Systems biology informed neural networks (SBINN) predict response and novel combinations for PD-1 checkpoint blockade

Abstract

Anti-PD-1 immunotherapy has recently shown tremendous success for the treatment of several aggressive cancers. However, variability and unpredictability in treatment outcome have been observed, and are thought to be driven by patient-specific biology and interactions of the patient’s immune system with the tumor. Here we develop an integrative systems biology and machine learning approach, built around clinical data, to predict patient response to anti-PD-1 immunotherapy and to improve the response rate. Using this approach, we determine biomarkers of patient response and identify potential mechanisms of drug resistance. We develop systems biology informed neural networks (SBINN) to calculate patient-specific kinetic parameter values and to predict clinical outcome. We show how transfer learning can be leveraged with simulated clinical data to significantly improve the response prediction accuracy of the SBINN. Further, we identify novel drug combinations and optimize the treatment protocol for triple combination therapy consisting of IL-6 inhibition, recombinant IL-12, and anti-PD-1 immunotherapy in order to maximize patient response. We also find unexpected differences in protein expression levels between response phenotypes which complement recent clinical findings. Our approach has the potential to aid in the development of targeted experiments for patient drug screening as well as identify novel therapeutic targets.

An integrative systems biology approach to overcome venetoclax resistance in acute myeloid leukemia

“…Ref. [ 166 ], offering the potential to significantly improve the predictive power of these algorithms for real patient data. Finally, while this study was focused on acquired resistance to venetoclax, implementing cellular heterogeneity into the model to include a population of cells that are sensitive and a population of cells that are resistant to venetoclax could give insight into how to overcome intrinsic drug resistance in AML.…”

A review of mechanistic learning in mathematical oncology

“…Another example is given by Przedborski et al. ( 115 ) who used biology-informed neural networks to predict patient response to anti-PD-1 immunotherapy and present biomarkers and possible mechanisms of drug resistance. Their model offers insights for optimizing treatment protocols and discovering novel therapeutic targets.…”

Functional genomics of complex cancer genomes

“…More recently, systems biology has been successfully integrated with machine learning approaches to predict precise therapeutic response dependencies. Przedborski et al described a multi-disciplinary approach combining a well characterized systems biology model of anti-PD-1 immunotherapy to generate simulated clinical trials and a neural network-based classification algorithm that classifies patients based on their therapeutic response 23 . This combined approach allowed to identify biomarkers of anti-PD-1 immunotherapy response in real patients and to speculate on potential mechanisms of drug resistance.…”