Treatment of evolving cancers will require dynamic decision support

Deep learning identifies heterogeneous subpopulations in breast cancer cell lines

Motivation

Cells exhibit a wide array of morphological features, enabling computer vision methods to identify and track relevant parameters. Morphological analysis has long been implemented to identify specific cell types and cell responses. Here we asked whether morphological features might also be used to classify transcriptomic subpopulations within in vitro cancer cell lines. Identifying cell subpopulations furthers our understanding of morphology as a reflection of underlying cell phenotype and could enable a better understanding of how subsets of cells compete and cooperate in disease progression and treatment.

Results

We demonstrate that cell morphology can reflect underlying transcriptomic differences in vitro using convolutional neural networks. First, we find that changes induced by chemotherapy treatment are highly identifiable in a breast cancer cell line. We then show that the intra cell line subpopulations that comprise breast cancer cell lines under standard growth conditions are also identifiable using cell morphology. We find that cell morphology is influenced by neighborhood effects beyond the cell boundary, and that including image information surrounding the cell can improve model discrimination ability.

Roadmap for the next generation of Children's Oncology Group rhabdomyosarcoma trials

Clinical trials conducted by the Intergroup Rhabdomyosarcoma (RMS) Study Group and the Children's Oncology Group have been pivotal to establishing current standards for diagnosis and therapy for RMS. Recent advancements in understanding the biology and clinical behavior of RMS have led to more nuanced approaches to diagnosis, risk stratification, and treatment. The complexities introduced by these advancements, coupled with the rarity of RMS, pose challenges to conducting large-scale phase 3 clinical trials to evaluate new treatment strategies for RMS. Given these challenges, systematic planning of future clinical trials in RMS is paramount to address pertinent questions regarding the therapeutic efficacy of drugs, biomarkers of response, treatment-related toxicity, and patient quality of life. Herein, the authors outline the proposed strategic approach of the Children's Oncology Group Soft Tissue Sarcoma Committee to the next generation of RMS clinical trials, focusing on five themes: improved novel agent identification and preclinical to clinical translation, more efficient trial development and implementation, expanded opportunities for knowledge generation during trials, therapeutic toxicity reduction and quality of life, and patient engagement.

To modulate or to skip: De-escalating PARP inhibitor maintenance therapy in ovarian cancer using adaptive therapy

Toxicity and emerging drug resistance pose important challenges in poly-adenosine ribose polymerase inhibitor (PARPi) maintenance therapy of ovarian cancer. We propose that adaptive therapy, which dynamically reduces treatment based on the tumor dynamics, might alleviate both issues. Utilizing in vitro time-lapse microscopy and stepwise model selection, we calibrate and validate a differential equation mathematical model, which we leverage to test different plausible adaptive treatment schedules. Our model indicates that adjusting the dosage, rather than skipping treatments, is more effective at reducing drug use while maintaining efficacy due to a delay in cell kill and a diminishing dose-response relationship. In vivo pilot experiments confirm this conclusion. Although our focus is toxicity mitigation, reducing drug use may also delay resistance. This study enhances our understanding of PARPi treatment scheduling and illustrates the first steps in developing adaptive therapies for new treatment settings. A record of this paper's transparent peer review process is included in the supplemental information.

Leveraging Cancer Phenotypic Plasticity for Novel Treatment Strategies

Cancer cells, like all other organisms, are adept at switching their phenotype to adjust to the changes in their environment. Thus, phenotypic plasticity is a quantitative trait that confers a fitness advantage to the cancer cell by altering its phenotype to suit environmental circumstances. Until recently, new traits, especially in cancer, were thought to arise due to genetic factors; however, it is now amply evident that such traits could also emerge non-genetically due to phenotypic plasticity. Furthermore, phenotypic plasticity of cancer cells contributes to phenotypic heterogeneity in the population, which is a major impediment in treating the disease. Finally, plasticity also impacts the group behavior of cancer cells, since competition and cooperation among multiple clonal groups within the population and the interactions they have with the tumor microenvironment also contribute to the evolution of drug resistance. Thus, understanding the mechanisms that cancer cells exploit to tailor their phenotypes at a systems level can aid the development of novel cancer therapeutics and treatment strategies. Here, we present our perspective on a team medicine-based approach to gain a deeper understanding of the phenomenon to develop new therapeutic strategies.

Mathematical Model-Driven Deep Learning Enables Personalized Adaptive Therapy

Standard-of-care treatment regimens have long been designed for maximal cell killing, yet these strategies often fail when applied to metastatic cancers due to the emergence of drug resistance. Adaptive treatment strategies have been developed as an alternative approach, dynamically adjusting treatment to suppress the growth of treatment-resistant populations and thereby delay, or even prevent, tumor progression. Promising clinical results in prostate cancer indicate the potential to optimize adaptive treatment protocols. Here, we applied deep reinforcement learning (DRL) to guide adaptive drug scheduling and demonstrated that these treatment schedules can outperform the current adaptive protocols in a mathematical model calibrated to prostate cancer dynamics, more than doubling the time to progression. The DRL strategies were robust to patient variability, including both tumor dynamics and clinical monitoring schedules. The DRL framework could produce interpretable, adaptive strategies based on a single tumor burden threshold, replicating and informing optimal treatment strategies. The DRL framework had no knowledge of the underlying mathematical tumor model, demonstrating the capability of DRL to help develop treatment strategies in novel or complex settings. Finally, a proposed five-step pathway, which combined mechanistic modeling with the DRL framework and integrated conventional tools to improve interpretability compared with traditional "black-box" DRL models, could allow translation of this approach to the clinic. Overall, the proposed framework generated personalized treatment schedules that consistently outperformed clinical standard-of-care protocols.

