Development of a prognostic model for NSCLC based on differential genes in tumour stem cells

Abstract

Non-small cell lung cancer (NSCLC) constitutes a significant portion of lung cancers and cytotoxic drugs (e.g. cisplatin) are currently the first-line treatment. However, NSCLC has developed resistance to this drug, which limits the therapeutic effect and thus affects prognosis. NSCLC sc-RNA-seq data were downloaded from the GEO database and Ku Leuven Laboratory for Functional Epigenetics, and bulk RNA-seq data were obtained from the TCGA database. The "Seurat" package was employed for scRNA-seq data processing, and the uniform manifold approximation and projection (UMAP) were applied for downscaling and cluster identification. Use the FindAllMarkers function to find differential genes (DEGs) for tumor stem cells. Then, we performed univariate regression analyses on the DEGs to identify potential prognostic genes. We created a machine learning framework based on potential prognostic genes, which combines 10 machine learning methods and their 101 combinations to get the optimal prognostic risk model. The model was evaluated in the training set and validation set. A nomogram was developed to provide physicians with a quantitative tool for prognosis prediction. Finally, we evaluated the expression and functionality of SLC2A1. We discovered 22 cell clusters containing 218379 cells by examining single-cell RNA sequencing datasets (GSE148071, KU_lom, GSE131907, GSE136246, GSE127465). Tumour cells were isolated for subpopulation analysis and 162 differential genes from SOX2_cancer were obtained. After univariate Cox analysis, we found 23 genes with prognostic potential prognostic value and utilized them to develop 101‑combination machine learning computational framework. We eventually picked the best performing 'StepCox[both] + RSF', which includes 8 genes. The model has a relatively high prediction accuracy in both TCGA and GEO datasets. In in vitro investigations, targeted suppression of the SLC2A1 gene resulted in significant reductions in proliferation, invasion and migration in A549 cells. In addition, a significant reduction in cisplatin resistance was seen in A549/DDP cells. The outcomes demonstrated the precision and credibility of the prognostic model for NSCLC, highlighting its potential significance in the treatment and prognosis of individuals affected by this disease. SLC2A1 may become a promising prognostic marker and a potential therapeutic target, offering valuable insights to inform clinical treatment decisions.

Keywords: Machine learning; NSCLC; Prognosis; Single cell.

Fig. 1

Flowchart.

Fig. 2

(a-c) Clustering annotation and cell type identification by UMAP. (d-e) Secondary clustering and annotation of tumour cells. (f) stemness score of tumour cells.

Fig. 3

C-index of each model on all validation datasets. (a) A total of 101 predictive models were built by the tenfold cross-validation framework and the C-index of each model was further calculated on all validation datasets. (b) Kaplan-Meier and ROC curves for TCGA-LUAD. (c-d) Kaplan-Meier and ROC curves for GSE29016 and GSE13213. (e) Nomograms constructed on the basis of clinical characteristics including age, graders and stages.

Fig. 4

(a-b) Waterfall plot of gene mutations. (c) Tumour Mutation Burden (TMB) risk.

Fig. 5

(a-b) Heat map of immune cell infiltration. (c) Distribution and correlation of tumour infiltrating immune cells in LUAD and LUSC.

Fig. 6

GSEA.

Fig. 7

Seven key cellular interactions within tumour cells. (a) Efferent and afferent signalling patterns of tumour cells. (b) Signals from various types of tumour cells. (c) The number and strength of 7 types of cell interactions.

Fig. 8

Drug sensitivity analysis.

Fig. 9

(a-b) qPCR and WB showing SLC2A1 expression in A549/DDP cell line compared to A549 cell line.

Fig. 10

(a) Proliferation of CCK-8. (b) Transwell assay. (c) Expression of SLC2A1 in Transwell assay.

Fig. 11

(a) Apoptosis assay. (b) Cytotoxicity of CCK-8.