Halkola, A. S. | Search bioRxiv

bioRxiv2022

A Community Challenge to Predict Clinical Outcomes After Immune Checkpoint Blockade in Non-Small Cell Lung Cancer

PurposePredictive biomarkers of immune checkpoint inhibitors (ICIs) efficacy are currently lacking for non-small cell lung cancer (NSCLC). Here, we describe the results from the Anti-PD-1 Response Prediction DREAM Challenge, a crowdsourced initiative that enabled the assessment of predictive models by using data from two randomized controlled clinical trials (RCTs) of ICIs in first-line metastatic NSCLC. MethodsParticipants developed and trained models using public resources. These were evaluated with data from the CheckMate 026 trial (NCT02041533), according to the model-to-data paradigm to maintain patient confidentiality. The generalizability of the models with the best predictive performance was assessed using data from the CheckMate 227 trial (NCT02477826). Both trials were phase III RCTs with a chemotherapy control arm, which supported the differentiation between predictive and prognostic models. Isolated model containers were evaluated using a bespoke strategy that considered the challenges of handling transcriptome data from clinical trials. ResultsA total of 59 teams participated, with 417 models submitted. Multiple predictive models, as opposed to a prognostic model, were generated for predicting overall survival, progression-free survival, and progressive disease status with ICIs. Variables within the models submitted by participants included tumor mutational burden (TMB), programmed death ligand 1 (PD-L1) expression, and gene-expression-based signatures. The bestperforming models showed improved predictive power over reference variables, including TMB or PD-L1. ConclusionThis DREAM Challenge is the first successful attempt to use protected phase III clinical data for a crowdsourced effort towards generating predictive models for ICIs clinical outcomes and could serve as a blueprint for similar efforts in other tumor types and disease states, setting a benchmark for future studies aiming to identify biomarkers predictive of ICIs efficacy. Context summaryO_ST_ABSKey objectiveC_ST_ABSNot all patients with non-small cell lung cancer (NSCLC) eligible for immune checkpoint inhibitor (ICIs) respond to treatment, but accurate predictive biomarkers of ICIs clinical outcomes are currently lacking. This crowdsourced initiative enabled the robust assessment of predictive models using data from two randomized clinical trials of first-line ICI in metastatic NSCLC. Knowledge generatedModels submitted indicate that a combination of programmed death ligand 1 (PD-L1), tumor mutational burden (TMB), and immune gene signatures might be able to identify patients more likely to respond to ICIs. TMB and PD-L1 seemed important to predict progression-free survival and overall survival. Mechanisms including apoptosis, T-cell crosstalk, and adaptive immune resistance appeared essential to predict response. Relevance

cancer biology↗

bioRxiv2022

OSCAR: Optimal subset cardinality regression using the L0-pseudonorm with applications to prognostic modelling of prostate cancer

In many real-world applications, such as those based on patient electronic health records, prognostic prediction of patient survival is based on heterogeneous sets of clinical laboratory measurements. To address the trade-off between the predictive accuracy of a prognostic model and the costs related to its clinical implementation, we propose an optimized L0-pseudonorm approach to learn sparse solutions in multivariable regression. The model sparsity is maintained by restricting the number of nonzero coefficients in the model with a cardinality constraint, which makes the optimization problem NP-hard. In addition, we generalize the cardinality constraint for grouped feature selection, hence making it possible to identify key sets of predictors that may be measured together in a kit in clinical practice. We demonstrate the operation of our cardinality constraint-based feature subset selection method, named OSCAR, in the context of prognostic modelling of prostate cancer, where it enabled one to determine the key explanatory predictors at different levels of model sparsity, and to explore how the model sparsity affects the model accuracy and implementation cost. Author summaryFeature selection has become a crucial part in building biomedical models, due to the abundance of available predictors in many applications, yet there remains an uncertainty of their importance and generalization ability. Regularized regression methods have become popular approaches to tackle this challenge by balancing the model goodness-of-fit against the increasing complexity of the model in terms of coefficients that deviate from zero. Regularization norms are pivotal in formulating the model complexity, and currently L1 (LASSO), L2 (Ridge Regression) and their hybrid (Elastic Net) norms dominate the field. In this paper, we present a novel methodology using the L0-pseudonorm, also known as the best subset selection, which has largely gone overlooked due to its challenging discrete nature. Our methodology makes use of a continuous transformation of the discrete optimization problem, and provides effective solvers implemented in a user friendly R software package. We exemplify the use of oscar-package in the context of prostate cancer prognostic prediction using both real-world hospital registry and clinical cohort data. By benchmarking the methodology against related regularization methods, we illustrate the advantages of the L0-pseudonorm for better clinical applicability and selection of grouped features.

bioinformatics↗