SIGNIFICANCE

Generation of interpretable and personalized adaptive treatment schedules using a deep reinforcement framework that interacts with a virtual patient model overcomes the limitations of standardized strategies caused by heterogeneous treatment responses.

Modeling tumors as species-rich ecological communities

Many advanced cancers resist therapeutic intervention. This process is fundamentally related to intra-tumor heterogeneity: multiple cell populations, each with different mutational and phenotypic signatures, coexist within a tumor and its metastatic nodes. Like species in an ecosystem, many cancer cell populations are intertwined in a complex network of ecological interactions. Most mathematical models of tumor ecology, however, cannot account for such phenotypic diversity nor are able to predict its consequences. Here we propose that the Generalized Lotka-Volterra model (GLV), a standard tool to describe complex, species-rich ecological communities, provides a suitable framework to describe the ecology of heterogeneous tumors. We develop a GLV model of tumor growth and discuss how its emerging properties, such as outgrowth and multistability, provide a new understanding of the disease. Additionally, we discuss potential extensions of the model and their application to three active areas of cancer research, namely phenotypic plasticity, the cancer-immune interplay and the resistance of metastatic tumors to treatment. Our work outlines a set of questions and a tentative road map for further research in cancer ecology.

Interplay of mutations, alternate mechanisms, and treatment breaks in leukaemia: Understanding and implications studied with stochastic models

Bcr-Abl1 kinase domain mutations are the most prevalent cause of treatment resistance in chronic myeloid leukaemia (CML). Alternate resistance pathways nevertheless exist, and cell line experiments show certain patterns in the gain, and loss, of some of these alternate adaptations. These adaptations have clinical consequences when the tumour develops mechanisms that are beneficial to its growth under treatment, but slow down its growth when not treated. The results of temporarily halting treatment in CML have not been widely discussed in the clinic and there is no robust theoretical model that could suggest when such a pause in therapy can be tolerated. We constructed a dynamic model of how mechanisms such as Bcr-Abl1 overexpression and drug transporter upregulation evolve to produce resistance in cell lines, and investigate its behaviour subject to different treatment schedules, in particular when the treatment is paused ('drug holiday'). Our study results suggest that the presence of additional resistance mechanisms creates an environment which favours mutations that are either preexisting or occur late during treatment. Importantly, the results suggest the existence of tumour drug addiction, where cancer cells become dependent on the drug for (optimal) survival, which could be exploited through a treatment holiday. All simulation code is available at https://github.com/Sandalmoth/dual-adaptation.

Adaptive Control of Tumor Growth

Cancer treatment optimizations select the most optimum combinations of drugs, sequencing schedules, and appropriate doses that would limit toxicity and yield an improved patient quality of life. However, these optimizations often lack an adequate consideration of cancer's near-infinite potential for evolutionary adaptation to therapeutic interventions. Adapting cancer therapy based on monitored tumor burden and clonal composition is an intuitively sound approach to the treatment of cancer as an inherently complex and adaptive system. The adaptation would be driven by clinical outcome setpoints embodying the aims to thwart therapeutic resistance and maintain a long-term management of the disease or even a cure. However, given the nonlinear, stochastic dynamics of tumor response to therapeutic interventions, adaptive therapeutic strategies may at least need a one-step-ahead prediction of tumor burden to maintain their control over tumor growth dynamics. The article explores the feasibility of adaptive cancer treatment driven by tumor state feedback assuming cell adaptive fitness to be the underlying source of phenotypic plasticity and pathway entropy as a biomarker of tumor growth trajectory. The exploration is undertaken using deterministic and stochastic models of tumor growth dynamics.

Antifragility as a complex system's response to perturbations, volatility, and time

Antifragility characterizes the benefit of a dynamical system derived from the variability in environmental perturbations. Antifragility carries a precise definition that quantifies a system's output response to input variability. Systems may respond poorly to perturbations (fragile) or benefit from perturbations (antifragile). In this manuscript, we review a range of applications of antifragility theory in technical systems (e.g., traffic control, robotics) and natural systems (e.g., cancer therapy, antibiotics). While there is a broad overlap in methods used to quantify and apply antifragility across disciplines, there is a need for precisely defining the scales at which antifragility operates. Thus, we provide a brief general introduction to the properties of antifragility in applied systems and review relevant literature for both natural and technical systems' antifragility. We frame this review within three scales common to technical systems: intrinsic (input-output nonlinearity), inherited (extrinsic environmental signals), and interventional (feedback control), with associated counterparts in biological systems: ecological (homogeneous systems), evolutionary (heterogeneous systems), and interventional (control). We use the common noun in designing systems that exhibit antifragile behavior across scales and guide the reader along the spectrum of fragility-adaptiveness-resilience-robustness-antifragility, the principles behind it, and its practical implications.