Autophagy crosstalk with the immune microenvironment in chronic myeloid leukemia and serves as a biomarker for diagnosis and progression

Abstract

Background: Previous studies have shown that autophagy is closely related to the occurrence, development, and treatment resistance of chronic myeloid leukemia (CML) and has dual roles in promoting cell survival and inducing cell death.

Methods: We analyzed autophagy levels in CML samples via transcriptome data and evaluated the relationships between autophagy and the immune microenvironment, treatment response, and disease progression. A consensus clustering algorithm was used to identify autophagy-related molecular subtypes. The value of autophagy-related genes (ARGs) in diagnosis and treatment evaluation was analyzed and verified by a variety of machine learning algorithms.

Results: Compared with normal samples, CML samples had significantly lower autophagy scores and more downregulated ARGs. The autophagy score was positively correlated with the activity of immune and signal transduction-related pathways and negatively correlated with proliferation-related pathways. Patients with high autophagy scores had a greater proportion of regulatory T-cell infiltration and greater cytokine-cytokine receptor interaction signaling pathway activity, while patients with low autophagy scores had greater γδT cell infiltration and PD-1 expression. Low autophagy scores are also associated with malignant progression and nonresponse to treatment. The immune landscape and chemotherapy sensitivity significantly differed between the two autophagy-related molecular subtypes. Three diagnostic ARGs (FOXO1, TUSC1, and ATG4A) were identified by support vector machine recursive feature elimination, least absolute shrinkage selection operator, and random forest algorithms, and the combined diagnostic efficiency of the three was further improved. The diagnostic value of the three ARGs was verified by an additional validation cohort and our clinical real-world clinical cohort, and they can also be used for the differential diagnosis of CML from other hematological malignancies.

Conclusion: Our study revealed that CML samples exhibit decreased autophagy, and autophagy may induce Tregs to undergo immunosuppression through cytokines. Autophagy-related molecular subtypes are helpful for guiding the clinical treatment of CML. The identification of ARGs by a variety of machine learning algorithms has potential clinical application value.

Keywords: autophagy; chronic myeloid leukemia; diagnosis; immune microenvironment; machine learning; molecular subtypes.

Figure 1

Characteristics of autophagy activity and ARG expression in CML samples. (A) Correlation analysis of the autophagy score and autophagy marker gene expression. Red indicates a positive correlation, blue indicates a negative correlation, and the darker the color is, the stronger the correlation. *P<0.05. (B) Autophagy score distribution in normal (n=74) and CML (n=76) samples. (C, D) Volcano map (C) and heatmap (D) showing the expression characteristics of ARGs. (E, F) Functional annotation (E) and pathway enrichment analysis (F) of DEARGs. The functional enrichment analysis in Figure F highlights the most significant signaling pathways and their corresponding genes, while excluding the visualization of less enriched pathways and their associated genes. BP, biological process; CC, cellular component; MF, molecular function. (*P < 0.05).

Figure 2

Correlations of the autophagy score with the immune microenvironment, treatment response, and disease progression in CML patients. (A) Expression correlation analysis among DEARGs; red indicates the upregulated expression of DEARGs in CML, and blue indicates the downregulated expression. (B) PPI network analysis of the DEARGs. The solid lines usually represent direct physical interactions, such as the binding between proteins. Different colors represent different interaction types or functional categories. The specific color meanings can be referred to the STRING database. (C-F) Correlation analysis of the autophagy score with the tumor marker gene set enrichment score (C), immune cell infiltration (D), Treg infiltration (E), and immune checkpoint expression (F). (G, H) Differences in autophagy scores between patients in the GSE14671 (G) and GSE44589 (H) cohorts who responded to TKI treatment and those who did not. (I) Differences in autophagy scores among normal, CML, and treatment-remission samples in the GSE144119 cohort. (J) Differences in autophagy scores among normal, chronic-phase (CP), and blast-phase (BP) CML samples in our clinical cohort. MMR, major molecular response; NR, no response. P values refer to adjusted P values. (*P < 0.05; ***P < 0.001).

