close

Join our Mailing List

Receive the latest news, event invites, funding opportunities and more from the Ontario Institute for Cancer Research.

OICR welcomes new investigator, Dr. Parisa Shooshtari

Dr. Parisa Shooshtari, OICR Investigator and Assistant Professor in the Schulich School of Medicine and Dentistry at Western University
Dr. Parisa Shooshtari, OICR Investigator and Assistant Professor in the Schulich School of Medicine and Dentistry at Western University.

OICR is proud to welcome Dr. Parisa Shooshtari as an OICR Investigator.

Shooshtari specializes in developing computational, statistical and machine learning methods to understand the biological mechanisms underlying complex diseases, like cancer and autoimmune conditions. She is interested in uncovering how genes are dysregulated in complex diseases by integrating multiple data types and applying machine learning methods to analyze single-sell sequencing data.

Of her many achievements, Shooshtari developed a computational pipeline to uniformly process more than 800 epigenomic data samples from different international consortia. She then built and led a team that developed a web-interface and an interactive genome-browser to make the database publicly available to download and explore.

Shooshtari joins the OICR community with research experience from Yale University and the Broad Institute of MIT and Harvard. She also served as a Research Associate with the Centre for Computational Medicine at the Hospital for Sick Children (SickKids).

Shooshtari recently became an Assistant Professor in the Schulich School of Medicine and Dentistry at Western University, where she officially began her career as an independent researcher. Here, Shooshtari discusses her commitment to collaboration and her transition to professorship.

Your work spans multiple disease areas from autoimmune diseases to cancer, what do these diseases have in common? Is there a specific disease that you’re more interested in?

My work focuses on complex diseases, where instead of one gene causing the disease, there are sometimes tens or hundreds of genes working together to give rise to an ailment.

When it comes to complex diseases, we also know that there are multiple factors that we need to consider, including genetics, epigenetics and environmental factors. We live in an era where we have rich datasets with many different types of data. Each of these data types sheds light upon a different aspect of the disease mechanism, but we need to integrate these data types to gain a comprehensive understanding of how a complex disease works.

I develop computational methods for integrative analysis, so complex diseases are definitely the most interesting to me. I feel lucky to be a researcher at this time when I can help bring these data types together to understand mechanisms of diseases, which in turn will help inform treatment selection or help find new therapeutic strategies.

I am interested in applying our data integration methods to several complex diseases but I am currently working with a few Canadian groups to help better understand Diffuse Intrinsic Pontine Glioma (DIPG) – a type of fatal childhood brain cancer.

Your current collaborators include researchers from Yale, Harvard, MIT, SickKids and other leading organizations. How did you initiate and sustain these collaborations?

At the beginning of my research career, I would reach out to scientists who were working on interesting, challenging and cutting-edge problems. I enjoy working in collaborative environments because I believe the key to success in biomedical research is through collaborations between researchers from diverse backgrounds.

With the support of my collaborators, I’ve been able to learn and shift my focus from theoretical computational sciences to applications of data science in genetics of complex diseases. Now, sometimes collaborators approach me with their rich data, which I’m eager to help analyze.

With your new appointment, what are you looking forward to over the next few years?

I am eager to continue expanding my research program and working with new scientists on exciting cutting-edge problems in genetics and epigenetics of complex diseases. New technologies have revolutionized how we study diseases, and we are transitioning to a point where these new technologies are revolutionizing how we treat diseases. I am confident that we will have better ways of treating these diseases in the future using personalized medicine, and I want to help make that a reality.

Visit Dr. Shooshtari’s OICR website page

Addressing high priority issues in cancer care

An image of the report cover. Text: Addressing high priority issues in cancer care

OICR and Cancer Care Ontario’s Health Services Research Network releases the 2019 Synthesis Report, summarizing 14 studies that address high priority issues in cancer care

An excerpt from the foreword by Drs. Christine Williams and Eva Grunfeld:

Read the full report.

Optimal cancer care across Ontario cannot be solely provided by a clinician or implemented by a researcher, enacted by a policy maker or attained by a patient. To improve the delivery of cancer services, we need to work together with stakeholders from across our rich cancer care ecosystem and involve them in prioritizing concerns, designing interventions and implementing solutions. For these reasons, OICR and Cancer Care Ontario (CCO) teamed up to co-create the OICR-CCO Health Services Research Network (HSRN).

Now, a decade later, we present our second Synthesis Report with an additional 14 studies that have emerged from this network. These studies have addressed high priority issues in cancer care including the gap in follow up after a positive colorectal cancer screening test, and the challenges that cancer patients face with co-existing chronic conditions like diabetes. The studies have led to the development of new methods to determine the burden of cancer in Ontario, and new resources to facilitate health services research across the province. This report provides summaries of these studies and others and their impact to date.

