A Simplified Genomic Profiling Approach Predicts Outcome in Metastatic Colorectal Cancer

Abstract

The response of metastatic colorectal cancer (mCRC) to the first-line conventional combination therapy is highly variable, reflecting the elevated heterogeneity of the disease. The genetic alterations underlying this heterogeneity have been thoroughly characterized through omic approaches requiring elevated efforts and costs. In order to translate the knowledge of CRC molecular heterogeneity into a practical clinical approach, we utilized a simplified Next Generation Sequencing (NGS) based platform to screen a cohort of 77 patients treated with first-line conventional therapy. Samples were sequenced using a panel of hotspots and targeted regions of 22 genes commonly involved in CRC. This revealed 51 patients carrying actionable gene mutations, 22 of which carried druggable alterations. These mutations were frequently associated with additional genetic alterations. To take into account this molecular complexity and assisted by an unbiased bioinformatic analysis, we defined three subgroups of patients carrying distinct molecular patterns. We demonstrated these three molecular subgroups are associated with a different response to first-line conventional combination therapies. The best outcome was achieved in patients exclusively carrying mutations on TP53 and/or RAS genes. By contrast, in patients carrying mutations in any of the other genes, alone or associated with mutations of TP53/RAS, the expected response is much worse compared to patients with exclusive TP53/RAS mutations. Additionally, our data indicate that the standard approach has limited efficacy in patients without any mutations in the genes included in the panel. In conclusion, we identified a reliable and easy-to-use approach for a simplified molecular-based stratification of mCRC patients that predicts the efficacy of the first-line conventional combination therapy.

Keywords: NGS; chemotherapy; genomic profiling; precision medicine; predictive.

Figure 1

Mutation frequency for each gene of the panel in the study cohort.

Figure 2

Heat-map representation of hierarchical clustering analysis of mCRC data. Columns represent the 77 samples of mCRC patients and rows represent the 22 different mutational markers. Three separate clusters were generated by this analysis. Each cluster corresponds to a distinct genetic profile. The color assigned to a cell in the heatmap grid indicates mutational condition (yellow for mutation, blue for wild-type gene) of a particular gene in a given patient sample.

Figure 3

Kaplan–Meier plot showing the impact of p53/RAS Group (PRG; green), All Genes Group (AGG; red) and No Mutations Group (NMG; blue) group stratification on progression free survival (PFS) in the mCRC cohort.