Adjuvant Wilms' tumour 1-specific dendritic cell immunotherapy complementing conventional therapy for paediatric patients with high-grade glioma and diffuse intrinsic pontine glioma: protocol of a monocentric phase I/II clinical trial in Belgium.

INTRODUCTION: Diffuse intrinsic pontine glioma (DIPG) and paediatric high-grade glioma (pHGG) are aggressive glial tumours, for which conventional treatment modalities fall short. Dendritic cell (DC)-based immunotherapy is being investigated as a promising and safe adjuvant therapy. The Wilms' tumour protein (WT1) is a potent target for this type of antigen-specific immunotherapy and is overexpressed in DIPG and pHGG. Based on this, we designed a non-randomised phase I/II trial, assessing the feasibility and safety of WT1 mRNA-loaded DC (WT1/DC) immunotherapy in combination with conventional treatment in pHGG and DIPG. METHODS AND ANALYSIS: 10 paediatric patients with newly diagnosed or pretreated HGG or DIPG were treated according to the trial protocol. The trial protocol consists of leukapheresis of mononuclear cells, the manufacturing of autologous WT1/DC vaccines and the combination of WT1/DC-vaccine immunotherapy with conventional antiglioma treatment. In newly diagnosed patients, this comprises chemoradiation (oral temozolomide 90 mg/m2 daily+radiotherapy 54 Gy in 1.8 Gy fractions) followed by three induction WT1/DC vaccines (8-10×106 cells/vaccine) given on a weekly basis and a chemoimmunotherapy booster phase consisting of six 28-day cycles of oral temozolomide (150-200 mg/m2 on days 1-5) and a WT1/DC vaccine on day 21. In pretreated patients, the induction and booster phase are combined with best possible antiglioma treatment at hand. Primary objectives are to assess the feasibility of the production of mRNA-electroporated WT1/DC vaccines in this patient population and to assess the safety and feasibility of combining conventional antiglioma treatment with the proposed immunotherapy. Secondary objectives are to investigate in vivo immunogenicity of WT1/DC vaccination and to assess disease-specific and general quality of life. ETHICS AND DISSEMINATION: The ethics committee of the Antwerp University Hospital and the University of Antwerp granted ethics approval. Results of the clinical trial will be shared through publication in a peer-reviewed journal and presentations at conferences. TRIAL REGISTRATION NUMBER: NCT04911621.

Data mining methods for classification of Medium-Chain Acyl-CoA dehydrogenase deficiency (MCADD) using non-derivatized tandem MS neonatal screening data.

Newborn screening programs for severe metabolic disorders using tandem mass spectrometry are widely used. Medium-Chain Acyl-CoA dehydrogenase deficiency (MCADD) is the most prevalent mitochondrial fatty acid oxidation defect (1:15,000 newborns) and it has been proven that early detection of this metabolic disease decreases mortality and improves the outcome. In previous studies, data mining methods on derivatized tandem MS datasets have shown high classification accuracies. However, no machine learning methods currently have been applied to datasets based on non-derivatized screening methods. A dataset with 44,159 blood samples was collected using a non-derivatized screening method as part of a systematic newborn screening by the PCMA screening center (Belgium). Twelve MCADD cases were present in this partially MCADD-enriched dataset. We extended three data mining methods, namely C4.5 decision trees, logistic regression and ridge logistic regression, with a parameter and threshold optimization method and evaluated their applicability as a diagnostic support tool. Within a stratified cross-validation setting, a grid search was performed for each model for a wide range of model parameters, included variables and classification thresholds. The best performing model used ridge logistic regression and achieved a sensitivity of 100%, a specificity of 99.987% and a positive predictive value of 32% (recalibrated for a real population), obtained in a stratified cross-validation setting. These results were further validated on an independent test set. Using a method that combines ridge logistic regression with variable selection and threshold optimization, a significantly improved performance was achieved compared to the current state-of-the-art for derivatized data, while retaining more interpretability and requiring less variables. The results indicate the potential value of data mining methods as a diagnostic support tool.