Read more about the OICR-CCO HSRN.

How do cancer patients help future cancer patients? This is Ron’s story

The Canadian Cancer Clinical Trials Network launches new pilot project at Windsor Regional Hospital to help patients understand their treatment options and access current clinical studies

In early 2012, Ron Truant, the former Board Chair of Windsor Regional Hospital (WRH), became a patient when he was diagnosed with pancreatic cancer.

Facing a disease with a dismal prognosis, Ron and his wife, Noella Truant, made an appointment for a second opinion at a hospital outside of Windsor. It was there that the Truants learned about an open clinical trial and secured the study’s last available spot.

Noella says not everyone is as fortunate as they were.

“We were lucky to gain access to an immunotherapy trial, which – in combination with a new chemotherapy treatment – gave us another four years together,” says Noella. “Throughout his own treatment, Ron was always thinking about others and realized there were many others who weren’t as fortunate as we were to find a trial. He knew that trials are complex and not everyone can navigate them, so he saw an opportunity to help.”

Noella and Ron Truant

Last year, only eight per cent of cancer patients in Ontario were recruited to clinical trials and in community hospitals, like WRH, that number drops to fewer than two per cent. These statistics, Noella says, indicate that patients are missing opportunities to gain access to new treatment options and contribute to clinical research.

Currently, each cancer centre in Ontario has a clinical research team that recruits patients for available trials at their respective sites but patients, like Ron, often want to explore all treatment options, including those at other nearby hospitals. These patients and their care givers are frequently left to research trials on their own through websites that may not contain current information or online trial databases that may be difficult to navigate. Even if a patient finds an available trial, understanding eligibility criteria requires specialized knowledge and advanced medical literacy.

Ron, a long-standing advocate for the quality of patient care, teamed up with Dr. Caroline Hamm, an oncologist at the WRH, to develop a better way for patients to navigate clinical trials.

“We want to make sure patients are offered the best treatments available for their individual needs, and that requires more than a database of trials,” says Hamm, who is also the Director of the Windsor Cancer Research Group. “There are many considerations that a patient weighs when deciding to participate in a trial and we need a more considerate approach to help patients with these decisions.”

With support from the Canadian Cancer Clinical Trials Network (3CTN), Hamm and the Truants designed a program where a designated clinical trials specialist – a Clinical Trials Navigator – would help patients find and understand the trials available. A patient could refer themselves to the navigator or they could be referred to the navigator by their oncologist. After reviewing the patient’s case and considering their preferences, the navigator could then identify available trials for which the patient is likely eligible, and help facilitate the connection between a patient and the study team.

Hamm, in Ron Truant’s legacy, launched the Clinical Trials Navigator pilot project at WRH in January and so far the project has since helped more than 40 patients explore trial options.

The process by which the Clinical Trials Navigator project helps patients find clinical trials that may be of benefit.

Youshaa El-Abed, the project’s navigator, sees the impact of this initiative on patients and their care givers first-hand.

“When a patient comes to us, they’re looking for a trial,” says El-Abed. “But even if there are no trials available for them, the patient – and their loved ones – gain reassurance that they have explored their options.”

Due to growing demand for clinical trial navigation services at other hospitals, the project is now open to receive patient referrals from across Ontario.

Hamm, who has been recognized for her patient advocacy in Windsor, hopes to expand this initiative to new sites as she has in the past for a cancer drug access coordinator program. In addition to helping current patients with cancer, Hamm sees the Clinical Trials Navigator project as a way to accelerate clinical research so patients can benefit from research sooner.

“If we can help patients access trials, we can help trials reach their accrual targets sooner – a win-win for patients and for local clinical research,” says Hamm. “A health system with accelerated clinical research allows us to attract more study sponsors, bringing leading edge treatment options to our hospitals. Ron envisioned this solution and we’re proud it’s in action today.”

Read more about the Clinical Trials Navigator project on 3CTN’s website

Dr. Rola Saleeb on her path to becoming a pathologist

Rola Saleeb
Dr. Rola Saleeb, Assistant Professor, Department of Laboratory Medicine and Pathobiology, University of Toronto.

OMPRN grantee and former Transformative Pathology Fellow discusses her recently-awarded faculty appointment with the University of Toronto

Despite research advances in identifying the subtypes of kidney cancer, treatment decisions are often based on the size of a patient’s tumour. Dr. Rola Saleeb, who has been studying kidney cancer for nearly a decade, thinks there’s a better way to make these decisions.

