Development of an anoikis-related gene signature and prognostic model for predicting the tumor microenvironment and response to immunotherapy in colorectal cancer

Abstract

The effect of anoikis-related genes (ARGs) on clinicopathological characteristics and tumor microenvironment remains unclear. We comprehensively analyzed anoikis-associated gene signatures of 1057 colorectal cancer (CRC) samples based on 18 ARGs. Anoikis-related molecular subtypes and gene features were identified through consensus clustering analysis. The biological functions and immune cell infiltration were assessed using the GSVA and ssGSEA algorithms. Prognostic risk score was constructed using multivariate Cox regression analysis. The immunological features of high-risk and low-risk groups were compared. Finally, DAPK2-overexpressing plasmid was transfected to measure its effect on tumor proliferation and metastasis in vitro and in vivo. We identified 18 prognostic ARGs. Three different subtypes of anoikis were identified and demonstrated to be linked to distinct biological processes and prognosis. Then, a risk score model was constructed and identified as an independent prognostic factor. Compared to the high-risk group, patients in the low-risk group exhibited longer survival, higher enrichment of checkpoint function, increased expression of CTLA4 and PD-L1, higher IPS scores, and a higher proportion of MSI-H. The results of RT-PCR indicated that the expression of DAPK2 mRNA was significantly downregulated in CRC tissues compared to normal tissues. Increased DAPK2 expression significantly suppressed cell proliferation, promoted apoptosis, and inhibited migration and invasion. The nude mice xenograft tumor model confirmed that high expression of DAPK2 inhibited tumor growth. Collectively, we discovered an innovative anoikis-related gene signature associated with prognosis and TME. Besides, our study indicated that DAPK2 can serve as a promising therapeutic target for inhibiting the growth and metastasis of CRC.

Keywords: Anoikis; colorectal cancer; immunotherapy; metastasis; tumor microenvironment.

Figure 1

Landscape of the 18 ARGs in CRC: prognostic values, expression, and genetic variants. (A) The overall survival of 18 ARGs in CRC. (B) The positions of ARGs’ CNV changes. (C) Frequency of CNV. (D) The frequency of ARG mutations. (E) The different expression of the 18 ARGs between tumor tissue and normal tissue from the TCGA database (** p < 0.01; ***p< 0.001). (F) The interactions between ARGs in CRC. Positive correlations are denoted by red strings and negative correlations are denoted by blue strings. The intensity of the correlation is indicated by the shades of color.

Figure 2

Correlation of anoikis pattern with TME infiltration, functional enrichment, and clinical traits. (A) Molecular subgroup screening by means of unsupervised consensus cluster analysis. (B) Expression level of ARGs and clinicopathological features in different subtypes. (C) Subtype-specific K-M OS curves. (D, E) GSVA of two Anoikisclusters related cellular pathways, with red and blue representing activated and inhibited pathways. (D) A vs C, (E) B vs (C, F) GO analyses of prognostic DEGs. (G) Correlations between immune cell infiltration levels in three Anoikisclusters (*** p< 0.001).

Figure 3

Identified gene subtypes based on DEGs. (A) Consensus matrix heatmap identified three clusters (k = 3). (B) Relative change area under cumulative distribution function curve. (C) Differences in clinicopathologic characteristics of the three geneClusters. (D) Variations in the expression of the 18 ARGs in three geneClusters. * p < 0.05 ** p< 0.01, *** p< 0.001. (E) K-M OS curves of three geneClusters.

Figure 4

Construction of the prognostic signature based on prognostic DEGs. (A) The LASSO coefficient spectrum of prognostic DEGs. (B) Partial likelihood bias identified by the LASSO regression model. (C) The forest map of prognostic DEGs constructed by multivariate Cox regression analysis. (D) Alluvial diagram of subtype distributions among groups, risk scores, and survival states. (E), K−M curves showing the differences in survival between the high-risk and low- risk groups. (F) Variations in risk scores among different Anoikisclusters. (G) Variations in risk scores among different geneClusters.

Figure 5

Developing a nomogram with independent prognostic value. Univariate (A) and multivariate (B) Cox regression analysis of the prognostic value of anoikis-related risk score and clinicopathological parameters. (C) Construction of the nomogram based on the risk score to evaluate OS of 1-, 3-, and 5-years for CRC patients. (D) Calibration curve for the nomogram. (E) Prediction of AUC for forecasting 1-, 3-, and 5-year OS. (F) ROC curves for the risk score and clinical characteristics.

Figure 6

Comparison of response to immunotherapy between subgroups. (A) Correlation between risk score and the expression of immune checkpoint genes in CRC patients. (B) Heatmap displaying immunological function enrichment for high-risk and low-risk score groups. * p< 0.05, and *** p< 0.001. (C–F) Comparison of CTLA4/PD-1 IPS scores between high-risk group and low-risk group. CTLA4–PD1–, CTLA4– PD1+, CTLA4+ PD1–, and CTLA4+ PD1+. (G, H) The relationship between MSI and risk scores, *** P< 0.001.

Figure 7

The expression of the anoikis-related gene DAPK2. (A) RT-PCR detected the mRNA expression of DAPK2 in 9 CRC cell lines. (B) RT-PCR detected DAPK2 mRNA expression in cancer and paracancerous tissues. (C) Western blotting analysis of the DAPK2 protein expression in 9 CRC cell lines. (D) The bar chart showed the relationship between DAPK2 and T stage. (E) CCK8 assessing the reproductive capacity in the vector group and DAPK2 overexpression group of SW1116 cells. ** p < 0.01 and *** p < 0.001.

Figure 8

Overexpression of DAPK2 promoted cell apoptosis and inhibited cell proliferation. (A). Representative pictures of colony formation. (B) The average number of cell colonies in (A) (*** p< 0.001). (C) Flow cytometry showing the percentage of cells in each quadrant. Cells in quadrants Q2 and Q3 represented apoptotic cells. (D) Cell apoptotic rate of (C) (*** p< 0.001). (E) Western blotting showing the protein levels of DAPK2, Caspases-3, Cleaved-Caspase-3, Caspases-7 and Cleaved-Caspase-7. (F) Representative images of SW1116 cells in wound healing assay. Scale bar, 100 um. (G) The wound closure rate in (F), *** p<0.01. (H) Representative images of SW1116 cells in Transwell plates. Scale bar, 100 um. (I) Quantification of the number of migration and invasion cells in. (J) Images of xenograft tumors displayed the shape and size of tumor. (K) Volume of xenograft tumors in (J) at day 32 (n = 3, ** p<0.01).

Figure 9

Overexpression of DAPK2 inhibited AKT1/CyclinD1 pathway. (A) GSEA plots for 5 DAPK2 related pathways significantly enriched in TCGA and GEO database. Screening criteria of select pathways: FDR-value< 0.25, and p-value< 0.05. (B) SW1116 cells were treated with DAPK2 overexpression plasmid or AKT1 agonist (SC79). The expression of AKT1, p-AKT1 and epithelial and mesenchymal markers were assessed via western blotting.