What if some of the leading organizations in technology, research and medicine worked together to share data and advance lifesaving science?
That vision is starting to take shape, with three pilot awards announced this fall by the Cascadia Data Alliance, launched in 2019 to create a Pacific Northwest data-sharing ecosystem comprising some of the region’s powerhouse institutions, working together across disciplines to accelerate innovation and save lives from cancer and infectious diseases.
The three Cascadia Collaboration Awards to cross-institutional teams at the Alliance’s member organizations — Fred Hutchinson Cancer Research Center, the University of Washington eScience Institute, BC Cancer, the University of British Columbia Data Science Institute and the Knight Cancer Institute at Oregon Health & Science University — represent more than $1.2 million in funding and credits for Microsoft’s Azure cloud computing service.
These projects are made possible thanks to support from Microsoft and institutional support from each participating organization.
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. The three projects tackle a range of questions in the cancer field.
“The Cascadia Data Alliance is committed to transforming cancer care through research powered by technology and data science,” said Dr. Raphael Gottardo, scientific director of the Translational Data Science Integrated Research Center at Fred Hutch and holder of the J. Orin Edson Foundation Endowed Chair. “By connecting experts from across the Pacific Northwest to work on projects focused on immune checkpoint inhibitors, accurately diagnosing distinct ovarian cancer types and single-cell genomic sequencing on breast cancer biopsies, we can make impactful, life-changing and potentially lifesaving discoveries.”
Microsoft is a partner in the Cascadian Data Alliance, aligned with the company’s strategic efforts to improve the health of people around the world by empowering nonprofits, researchers and organizations with artificial intelligence through the AI for Health program.
“Through our AI for Health program, we are supporting organizations tackling some of the world’s biggest challenges,” said John Kahan, vice president, chief data analytics officer and global AI for Health lead at Microsoft. “By enabling data sharing between researchers, we can unearth insights that can further existing and new research. We are proud to help facilitate and accelerate data sharing and analytics for our partners in the Cascadia Data Alliance and look forward to seeing the innovation that comes from the three Cascadia Collaboration Awards.”
A breast tumor’s genetics can change as the cancer progresses throughout treatment. But the changes don’t happen universally throughout all cells in the tumor, leading to distinct populations of cancer cells. If some of the cell populations have mutations that confer drug resistance, this can become a serious problem for the patient. In this new project, the research team will use state-of-the-art genomic methods to determine how tumor cells’ genetic profiles change during treatment and how those changes are linked to the patient’s outcomes.
Computational biologist Dr. Gavin Ha of Fred Hutch is one of the project’s leaders, along with BC Cancer’s Drs. Andrew Roth and Samuel Aparicio, and Dr. Julie Gralow of the University of Washington and Fred Hutch.
“This project brings together computational, experimental and clinical expertise to bridge data science and clinical translation,” Ha said. “Together with our partners at the BC Cancer Research Institute, we hope that this pilot project to study treatment resistance in breast cancer will provide the foundation for future cross-border collaborations to better understand and monitor how cancer patients respond to treatments.”
The project brings together two exciting technologies in cancer research, Ha explained: single-cell genome sequencing, which reveals unprecedented details about the inner workings of individual cells, and liquid biopsies, blood tests to detect and analyze cancer.
“These technologies will allow us to learn about how the DNA mutations [in breast tumors] change over space and time,” Ha said. “These techniques generate large amounts of sequencing data that will require the appropriate computing resources to allow robust analysis and efficient data sharing between institutions. The Azure cloud environment is the perfect platform to address these needs.”
The researchers hope their pilot project produces new opportunities to bring these methods into the clinic to help patients, such as through the discovery of biomarkers in blood or tumor tissue that could help doctors monitor a cancer’s progression.
Drugs called checkpoint inhibitors that release the power of the immune system against tumors are important treatments for many different types of cancer. But the drugs’ effectiveness and side effects vary from patient to patient — and research has shown that the communities of bacteria in a patient’s body, or microbiome, plays a role. But which bacterial species are most important?
A team of scientists hopes to find out. They will create a large, multi-institutional repository of samples of mouth tissues and stool from people who are using checkpoint inhibitors for cancer treatment.
