DNA methylation-based profiling of bone and soft tissue tumours: a validation study of the 'DKFZ Sarcoma Classifier'

Abstract

Diagnosing bone and soft tissue neoplasms remains challenging because of the large number of subtypes, many of which lack diagnostic biomarkers. DNA methylation profiles have proven to be a reliable basis for the classification of brain tumours and, following this success, a DNA methylation-based sarcoma classification tool from the Deutsches Krebsforschungszentrum (DKFZ) in Heidelberg has been developed. In this study, we assessed the performance of their classifier on DNA methylation profiles of an independent data set of 986 bone and soft tissue tumours and controls. We found that the 'DKFZ Sarcoma Classifier' was able to produce a diagnostic prediction for 55% of the 986 samples, with 83% of these predictions concordant with the histological diagnosis. On limiting the validation to the 820 cases with histological diagnoses for which the DKFZ Classifier was trained, 61% of cases received a prediction, and the histological diagnosis was concordant with the predicted methylation class in 88% of these cases, findings comparable to those reported in the DKFZ Classifier paper. The classifier performed best when diagnosing mesenchymal chondrosarcomas (CHSs, 88% sensitivity), chordomas (85% sensitivity), and fibrous dysplasia (83% sensitivity). Amongst the subtypes least often classified correctly were clear cell CHSs (14% sensitivity), malignant peripheral nerve sheath tumours (27% sensitivity), and pleomorphic liposarcomas (29% sensitivity). The classifier predictions resulted in revision of the histological diagnosis in six of our cases. We observed that, although a higher tumour purity resulted in a greater likelihood of a prediction being made, it did not correlate with classifier accuracy. Our results show that the DKFZ Classifier represents a powerful research tool for exploring the pathogenesis of sarcoma; with refinement, it has the potential to be a valuable diagnostic tool.

Keywords: bone; classifier; methylation profiling; sarcoma; soft tissue.

Figure 1

Overview of performance of the ‘DKFZ Classifier’ on the RNOH validation data set. (A) Overview of all cases in the study. (B) Overview of cases from the core validation cohort. (A and B) Prediction: classifier result with a calibrated score ≥0.9. The calibrated score is the probability for the given methylation class assignment. QC, quality control Concordant: samples predicted by the classifier to the methylation class corresponding with the original or revised diagnosis. Discrepant: where the predicted methylation class did not match the original histological diagnosis, and following review there was either sufficient evidence to reject the predicted result (discrepant with evidence) or the absence of sufficient evidence, such as targeted or RNA sequencing, to completely exclude the prediction (discrepant but inconclusive). ‘Represented samples’: diagnoses where the subtype was represented by a methylation class. ‘Unrepresented samples’: diagnoses not represented in the DKFZ Classifier. (C) The estimated tumour purity is higher in predicted (calibrated score ≥0.9) cases compared to cases not receiving a prediction (p = 0.008, Student's t‐test).

Figure 2

Sankey plot showing the classifier predictions of samples with a subtype not represented in the current version (v12) of the ‘DKFZ sarcoma Classifier’. (A) Case 826, (i) Haematoxylin and eosin (H&E) demonstrating high‐grade spindle cell areas of a malignant GCTB with (ii) focal loss of H3F3A G34W expression on immunohistochemistry. (B) Case 120, H&E showing typical bony trabeculae within a low‐grade parosteal OS. (C) Case 828, H&E showing a spindle cell lesion with scattered squamous islands characteristic of an adamantinoma. (D) Case 311, (i) H&E of high‐grade spindle cell lesion in a patient with a background of breast carcinoma; (ii) the lesion showed widespread CAM5.2 immunopositivity and was subsequently diagnosed as a metastatic focus. FDY, fibrous dysplasia; HG, high grade; IMT, inflammatory myofibroblastic tumour; MIFS, myxoinflammatory fibroblastic sarcoma; NFB(Plex), plexiform neurofibroma; PEComa, perivascular epithelioid cell tumour; PHAT, pleomorphic hyalinising angiectatic tumour; WDLS_DDLS, well‐differentiated liposarcoma/dedifferentiated liposarcoma.