BackgroundGlioblastoma (GBM) presents a significant clinical challenge due to its aggressive nature and extensive heterogeneity. Tumour purity, the proportion of malignant cells within a tumour, is an important covariate for understanding the disease, having direct clinical relevance or obscuring signal of the malignant portion in molecular analyses of bulk samples. However, current methods for estimating tumour purity are non-specific, unreliable or technically demanding. Therefore, we aimed to build a reliable and accessible purity estimator for GBM.MethodsWe developed GBMPurity, a deep learning model specifically designed to estimate the purity of IDH-wildtype primary GBM from bulk RNA-seq data. The model was trained using simulated pseudobulk tumours of known purity from labelled single-cell data acquired from the GBmap resource. The performance of GBMPurity was evaluated and compared to several existing tools using independent datasets.ResultsGBMPurity outperformed existing tools, achieving a mean absolute error of 0.15 and a concordance correlation coefficient of 0.88 on validation datasets. We demonstrate the utility of GBMPurity through inference on bulk RNA-seq samples and reveal reduced purity of the Proneural molecular subtype attributed to increased presence of healthy brain cells.ConclusionsGBMPurity provides a reliable and accessible tool for estimating tumour purity from bulk RNA-seq data, enhancing the interpretation of bulk RNA-seq data and offering valuable insights into GBM biology. To facilitate the use of this tool by the wider research community, GBMPurity is available as a web-based tool at:https://gbmdeconvoluter.leeds.ac.uk/.Key PointsGBMPurity is a glioblastoma-specific purity estimation tool.The model accurately estimates the purity of bulk RNA-seq data, outperforming existing tools.The model is available online at:https://gbmdeconvoluter.leeds.ac.uk/.Importance of the StudyGlioblastoma (GBM) is a deadly brain tumour with a dismal prognosis. Research on this disease has lagged compared to other cancers, underscoring the need to streamline investigations. The cellular composition of the GBM tumour microenvironment significantly influences therapy resistance, prognosis, and the molecular state of neoplastic cells. Consequently, tumour purity (the proportion of malignant cells within a tumour) is a critical variable for understanding and contextualizing molecular and clinical analyses. We present GBMPurity (https://gbmdeconvoluter.leeds.ac.uk/), an accessible, GBM-specific tool that accurately predicts sample purity from bulk RNA-seq data. This tool can be used by the wider research community to support the interpretation of bulk omics data and accelerate the identification of more effective therapeutic strategies for treating GBM.
