Construction of prediction model of inflammation related genes in idiopathic pulmonary fibrosis and its correlation with immune microenvironment

Abstract

Background: The role of inflammation in the formation of idiopathic pulmonary fibrosis (IPF) has gained a lot of attention recently. However, the involvement of genes related to inflammation and immune exchange environment status in the prognosis of IPF remains to be further clarified. The objective of this research is to establish a new model for the prediction of the overall survival (OS) rate of inflammation-related IPF.

Methods: Gene Expression Omnibus (GEO) was employed to obtain the three expression microarrays of IPF, including two from alveolar lavage fluid cells and one from peripheral blood mononuclear cells. To construct the risk assessment model of inflammation-linked genes, least absolute shrinkage and selection operator (lasso), univariate cox and multivariate stepwise regression, and random forest method were used. The proportion of immune cell infiltration was evaluated by single sample Gene Set Enrichment Analysis (ssGSEA) algorithm.

Results: The value of genes linked with inflammation in the prognosis of IPF was analyzed, and a four-genes risk model was constructed, including tpbg, Myc, ffar2, and CCL2. It was highlighted by Kaplan Meier (K-M) survival analysis that patients with high-risk scores had worse overall survival time in all training and validation sets, and univariate and multivariate analysis highlighted that it has the potential to act as an independent risk indicator for poor prognosis. ROC analysis showed that the prediction efficiency of 1-, 3-, and 5-year OS time in the training set reached 0.784, 0.835, and 0.921, respectively. Immune infiltration analysis showed that Myeloid-Derived Suppressor Cells (MDSC), macrophages, regulatory T cells, cd4+ t cells, neutrophils, and dendritic cells were more infiltrated in the high-risk group than in the low-risk group.

Conclusion: Inflammation-related genes can be well used to evaluate the IPF prognosis and impart a new idea for the treatment and follow-up management of IPF patients.

Keywords: idiopathic pulmonary fibrosis; immune microenvironment; inflammation; prognosis; ssGSEA.

Figure 1

Expression and enrichment analysis of inflammation-linked genes in IPF. (A) Heat map of the expression of genes linked with inflammation in the discovery set. (B) GO enrichment analysis of DEGs. (C) KEGG analysis of DEGs.

Figure 2

Identifying prognostic biomarkers. (A) Univariate Cox regression identifying genes associated with IPF prognosis. (B) Lasso regression further identifying prognosis-related genes. (C) Random Forest identifying the top 10 genes that are relatively important in prognosis. (D) Wayne diagram identifying the common genes selected by the two methods. (E) Multivariate stepwise Cox regression finally determined the prognosis-related genes.

Figure 3

Prognostic value of risk model in the training cohort. (A) K-M method was used to draw the survival curve according to risk score, and for comparison, a log-rank test was employed. (B) The distribution of risk score and survival status between high and low-risk groups. (C) To evaluate the differentiation between groups with high and low risk, PCA was utilized. (D) Through ROC analysis, the predictive effect of the risk model in the training queue was evaluated. (E) Univariate and multivariate Cox analysis. (F) C-index analysis was used to evaluate the prediction ability of the model.

Figure 4

The effectiveness of the risk model was verified in the validation set. (A) K-M method was used to draw the survival curve according to risk score, and for the comparison, the log-rank test was employed. (B) The distribution of risk score and survival status between high and low-risk groups. (C) To evaluate the differentiation between groups with high and low risk, PCA was utilized. (D) Through ROC analysis, the predictive role of the risk model in the validation queue was evaluated. (E) Univariate and multivariate Cox analysis. (F) C-index analysis was used to evaluate the prediction ability of the model.

Figure 5

The effectiveness of the risk model was verified in the validation set. (A) K-M method was used to draw the survival curve based on risk score, and for comparison, a log-rank test was employed. (B) The distribution of RS and survival status between high and low-risk groups. (C) To evaluate the differentiation between groups with high and low-risk, PCA was utilized. (D) Through ROC analysis, the predictive role of the risk model in the validation cohort was evaluated. (E) Univariate and multivariate Cox analysis. (F) for the evaluation of the prediction ability of the model, C-index analysis was employed.

Figure 6

Survival analysis of risk model in different subgroups. Survival analysis of risk models in the subgroup of age ≤ 65 (A) and greater than 65 (B). Survival analysis of risk models in female (C) and male (D).

Figure 7

Immune infiltration analysis. (A) In the discovery set, the immune cell infiltration between groups with high and low risk was evaluated based on the ssGSEA algorithm. (B) In the validation set, the immune cell infiltration between high-risk and low-risk groups was analyzed based on the ssGSEA algorithm ns, non significance; *p<0.05; **p<0.01; ***p<0.001.

Figure 8

Construction and evaluation of nomogram. (A) Nomogram was constructed based on the expression values of four genes to predict the OS rate at 1, 3, and 5 years. (B) The calibration curve was used to assess the nomogram.