Identification and Construction of a Disulfidptosis-Mediated Diagnostic Model and Associated Immune Microenvironment of Osteoarthritis from the Perspective of PPPM

Abstract

Background: Osteoarthritis (OA) is a major cause of human disability. Despite receiving treatment, patients with the middle and late stage of OA have poor survival outcomes. Therefore, within the framework of predictive, preventive, and personalized medicine (PPPM/3PM), early personalized diagnosis of OA is particularly prominent. PPPM aims to accurately identify disease by integrating multiple omic techniques; however, the efficiency of currently available methods and biomarkers in predicting and diagnosing OA should be improved. Disulfidptosis, a novel programmed cell death mechanism and appeared in particular metabolic status, plays a mysterious characteristic in the occurrence and development of OA, which warrants further investigation.

Methods: In this study, we integrated three public datasets from the Gene Expression Omnibus (GEO) database, including 26 OA samples and 20 normal samples. Via a series of bioinformatic analysis and machine learning, we identified the diagnostic biomarkers and several subtypes of OA. Moreover, the expression of these biomarkers were verified in our in-house cohort and the single cell dataset.

Results: Three significant regulators of disulfidptosis (NCKAP1, OXSM, and SLC3A2) were identified through differential expression analysis and machine learning. And a nomogram constructed based on these three regulators exhibited ideal efficiency in predicting early- and late-stage OA. Furthermore, based on the expression of three regulators, we identified two disulfidptosis-related subtypes of OA with different infiltration of immune cells and personalized expression level of immune checkpoints. Notably, the expression of the three regulators was demonstrated in a single-cell RNA profile and verified in the synovial tissue in our in-house cohort including 6 OA patients and 6 normal people. Finally, an efficient disulfidptosis-mediated diagnostic model was constructed for OA, with the AUC value of 97.6923% in the training set and 93.3333% and 100% in two validation sets.

Conclusion: Overall, with regard to PPPM, this study provided novel insights into the role of disulfidptosis regulators in the personalized diagnosis and treatment of OA.

Keywords: diagnostic model; disulfidptosis; immune microenvironment; osteoarthritis; perspective of predictive, preventive and personalized medicine.

Figure 1

General status of disulfidptosis in OA and step-by-step protocol of this study.

Figure 2

Identification of significant disulfidptosis regulators in OA. (A) Heat map demonstrating the correlation among 9 disulfidptosis regulators in OA samples. (B) Co-expression network of the 9 disulfidptosis regulators and their potential biological functions. (C) Volcano map demonstrating DEGs with p-value of <0.05 between NM and OA samples. (D) The intersection between the DEGs and the 9 disulfidptosis regulators. (E, F) Results of Lasso-Cox regression analysis. (G, H) Results of RF (screening threshold: importance > 1). (I) Intersection between the results of Lasso-Cox regression and RF. (J-l) ROC curves of (J) NCKAP1, (K) OXSM and (l) SLC3A2. (M) Nomogram demonstrating the efficacy of the three regulators in distinguishing early- and end-stage patients with OA. (N) Calibration curve of the nomogram (*, p < 0.05; **, p < 0.01; ***, p < 0.001).

Figure 3

Identification of two disulfidptosis-related subtypes of OA and establishment of a disulfidptosis scoring model for OA. (A) A cumulative distribution curve was plotted to determine the most appropriate K value. (B) The area under the cumulative distribution curve in each K value. (C) Heat map of two disulfidptosis-related subtypes of OA. (D) UMAP plot of the two subtypes. (E) Heat map demonstrating the normalised expression level in the two subtypes. (F) Differences in the disulfidptosis score between the two subtypes. (G–I) Differential expression of (G) NCKAP1, (H) OXSM and (I) SLC3A2 between the two subtypes (*, p < 0.05; ****, p < 0.0001).

Figure 4

Identification of significant diagnostic genes in the two OA subtypes. (A, B) Volcano map of DEGs between (A) the two disulfidptosis-related subtypes of OA and (B) between the NM and OA groups. (C) Venn diagram demonstrating the intersection between the two DEG sets. (D, E) Selection of the soft-thresholding power for WGCNA. (F) Division of modules to identify genes correlated with OA. (G) Venn diagram demonstrating the intersection among the overlapped DEGs, genes in the negatively correlated modules and genes in the positively correlated modules.

Figure 5

Construction and verification of the disulfidptosis-related diagnostic model of OA. (A) PPI network of significant genes in the two OA subtypes. (B) UpSet plot demonstrating the overlapped top 15 genes identified using seven algorithms of cyttoHubba. (C, D) Results of SVM-RFE revealed 9 significant genes. (E, F) Results of RF revealed 7 significant genes. (G, H) Results of Lasso-Cox regression analysis revealed 5 significant genes. (I) Venn diagram demonstrating the intersection of the results of the abovementioned three machine learning methods. (J) Calibration curve of logistic analysis to ensure the accuracy of the diagnostic model. (K, M, O) Differences in the diagnostic score between the NM and OA groups in the (K) training set, (M) GSE12021 dataset and (O) GSE1919 dataset. (L, N, P) ROC curve of the diagnostic score in the (L) training set, (N) GSE12021 dataset and (P) GSE1919 dataset (**, p < 0.01; ****, p < 0.0001).

Figure 6

Investigation of the immune microenvironment and expression of ICKs in the two disulfidptosis-related subtypes of OA. (A) Differences in the ESTIMATE score between the two subtypes. (B) Stacked column chart demonstrating the infiltration of 28 types of immune cells in each sample of the training set. (C, D) Differences in the infiltration scores of each immune cell between (c) the NM and OA groups and (D) between the two subtypes of OA. (E–G) Lollipop chart demonstrating the correlation between the infiltration scores and the expression of (E) NCKAP1, (F) OXSM and (G) SLC3A2 in the C1 subtype and their corresponding p-values. (H–J) Lollipop chart demonstrating the correlation between the infiltration scores and the expression of (H) NCKAP1, (I) OXSM and (J) SLC3A2 in the C2 subtype and their corresponding p-values. (k–x) Differences in the expression of (K) CD2, (L) CD47, (M) CD96, (N) CD200, (O) CD226, (P) CTLA4, (Q) HHLA2, (R) KIR3DL1, (S) KLRD1, (T) LAG3, (U) PDCD1, (V) PDCD1LG2, (W) SIGIRR and (X) SIGLEC15 between the two subtypes of OA. (Y) Potential relationship among disulfidptosis, immune microenvironment and ICKs in OA. (-, p ≥ 0.05; *, p < 0.05; **, p < 0.01; ***, p < 0.001; ****, p < 0.0001).

Figure 7

Expression of disulfidptosis regulators analysed via single-cell RNA sequencing. (A) General distribution of each cell in the NM, OA and RA groups. (B–D) Expression of (B) NCKAP1, (C) OXSM and (D) SLC3A2 as analysed via single-cell RNA-seq. (E–G) Expression of (E) NCKAP1, (F) OXSM and (G) SLC3A2 at the transcriptomic level in the NM, OA and RA groups. (H-J) Expression of (H) NCKAP1, (I) OXSM and (J) SLC3A2 at the mRNA level in the NM and OA patients in our in-house cohort via RT-qPCR. (-, p ≥ 0.05; *, p < 0.05; **, p < 0.01).