“Each month, more than 500 people are diagnosed with kidney cancer in Canada,” says Saleeb. “These individuals and their oncologists face tough decisions to make about their treatment options and I want to help make that decision easier.”

Saleeb, a former OICR Transformative Pathology Fellow and two-time Ontario Molecular Pathology Network (OMPRN) grantee, has recently become a certified pathologist and faculty member in the Department of Laboratory Medicine and Pathobiology at the University of Toronto.

Throughout her doctoral research, Saleeb developed a classification system that could help pathologists distinguish between aggressive kidney cancers and less aggressive cancers. She says this system could, one day, help spare patients from unnecessary surgery if they don’t have aggressive tumours. Additionally, she says classifying these tumours could enable the development of new therapies for these subtypes.

Now as a certified pathologist, Saleeb is the second Transformative Pathology Fellow to have been recruited to a faculty position. Both former fellows have committed to a career where research and development is central to their practice of pathology.

“Not all pathologists do research,” says Saleeb. “But for me, I feel like I can help more patients if I can help find solutions to unsolved problems.”

Saleeb is currently completing a validation study on her classification system. She looks forward to implementing the system at St. Michael’s Hospital and broadening her research to study the molecular origins of kidney cancers and new kidney cancer prevention strategies.

Read more about OMPRN here or find current pathology funding opportunities here.

Canadian Government-Sponsored Collaboration Targets Standardized Cancer Testing

Genome Canada, Ontario Institute for Cancer Research and Thermo Fisher Scientific to focus on pancreatic, prostate and breast cancer

CARLSBAD, Calif. – (July 30, 2019) – Genome Canada, the Ontario Institute for Cancer Research (OICR) and Thermo Fisher Scientific are collaborating to develop a complete solution of targeted next generation sequencing (NGS) assays and analysis software designed to more effectively assess – and eventually improve management of – pancreatic, prostate and breast cancer.  

The $6 million, three-year initiative aims to standardize advanced molecular profiling in these disease areas and make the assays commercially available globally. Focusing on rapid genomic diagnostics in pancreatic cancer and targeting treatment in breast and prostate cancers, the partnership builds on previous clinical research between OICR and Thermo Fisher and will inform development of three assays that will be utilized to stratify patients in clinical trials in Ontario and other jurisdictions.

“By supporting research and clinical trials, Genome Canada is helping to put more of Ontario’s innovative cancer diagnostics research into clinical use,” said Dr. John Bartlett, program director, diagnostic development at OICR. “This project has the potential to springboard advanced next-generation sequencing to routine clinical use in Ontario and across Canada.”

Breast and prostate cancer are among the most common types of cancer in Canada, and the country’s five-year net survival rate for pancreatic cancer is only 8 percent. However, there is clear evidence that patient outcomes can be improved with NGS-based testing strategies. A recent U.S. health economics study has shown that advanced cancer patients who received treatment based on NGS testing results experienced double the length of progression-free survival without increasing health care costs.1

While some solutions analyze only DNA sequences, the new targeted NGS assays will provide comprehensive genomic profiles by simultaneously assessing DNA and expression signatures from RNA to provide significantly more insight into driver mutations. The OICR/Thermo Fisher team will leverage this advantage by supplementing the new assays with unique DNA/RNA stratification biomarkers – specific to pancreatic, prostate and breast cancer – previously qualified by OICR translational researchers.

The collaboration is partly funded with a grant from Genome Canada through the Genomic Applications Partnership Program (GAPP). Genome Canada will contribute $2 million, the highest possible level of funding support, with the balance split between OICR and Thermo Fisher, which will cover development costs and validation activities.

Previous research collaborations led by OICR and Thermo Fisher are already well on their way to impacting cancer treatment in the future. Of particular note is a 2016 study designed to identify mutations and copy number variation changes in breast cancer, and clinical research utilizing the Oncomine Comprehensive Assay, which also supports both the National Cancer Institute’s Adult and Pediatric MATCH trials in the United States.

“OICR is a leader in clinical research, with extensive clinical trials in progress to improve care for patients with pancreatic, prostate and breast cancer,” said Jeff Smith, global lead of NGS precision medicine initiatives, clinical NGS and oncology for Thermo Fisher Scientific. “When OICR approached our team with the idea for this project, we saw it as another exciting for opportunity to bring Thermo Fisher’s proven Ion Torrent technology to clinical laboratories across Canada and to contribute to future improvement of patient care.”

