiency analysis, two transcriptomic datasets from patients with metastatic urothelial cancer (mUC) treated with anti-PD-L1 agents (atezolizumab, IMvigor dataset, retrieved via R software using “IMvigor” package) , and pa-tients with metastatic melanoma treated with anti-PD-1 agents (pembrolizumab or nivolumab, GSE78220, downloaded from GEO website) were downloaded. Expression profiles of these two cohorts were generated via high throughput sequencing. Raw “CEL” files of mi-croarray data were downloaded and normalised using a robust multiarray averaging method with “affy” and “simpleaffy” packages . RNA sequencing data was transformed using the “voom” algorithm in order to convert count data to values similar to those resulting from microarrays . The “ComBat” algorithm was applied to reduce the likelihood of batch effects from non-biological technical biases. A sum-mary of the information of all datasets used in this study is provided (Supplement Table S1).