The researchers — led by Fred Hutch’s Dr. David Fredricks, BC Cancer’s Dr. Kerry Savage and OHSU’s Dr. Morgan Hakki — will harness cutting-edge genomic technologies, data analysis tools and cloud computing to reveal the genetic fingerprints of the bacteria in the gut and match them to the outcomes of the patients’ treatment.
“This project is exciting for a number of reasons,” said OHSU’s Hakki, an infectious diseases physician who specializes in infections in patients with cancer. First, it represents a new collaboration that “will provide more power and generalizability to this work than could be achieved by each institution alone and may also lead to additional collaborations in the future.
“Second, this work will hopefully allow us to move beyond simple descriptive taxonomic analysis of the gut microbiome and toward an understanding of the mechanism or mechanisms by which the microbiome influences the outcome of checkpoint inhibitor therapy,” he said.
To do this, they’ll combine new methodologies developed at Fred Hutch with advanced computing.
“The analytic tools developed in the Fredricks Lab at the Hutch, coupled with the power of cloud computing, will help each group analyze, understand and share the data generated in this study,” Hakki said.
The team hopes to use the insights they glean to develop new strategies to improve patient care.
“We hope that this work generates novel data that will help us predict who will have a beneficial response to checkpoint inhibitor therapy, and who will have serious side effects from those therapies. We also hope that, by exploring the mechanistic basis for these outcomes, we can develop ways to intervene to positively affect these outcomes,” Hakki said.
As targeted treatments have become available for specific types of ovarian cancer, it’s become more important than ever that each patient receives an accurate diagnosis of her tumor type. To help make this possible, a research team wants to establish an international network for AI-based, privacy-protected pathology quality assurance. Ovarian cancer will be the team’s proof of concept for a system that could eventually be used for a variety of cancers.
The team is led by Fred Hutch’s Dr. Holly Harris, BC Cancer’s Dr. David Huntsman, OHSU’s Dr. Terry Morgan and Dr. Ivan Beschastnikh, a computer scientist at UBC. It also includes Simon Fraser University's Dr. Tania Bubela and UBC's Dr. Ali Bashashati, who developed the original algorithm the group hopes to generalize.
“A group of us at UBC has been working towards establishing a usable, end-to-end, privacy-enhancing system called LEAP, co-led by [UBC Professor of Medicine] Aline Talhouk and me” — said Beschastnikh — “that can be readily deployed in a health care setting. This project is a proof of concept for our ideas and, if successful, has the potential to impact how data is shared and analyzed in medicine.”
When someone is diagnosed with a cancer, a specialist called a pathologist studies a sample of their tissue, typically looking at the tissues under a microscope, to classify its type based on its biological features. These findings help to guide the treatments the patient receives.
The team plans to use real cancer pathology images from collaborating cancer centers to train an AI with a type of machine learning, or ML, to improve the pathological classification of ovarian cancer while ensuring patient privacy and data security.
“We will also collect privacy and security requirements informed by actual threats to health data,” Beschastnikh said. “This will help us to prepare our platform for implementation by striking the right balance between accuracy of results, privacy and security.”
He explained that their system will use a methodology called federated machine learning, which can train models without moving any real data to ensure it remains private.
“A key concern for modern ML/AI systems is privacy. This is because training high-quality models requires access to a lot of information, and in the medical domain this data is not only regarded as very private, it is also strictly regulated. Another concern is the fact that models trained on data remember aspects of the data and can even be used to reconstruct some of the original input data,” he said. The team’s federated ML methods are designed to avoid those problems, thus preserving patient privacy.
Besides identifying and counteracting privacy threats, the team will develop technical and socioethical guidelines for using the classifier worldwide. The team’s long-term vision is to establish a network of such AI-based systems that could be used by doctors everywhere, thereby ensuring more patients — even those far away from specialized cancer centers — receive accurate diagnoses and thus the most appropriate treatments for their specific cancer types.
“Ethical data sharing is the missing link to enable ML/AI applications in the health care domain. This project is at the intersection of health, machine learning, privacy, security and ethics,” said Beschastinikh.
Are you interested in reprinting or republishing this story? Be our guest! We want to help connect people with the information they need. We just ask that you link back to the original article, preserve the author’s byline and refrain from making edits that alter the original context. Questions? Email us at firstname.lastname@example.org