HLA-DQA1 expression is associated with prognosis and predictable with radiomics in breast cancer

Abstract

Background: High HLA-DQA1 expression is associated with a better prognosis in many cancers. However, the association between HLA-DQA1 expression and prognosis of breast cancer and the noninvasive assessment of HLA-DQA1 expression are still unclear. This study aimed to reveal the association and investigate the potential of radiomics to predict HLA-DQA1 expression in breast cancer.

Methods: In this retrospective study, transcriptome sequencing data, medical imaging data, clinical and follow-up data were downloaded from the TCIA ( https://www.cancerimagingarchive.net/ ) and TCGA ( https://portal.gdc.cancer.gov/ ) databases. The clinical characteristic differences between the high HLA-DQA1 expression group (HHD group) and the low HLA-DQA1 expression group were explored. Gene set enrichment analysis, Kaplan‒Meier survival analysis and Cox regression were performed. Then, 107 dynamic contrast-enhanced magnetic resonance imaging features were extracted, including size, shape and texture. Using recursive feature elimination and gradient boosting machine, a radiomics model was established to predict HLA-DQA1 expression. Receiver operating characteristic (ROC) curves, precision-recall curves, calibration curves, and decision curves were used for model evaluation.

Results: The HHD group had better survival outcomes. The differentially expressed genes in the HHD group were significantly enriched in oxidative phosphorylation (OXPHOS) and estrogen response early and late signalling pathways. The radiomic score (RS) output from the model was associated with HLA-DQA1 expression. The area under the ROC curves (95% CI), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the radiomic model were 0.866 (0.775-0.956), 0.825, 0.939, 0.7, 0.775, and 0.913 in the training set and 0.780 (0.629-0.931), 0.659, 0.81, 0.5, 0.63, and 0.714 in the validation set, respectively, showing a good prediction effect.

Conclusions: High HLA-DQA1 expression is associated with a better prognosis in breast cancer. Quantitative radiomics as a noninvasive imaging biomarker has potential value for predicting HLA-DQA1 expression.

Keywords: Biomarker; Breast cancer; Human leukocyte antigen; Prognosis; Radiomics.

Fig. 1

Bioinformatics analysis results. A Comparison of HLA expression among the HHD, LHD and normal groups. B Kaplan‒Meier curves for patients in the HHD and LHD groups. C Univariate and multivariate Cox analyses of clinicopathological factors and key genes. D Subgroup analyses showed no interaction between the main variable HLA-DQA1 (high vs. low) and each covariate

Fig. 2

Visualization results of the top 20 pathways for the Hallmark and KEGG gene sets by gene set enrichment analysis

Fig. 3

Graphical flowchart of the radiomics analysis. A Imaging data collection and lesion segmentation. B Feature extraction using PyRadiomics and feature selection using recursive feature elimination (RFE). C Modelling by the gradient boosting machine (GBM) algorithm and outputting the radiomics score (RS). D Model evaluation and application using ROC curves, the decision curve and the calibration curve

Fig. 4

Results of the evaluation of the RFE-GBM radiomics model. The AUC of ROC curves and the AUC of precision-recall curve (AUC_PR) of the model were 0.866 and 0.855, respectively, in the training set (A and B) and 0.780 and 0.723, respectively, in the validation set (E and F). The calibration curve and Hosmer‒Lemeshow test (C and G) showed that the prediction probability of high HLA-DQA1 expression was consistent with the true value, and P > 0.05 indicated good consistency. The DCA curve (D and H) showed that the model had clinical practicability within a certain range