Bioinformatics mining and experimental validation of prognostic biomarkers in colorectal cancer

Abstract

Colorectal cancer (CRC) is a prevalent condition with increasing incidence and mortality rates. The identification of robust prognostic gene signatures remains an unmet clinical need in CRC treatment. In this study, data from the GEO and TCGA databases were utilized to identify 2,779 upregulated and 2,629 downregulated genes in CRC tissues compared to adjacent normal tissues. WGCNA analysis highlighted the MEbrown module, which comprised 1,639 genes that exhibited strong correlations with CRC progression. Subsequently, an intersection analysis was conducted to further refine the candidate gene set, resulting in the selection of 926 differentially expressed CRC-related genes for subsequent analysis. Through univariate Cox regression, LASSO regularization, and multivariate Cox regression, a five-gene prognostic signature (TIMP1, PCOLCE2, MEIS2, HDC, CXCL13) was established, demonstrating consistent predictive accuracy in external (GSE32323) and internal validation cohorts. Mutational profiling showed predominant missense mutations across signature genes, with TIMP1 exhibiting the highest variant allele frequency. Functional enrichment analysis linked TIMP1 to critical CRC pathways including type I interferon receptor binding, oxidative phosphorylation, and Notch signaling pathways. High expression of TIMP1 was associated with poor prognosis in patients with CRC. Additionally, using siRNA technology, the impact of TIMP1 on cellular proliferation, metastasis and apoptosis in CRC cell lines (HCT116 and HT29) was investigated, showing that TIMP1 knockdown significantly inhibited CRC cell proliferation, metastasis, and promoted apoptosis. These experimental results were consistent with the conclusions drawn from the bioinformatics analysis. This research presents a prognostic risk model for CRC, further highlights TIMP1 as a potential biomarker and therapeutic target for the disease.

Keywords: TIMP1; Bioinformatics; Colorectal cancer; Prognostic biomarkers; WGCNA.

Fig. 1

Identification of the differentially expressed genes and DE-CRC-related genes in the TCGA cohort. A Volcano plot, is used to identify DEGs between tumor and normal tissues; B Heatmap visualization of differentially expressed genes; C Diagram of sample clustering; D. Chart of genes scale-free distribution; E. Diagram of modules; F. The heat map of module-trait relationships. The MEbrown module was identified as the key module associated with CRC; G. Venn diagram of DEGs and key module genes intersections

Fig. 2

GO and KEGG analyses of all differentially expressed genes in CRC. A PPI network; B Go analysis in biological process of DE-CRC-related genes; C Go analysis in cellular component of DE-CRC-related genes; D Go analysis in molecular function of DE-CRC-related genes; E KEGG [–29] pathway analysis of DE-CRC-related genes

Fig. 3

Construction and evaluation of the prognostic risk model. A and C respectively represent the univariate and multivariate Cox regression analyses conducted for prognostic gene screening; B. LASSO regression analysis; D. Chromosomal localization of prognostic genes; E. Scatter plots illustrating high and low risk scores, as well as the association between risk scores and prognosis; F. KM analysis demonstrated a significant difference in prognosis between the low-risk and high-risk groups (p < 0.0001); G. The ROC curve analysis. AUC values at 1, 2, and 3 years were approximately 0.7 indicating better efficacy of the risk model. H. Differential expression of prognostic genes in the GSE32323 dataset

Fig. 4

Functional assessment of the prognostic risk model. A Multivariate Cox regression analyses to detect independent prognostic factors; B Prognostic model nomogram were developed; C Calibration curve for evaluating the predictive performance of nomogram model; D The ROC curves for evaluating the predictive performance of nomogram model, the AUC values for 1, 2 and 3 years were all greater than 0.7

Fig. 5

Multiple analyses of characteristic genes in CRC. A Mutation analysis of all genes in the TCGA-CRC dataset; B Mutation status of five prognostic genes; C. Variant allele frequency of prognostic genes; D. Analysis of copy number variation (CNV) status of prognostic genes by GSCA database

Fig. 6

Functional analyses and histological expression of TIMP1 in CRC. A Go analysis items of TIMP1 in CRC; B KEGG pathways of TIMP1 in CRC; C Data from the UALCAN database indicating that TIMP1 is more highly expressed in CRC tissues than in normal tissues. *** P < 0.001. D The expression of TIMP1 increases with increasing pathological grade according to the UALCAN database. E, F. The HPA analysis; G. KM survival curves of patients with high versus low expression of TIMP1 in the TCGA database (P = 0.0058)

Fig. 7

The clinical significance of TIMP1 in CRC and in vitro study. A, B. Evaluation of silencing efficiency of siRNA in CRC cell lines; C. MTT and Cell colony forming assays are used to assess the influence of blocking TIMP1 expressions on proliferative abilities of HCT116 and HT29 cells; D. The transwell assays revealed that silencing of TIMP1 inhibited the migration and invasion of CRC cells; E. The apoptosis observed after knocking down TIMP1 in CRC cells. All experiments and analyses were performed in triplicate to ensure accuracy and reliability. Numerical data are displayed as the mean ± standard deviation (SD). siRNA Small interfering RNA; Control: Blank control group; NC: Negative control group; ** means p value < 0.01; *** means p value < 0.001