1 “A Retrospective Analysis of Precision Medicine Outcomes in Patients With Advanced Cancer Reveals Improved Progression- Free Survival Without Increased Health Care Costs,” Journal of Oncology Practice, Vol 13, Issue 2, February 2017

OICR funding for Ontario drug discovery projects will accelerate development of new cancer therapies

The Ontario Institute for Cancer Research (OICR) has selected two new Late Accelerator projects to receive support through its Cancer Therapeutics Innovation Pipeline (CTIP) initiative. The projects, detailed below, will each receive up to $250,000 per year, for up to two years, to advance the development of drug candidate molecules. The projects were selected by an international expert review panel from 18 applications.

By joining the CTIP portfolio, these projects will receive more than just financial support – they will also benefit from the guidance of the Therapeutics Pipeline Advisory Committee, a group of industry and academic experts that provides advice on the scientific and strategic direction of CTIP projects.

“CTIP projects have great potential to improve treatment for patients, promote scientific collaboration and drive investment to Ontario’s biomedical research sector,” says Dr. Christine Williams, OICR’s Deputy Director and Head of Therapeutic Innovation. “These new projects are great examples of the innovative cancer therapeutics research happening in our province. We are excited to add them to CTIP’s portfolio of promising drug candidates and look forward to their progress.”

Funded projects

Identification of kinase inhibitors to block the tumour-promoting activity of YAP/TAZ for cancer therapeutics

Liliana Attisano, Principal Investigator, University of Toronto

Rima Al-awar, Principal Investigator, OICR

Frank Sicheri, Co-investigator, Lunenfeld-Tanenbaum Research Institute

Jeff Wrana, Co-investigator, Lunenfeld-Tanenbaum Research Institute

David Uehling, Co-investigator, OICR

Richard Marcellus, Co-investigator, OICR

Methvin Isaac, Co-investigator, OICR

The highly conserved Hippo pathway is a key regulator of cell and tissue growth. Virtually all solid tumours display pathway disruptions, which drive cancer initiation and progression. Mutations in pathway components are rare, making it unclear how to target the pathway for cancer treatment. This research group has shown that certain kinases are key regulators of the pathway that promotes tumorigenicity and observed that diverse human cancers display elevated levels of these kinases. Kinases are highly amenable to the development of targeted inhibitors; therefore, this project will identify potent and specific inhibitors with the long-term goal of establishing novel cancer therapeutics.

Development of kinase inhibitors for ovarian cancer: A novel first in-class immune-oncology therapeutic agent targeting tumor intrinsic stress states

Rob Rottapel, Principal Investigator, Princess Margaret Cancer
Centre

Tracy McGaha, Principal Investigator, Princess Margaret Cancer
Centre

Rima Al-awar, Principal Investigator, OICR

Methvin Isaac, Co-investigator, OICR

David Uehling, Co-investigator, OICR

Richard Marcellus, Co-investigator, OICR

Ahmed Aman, Co-investigator, OICR

The development of new cancer immune therapeutics has triggered a revolution with the recent advent of diverse strategies that engage the patient’s immune system. This research group has identified a novel kinase target that has the unique property of being both an emergent essential gene in high-grade serous ovarian cancer and a repressor of the innate and adaptive immune system. Additionally, they have demonstrated that target inhibition sensitizes cancer cells to cisplatin – a standard of care chemotherapy drug. This project will work to develop a “first-in-class” dual-action, anti-tumour and immune-oncology kinase inhibitors for ovarian cancer and potentially other cancer types.

Patterns in pancreatic cancer samples lead to better prognostic power

Dr. Sangeetha Kalimuthu, gastrointestinal pathologist at the University Health Network, works in her lab.
Dr. Sangeetha N Kalimuthu, gastrointestinal pathologist at the University Health Network, works in her lab. (Photo: UHN)

University Health Network pathologist teams up with OICR researchers to develop an improved pancreatic cancer classification test that can better predict the severity of the disease

Under a microscope, pancreatic cancer often looks like a haphazard collection of cells with various shapes and sizes, but Dr. Sangeetha N Kalimuthu saw something different.

She had been analyzing hundreds of pancreas resections, which are classified using the current three-tiered staging system – well, moderate and poor – but found that the vast majority of cases fell into the moderate category, offering little information to physicians about how best to treat these patients.

N Kalimuthu, a gastrointestinal pathologist at the University Health Network (UHN), noticed that certain patterns in cell shape matched the molecular profile of tumours with poorer survival for patients. She teamed up with Drs. Runjan Chetty and Steven Gallinger at UHN to see if what she noticed was true. Gallinger is Director of OICR’s PanCuRx Translational Research Initiative.

