Abstract 4102: Vulnerability signature guided glioblastoma umbrella trial
Michael E. Berens, Sen Peng, Matthew Lee, Nanyun Tang, Manmeet Singh Ahluwalia, Ekokobe Fonkem, Karen E. Fink, Jeffrey J. Raizer, Christopher James Walker, Harshil Dhruv · Cancer Research · 2022
Abstract Glioblastoma is characterized by intra- and inter-tumoral heterogeneity. A glioblastoma umbrella signature trial (GUST) posits multiple investigational treatment arms based on corresponding biomarker signatures. One contingency for an efficient umbrella trial is a suite of orthogonal signatures to classify patients into the likely most-beneficial arm. Assigning optimal thresholds of vulnerability signatures to classify patients as “most-likely responders” for each specific treatment arm is a crucial task. We utilized relative expression orderings (REO), entropy-regularized logistic regression (ERLR) and random forest classifier, to predict vulnerability classification. By applying semi-supervised algorithms to the TCGA GBM cohort, we were able to transform the samples with the highest certainty of predicted response into a self-labeled dataset and thus augment the training data. In this case, we developed a predictive model with a larger sample size and potentially better performance. Our GUST design currently includes four treatment arms for GBM patients: Arsenic Trioxide, Methoxyamine, Selinexor and Pevonedistat. Each treatment arm manifests its own signature developed by the customized machine learning pipelines based on selected gene mutation status, whole transcriptome data and real world outcomes from clinical trials. In order to increase the robustness and scalability, we also developed a multi-class/label classification ensemble model that’s capable of predicting a probability of “fitness” of each novel therapeutic agent for each patient. Such a multi-class model would also enable us to rank each arm and provide sequential treatment planning. By expansion to four independent treatment arms within a single umbrella trial, a “mock” stratification of TCGA GBM patients labeled 56% of all cases into at least one “high likelihood of response” arm. Predicted vulnerability using genomic data from preclinical PDX models correctly placed 4 out of 6 models into the “responder” group. Our utilization of multiple vulnerability signatures in a GUST trial demonstrates how a precision medicine model can support an efficient clinical trial for heterogeneous diseases such as GBM. Citation Format: Michael E. Berens, Sen Peng, Matthew Lee, Nanyun Tang, Manmeet S. Ahluwalia, Ekokobe Fonkem, Karen L. Fink, Jeffrey Raizer, Christopher Walker, Harshil Dhruv. Vulnerability signature guided glioblastoma umbrella trial [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4102.