Small extracellular vesicle miRNAs as biomarkers for predicting antitumor efficacy in lung adenocarcinoma treated with chemotherapy and checkpoint blockade

Abstract

Checkpoint blockade combined with chemotherapy has become an important treatment option for lung cancer patients in clinical settings. However, biomarkers that effectively identify true responders remain lacking. We assessed the potential of plasma small extracellular vesicle (sEV)-derived microRNAs (miRNAs) as biomarkers for predicting and identifying responders to combined immunochemotherapy. A total of 29 patients with lung adenocarcinoma who received pembrolizumab combined with pemetrexed and carboplatin were enrolled. The efficacy evaluation revealed that 24 patients obtained durable clinical benefits from combined immunochemotherapy, and the rest experienced disease progression. Using unsupervised hierarchical clustering, 56 differentially expressed miRNAs (DEMs) were identified between responders and nonresponders. Efficacy prediction models incorporating a combination of sEV miRNAs were established and showed good performance (area under the curve (AUC) > 0.9). In addition, we found that miR-96-5p and miR-6815-5p were notably downregulated in the nonresponder group, while miR-99b-3p, miR-100-5p, miR-193a-5p, and miR-320d were upregulated. These findings were further confirmed by clinical imaging. sEV miRNAs derived from patients with lung cancer showed promise for identifying true responders to combined immunochemotherapy.

Keywords: chemotherapy; immune checkpoint inhibitors; lung cancer. sEV miRNAs predicting immunochemotherapy efficacy; miRNA; sEVs.

Figure 1

Characterization of the subgroups of responder and nonresponder. (A) Overview of the clinical workflow. Patients who signed informed consent were recruited. Blood samples from enrolled patients were collected and used for extraction and isolation of sEVs. After small RNA-sequencing, sEV miRNA was used for bioinformatics analysis. Following a differential analysis, 2-3 combinations of sEV miRNAs for modeling analysis. The sEV miRNA-based model can better predict the people who will benefit from the immune combination chemotherapy regimen. (B) Representative HE and PD-L1 IHC staining images of patients with lung adenocarcinoma. (C) Typical CT imaging features of the same patient before and after treatment. (D, E) Percentage of tumor changes in different groups ****p < 0.0001. (F) Patients diagnosed with nonresponder indicated a short survival.

Figure 2

Representative of morphology and protein expression features of the serum-derived sEVs and sEV DEMs analysis. (A) The diameter distribution of sEVs based on NTA analysis. (B) TEM images of sEVs. Scale bar, 200 nm. (C) Single particle interferometric reflectance imaging analysis for the expression surface markers of serum sEVs. (D) The samples were clearly separated into two groups (responder vs. nonresponder) based on serum sEV DEMs with unsupervised hierarchical clustering analysis.

Figure 3

KEGG/GO analysis of the differentially expressed sEV miRNAs. (A) Bubble plot of enriched GO terms (biological process) of the target genes of the DEMs between responder and nonresponder groups. (B) Bubble plot of enriched GO terms (cellular component and molecular function) of the target genes of the DEMs between responder and nonresponder groups. (C) Bubble plot of enriched KEGG pathways of the target genes of the DEMs between responder and nonresponder groups. (D) Bar plot showing the number of DEM target genes in each of the KEGG pathways (target genes ≥ 35).

Figure 4

The construction of the risk score model for screening the beneficiaries of immunochemotherapy. (A) The best performance of ROC curves with two sEV miRNAs. (B) The best performance of ROC curves with three sEV miRNAs. (C) Hazard ratio calculations with different sEV miRNA combinations. (D-I) Analysis of the expression levels of miR-96-5p, miR-99b-3p, miR-100-5p, miR-193a-5p, miR-320d, and miR-6815-5p.

Figure 5

qRT-PCR verification of selected plasma miRNAs. (A–F) Validation of serum sEV miR-96-5p (A), miR-99b-3p (B), miR-100-5p (C), miR-193a-5p (D), miR-320d (E), and miR-6815-5p (F) expression levels based on qRT-PCR analysis. (G, H) The best performance of ROC curves with two (G) or three (H) sEV miRNAs. *p < 0.05, ***p < 0.001, ns, not significant.

Figure 6

Predicted outcomes based on the risk score of different prediction model. (A, B) Examples of successful predictions of patient efficacy based on the two (A) or three (B) marker qRT-PCR model. (C, D) Examples of CT images and changes in the size of lung nodules (C) and mediastinal lymph nodes (D) after treatment with a combination of immunotherapy and chemotherapy.