Figure 3

WGCNA revealed potential mechanisms of autophagy regulation. (A) Univariate Cox regression analysis revealed the prognostic features of the DEARGs in the TCGA-AML cohort. (B) Cluster plot of CML samples. (C) Analysis of various soft threshold powers using the scale-free fitting index and average connectivity. The abscissa of both figures represents the value of the soft threshold (power). The ordinate of the left figure is the scale-free fit index, that is, the signed R². The greater the square of the correlation coefficient is, the closer the network is to the distribution of the scale-free network. When the signed R² is greater than 0.9, the network conforms to the distribution of the scale-free network. There is a red horizontal line in the figure, which indicates the best power value when the first signed R2 reaches this red line, which is 12 in this figure. The ordinate of the right graph represents the average connectivity number of all nodes, and a lower ordinate indicates better connectivity. (D) Clustering of different modules. The red line is the cutting height (0.2) to merge the modules with a correlation greater than 0.8. (E) Cluster plots based on different measures (1-TOM). (F) Heatmap of correlations between module genes and autophagy scores. (G) Scatter plot of module genes associated with the autophagy score in gray modules. (H) KEGG enrichment analysis of gray module genes. (I) Genes enriched in the cytokine–cytokine receptor interaction signaling pathway in the gray module. The size of the point represents the correlation of the specified gene with the corresponding phenotype, and the larger the point is, the greater the correlation.

Figure 4

Identification of autophagy-related molecular subtypes and analysis of their differences in biological characteristics and chemotherapy sensitivity. (A) Based on the expression of DEARGs, CML patients were divided into two autophagy-related molecular subtypes by a consensus clustering algorithm. (B) The PCA algorithm was used to analyze the differences in the distribution of patients between subtypes. (C-F) Differences in the expression of DEARGs (C), activity of tumor hallmark gene sets (D), infiltration of 22 immune cells (E), expression of immune checkpoints (F), autophagy scores (G), and therapeutic sensitivity to four TKIs (H) between the two MSs. (ns: P > 0.05; *P < 0.05; **P < 0.01; ***P < 0.001).

Figure 5

Identification of diagnostic ARGs. (A, B) Diagnostic ARGs were identified by the LASSO regression algorithm. The logarithm of the best tuning parameter (log lambda) was selected by cross-validation in the LASSO regression analysis, corresponding to the point with the smallest binomial deviance (A). The model genes with nonzero coefficients and their corresponding coefficients were screened based on the best log lambda value (B). (C, D) Diagnostic ARGs were identified by the RF algorithm. The red line represents the error in the CML group, the green line represents the error in the normal group, and the black line represents the total sample error. Analysis was performed based on minimum error points corresponding to 410 optimal random forest trees (C). MeanDecreaseGini shows the rank of genes according to their relative importance, and genes with MeanDecreaseGini scores greater than 2 were further screened (D). (E) The SVM-RFE algorithm was used to calculate the accuracy of fivefold cross-validation for different gene combinations, where the highest accuracy was achieved when the number of genes was 4. (F) Venn diagram of variables identified by the LASSO, RF, and SVM-RFE algorithms.

Figure 6

Analysis of the diagnostic value of the diagnostic ARGs. (A) Differences in the expression of the three diagnostic ARGs between CML samples and normal samples in the GSE13159 cohort. (B) Differences in the expression of the three diagnostic ARGs between autophagy-related molecular subtypes. (C) Differences in the risk score between CML samples and normal samples in the GSE13159 cohort. (D-G) ROC curve analysis was used to evaluate the diagnostic value of the three ARGs and the risk score in the GSE13159 cohort. (ns: P > 0.05; *P < 0.05; **P < 0.01; ***P < 0.001).

Figure 7

Validation of the diagnostic value of the diagnostic ARGs. (A, D) Differences in the expression of the three diagnostic ARGs between CML samples and normal samples in the GSE144119 cohort (A) and our clinical cohort (D). (B, E) Differences in the risk score between CML samples and normal samples in the GSE144119 cohort (B) and our clinical cohort (E). (C, F) ROC curve analysis was used to evaluate the diagnostic value of the three ARGs and the risk score in the GSE144119 cohort (C) and our clinical cohort (F). (ns: P > 0.05; **P < 0.01; ***P < 0.001).

Figure 8

Differential diagnostic value of the three ARGs in CML and other hematological malignancies. (A) The t-SNE plot shows the clustering characteristics of CML, AML, CLL, ALL, MDS and normal samples based on the expression of three diagnostic ARGs (FOXO1, TUSC1, ATG4A). The horizontal axis (t-SNE 1) and the vertical axis (t-SNE 2) are the principal components after dimensionality reduction, with no unit dimension, used to visualize the local structure of high-dimensional data. Different colored dots represent the corresponding samples. (B) Differences in the expression of three diagnostic ARGs among CML, AML, CLL, ALL, MDS, and normal samples. (C) Differences in risk scores among CML, AML, CLL, ALL, MDS, and normal samples. (D) ROC curve analysis of risk scores in patients with CML and other hematological malignancies. (E) Regulatory network of miRNAs and the three diagnostic ARGs; red indicates that miRNA expression is upregulated in CML samples, and green indicates that miRNA expression is downregulated. (***P < 0.001).