The Cascadia Data Alliance is a research collaboration with some of the leading technology, research, and medicine organizations in the Pacific Northwest. Launched in 2019, with funding from Microsoft, members include the Fred Hutchinson Cancer Research Center, BC Cancer, Knight Cancer Institute at Oregon Health & Science University, University of British Columbia Data Science Institute , and University of Washington eScience Institute. The Cascadia Data Alliance seeks to develop a robust regional data sharing ecosystem that has the potential to position the Pacific Northwest as a global leader in data-driven innovation in biomedical research and healthcare.
The first step was the creation of the Cascadia Data Discovery Initiative (CDDI) in 2019. Now in 2020, the Cascadia Data Alliance is delighted to announce funding for three Cascadia Collaboration Awards to cross-institutional teams at the Alliance’s member organizations. The early stage funding aims to promote collaborations that may answer important scientific questions and to develop new ways for using technical solutions and best practices, data and methods standardization, and Azure cloud services that could be broadly applied in future research.
List of Funded Projects:
Pathology AI for a Federated Quality Assurance Program: Ovarian Cancer Pilot
Principal investigators: Drs. David Huntsman [BC Cancer], Holly Harris [Fred Hutch], Terry Morgan [OHSU], and Ivan Beschastnikh [UBC]
As type-specific treatments are being developed for patients with epithelial ovarian cancer, it has become important to accurately diagnose the distinct cancer types. Our vision is to establish an international network for AI-based, privacy-protected pathology quality assurance. As proof of concept, we propose to develop and deploy a machine learning-based ovarian cancer histopathology classifier.
We plan to use privacy-preserving synthetic data generation to train an ovarian cancer classifier, using pathology images collected at our three institutions. We will specifically identify the privacy threats associated with the necessary data-sharing and then develop technical and socioethical guidelines that can be deployed around the world. Our long-term vision is to establish a learning systems network with point-of-care diagnostic applications that could also inform similar advances in other cancers.
Monitoring Breast Cancer: Bringing Single-cell and Liquid Biopsy Analysis to the Cloud
Principal investigators: Drs. Gavin Ha [Fred Hutch], Andrew Roth [UBC], Samuel Aparicio [BC Cancer], and Julie Gralow [UW]
Breast tumor genetics can change during disease progression, leading to distinct tumor cell populations that often contribute to therapeutic resistance. We propose to perform state-of-the-art, single-cell genomic sequencing on breast cancer biopsies and circulating tumor DNA (also known as liquid biopsies) to evaluate genetic changes during the course of a patient's therapy.
We will develop novel methods to integrate these data to monitor dynamic shifts in tumor composition. We also propose to create a harmonized database to store, access, and share abstracted clinical data. We will implement these solutions in the Azure cloud environment to support the cross-institutional study of tumor evolution and clinical outcomes in breast cancer. Our developments will facilitate future cross-institutional collaborations and likely produce significant opportunities for clinical translation, including biomarker discovery for improved disease surveillance.
Functional Capabilities of the Gut Microbiome in Immune Checkpoint Inhibitor-Associated Responses
Principal investigators: Drs. David Fredricks [Fred Hutch], Morgan Hakki [OHSU], and Kerry Savage [BC Cancer]
Immune checkpoint inhibitors, or ICIs, are a powerful new treatment option for a variety of tumors, but efficacy varies between patients and mild to life-threatening side effects can occur. The bacteria that reside in a patient's gut have been shown to impact ICI efficacy and to predict the development of colitis side-effects, but it is not clear specifically which bacteria impact ICI response or toxicity.
We propose to create a large, multi-institution repository of oral and stool samples from cancer patients undergoing ICI therapy. We will then use cutting-edge technology and data analysis tools, and the power of cloud computing, to detail the genetic content of gut-localized bacteria (the microbiome) in individual patients and how they are associated with clinical outcomes. We expect to accomplish fast and accurate data analysis and visualization at each study site, allowing researchers and clinicians to identify potential mechanistic drivers of ICI efficacy and toxicity, and thereby advance promising strategies to improve clinical outcomes for patients.