A transatlantic perspective on the integration of immuno-oncology prognostic and predictive biomarkers in innovative clinical trial design

Morfouace, Marie; Hewitt, Stephen M.; Salgado, Roberto; Hartmann, Katherine; Litière, Saskia; Tejpar, Sabine; Golfinopoulos, Vassilis; Lively, Tracy; Thurin, Magdalena; Conley, Barbara A.; Lacombe, Denis

doi:10.1016/j.semcancer.2018.01.003

Cited by 4 publications

(2 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed previously, the modern immuno-oncology scene is dominated by ICB, whereby our understanding of immune checkpoints has led to the commercial release of various cytotoxic T-lymphocyte-associated protein 4 and programmed death-1 blockers such as ipilimumab, pembrolizumab and nivolumab[ 32 , 33 ]. Despite the evident focus of research on ICB and the resounding progress made over the past decade, only a small fraction (approximately 20%) of patients enjoy long-term benefits from these therapies[ 34 ]. This could, in part or in full, be attributed to the previously discussed resistance mechanisms of malignancies against ICB.…”

Section: Exploitation Of the Innate Immune System: A Gap In The Immunmentioning

confidence: 99%

Why natural killer cells in triple negative breast cancer?

Abdel-Latif¹,

Youness²

2020

WJCO

View full text Add to dashboard Cite

The triple-negative subtype of breast cancer (TNBC) has the bleakest prognosis, owing to its lack of either hormone receptor as well as human epidermal growth factor receptor 2. Henceforth, immunotherapy has emerged as the front-runner for TNBC treatment, which avoids potentially damaging chemotherapeutics. However, despite its documented association with aggressive side effects and developed resistance, immune checkpoint blockade continues to dominate the TNBC immunotherapy scene. These immune checkpoint blockade drawbacks necessitate the exploration of other immunotherapeutic methods that would expand options for TNBC patients. One such method is the exploitation and recruitment of natural killer cells, which by harnessing the innate rather than adaptive immune system could potentially circumvent the downsides of immune checkpoint blockade. In this review, the authors will elucidate the advantageousness of natural killer cell-based immuno-oncology in TNBC as well as demonstrate the need to more extensively research such therapies in the future.

show abstract

Section: Exploitation Of the Innate Immune System: A Gap In The Immunmentioning

confidence: 99%

Why natural killer cells in triple negative breast cancer?

Abdel-Latif¹,

Youness²

2020

WJCO

View full text Add to dashboard Cite

show abstract

“…Local health care sites are frequently poorly resourced; efficient computation of TIL data is essential for adoption. Cancer working groups focused on TILs are notably international [26], [27]; the need for inexpensive locally produced TIL predictions and resource constraints are similarly crucial in international settings.…”

Section: B Cancer Research Applicationmentioning

confidence: 99%

Exascale Deep Learning to Accelerate Cancer Research

Patton

Abousamra

Samaras

et al. 2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Deep learning, through the use of neural networks, has demonstrated remarkable ability to automate many routine tasks when presented with sufficient data for training. The neural network architecture (e.g. number of layers, types of layers, connections between layers, etc.) plays a critical role in determining what, if anything, the neural network is able to learn from the training data. The trend for neural network architectures, especially those trained on ImageNet, has been to grow ever deeper and more complex. The result has been ever increasing accuracy on benchmark datasets with the cost of increased computational demands. In this paper we demonstrate that neural network architectures can be automatically generated, tailored for a specific application, with dual objectives: accuracy of prediction and speed of prediction. Using MENNDLan HPC-enabled software stack for neural architecture search-we generate a neural network with comparable accuracy to state-ofthe-art networks on a cancer pathology dataset that is also 16× faster at inference. The speedup in inference is necessary because of the volume and velocity of cancer pathology data; specifically, the previous state-of-the-art networks are too slow for individual researchers without access to HPC systems to keep pace with the rate of data generation. Our new model enables researchers with modest computational resources to analyze newly generated data faster than it is collected.

show abstract

Systemic Therapy of Advanced Liver Cancer

Ocker

2020

Liver Diseases

View full text Add to dashboard Cite

A transatlantic perspective on the integration of immuno-oncology prognostic and predictive biomarkers in innovative clinical trial design

Cited by 4 publications

References 74 publications

Why natural killer cells in triple negative breast cancer?

Why natural killer cells in triple negative breast cancer?

Exascale Deep Learning to Accelerate Cancer Research

Systemic Therapy of Advanced Liver Cancer

Contact Info

Product

Resources

About