In a study recently published in Gut BMJ, the study group assessed more than 800 pancreatic ductal adenocarcinoma (PDAC) slides and developed an improved classification method that could help differentiate patients with the most aggressive tumours.

“Our aim was to revise and reappraise the current grading system to find features that correlated with these molecular subtypes,” says N Kalimuthu. 

By linking molecular profiles of tumours with their appearance, N Kalimuthu was able to develop a classification method that can be easily integrated into current pathology laboratories.

“Any pathologist in any part of the world can do this,” says N Kalimuthu. “It’s the bread and butter of what pathologists do. It’s fast, cheap and accessible.”

N Kalimuthu also says that this method can be augmented using deep learning methods to reduce turn-around times and variability from one pathology laboratory to another.

“Pathologists have had a long, rich history in their vital roles to diagnose and stage pancreas cancer,” says Gallinger, who is co-author of the publication. “This study is an elegant demonstration of the potential of personalized medicine, with the promise of improved outcomes for our patients.”

Read the full UHN News story here.

From idea to impact: An expanding solution to a common surgical problem

Zaid Atto, Founder and CEO at Xpan Inc.
Zaid Atto, Founder and CEO at Xpan Inc.

Toronto-based entrepreneur Zaid Atto receives FACIT’s Ernsting Entrepreneurship Award to further develop his new device for safer and less invasive surgeries

Ten years to the day after he and his family landed in Canada from Iraq, Zaid Atto stood in front of a panel of judges and pitched his idea. He had developed a new surgical device – a port that could allow for safer and more efficient minimally invasive surgeries – but he needed commercialization support and resources to move it into the next stage of development.

Surgeons use ports, also known as trocars, to make a tunnel into the body for laparoscopic surgeries. Complications with ports include accidental organ perforation, hernias and potentially death from incorrect insertions. Adding to the risk of complications, sometimes surgeons have to switch an inserted port for one with a larger diameter during the procedure to accommodate larger surgical instruments, or reinsert a port that slipped out of the abdomen accidentally. Through interviewing surgeons and shadowing dozens of surgeries, Atto recognized these concerns and saw an opportunity to address an unmet need and help both patients and surgeons.

Traditional ports are fixed in size and may slip out of a patient’s abdomen during surgery. (Photo: Magnus1313 at English Wikipedia [CC BY-SA 3.0])

After graduating with a biomedical engineering degree from the University of Toronto, Atto and his team at Xpan Inc. developed an expandable port that reduces the risk of complications associated with port insertion and alleviates the need to remove and reinsert ports. The team has consulted stakeholders and device manufacturers throughout the development of their device and have received support and validation from surgeons with multiple minimally-invasive surgical specialties.

“We saw that our device could assist surgeons across many subspecialties, especially those who have to exchange ports often, like in surgeries for colorectal cancer, pediatric surgeries or emergency procedures” says Atto. “Our port, however, is not limited to cancer surgeries. It’s a device that can make a difference for all laparoscopic surgeons and the five million patients who undergo minimally invasive surgery every year in North America.”

Earlier this year Atto pitched his technology at the FACIT Falcons’ Fortunes pitch competition. In addition to creating exposure for novel oncology innovations and providing training support for entrepreneurs, FACIT’s annual pitch competition celebrates a culture of commercialization in Ontario. Atto was one of six finalists who were pre-selected by the FACIT team to deliver pitches. Impressing the judges with an innovation developed based on a clearly-identified market need, Atto was ultimately awarded the $50,000 Ernsting Entrepreneurship Award. Xpan Inc. plans to use this funding to complete proof-of-concept animal studies and prepare for regulatory submission.

“By partnering with FACIT, we hope to bring our device one step closer to patients,” says Atto. “This means one step closer to safer and more efficient surgeries for all of us who may need these surgeries in the future.”

Read more about this story in FACIT’s most recent announcement of investments.

New research projects to drive clinical adoption of novel cancer technologies and find ways to better deliver cancer services

10 projects to receive funding through OICR-CCO Health Services Research Network

Toronto (June 4, 2019) – The Ontario Institute for Cancer Research (OICR) today announced funding for 10 projects as part of the OICR-Cancer Care Ontario (CCO) Health Services Research Network (HSRN). As part of the HSRN, these projects are focused on optimizing the delivery of existing cancer services and guiding the dissemination of new practices and technologies in cancer prevention, screening and care in Ontario.

The funded projects, which involve 103 researchers and clinicians based at 29 institutions across Ontario, as well as five institutions outside of the province, focus on at least one of six priority areas: using real-world evidence to advance innovations; data infrastructure, integration and mobilization studies; use of artificial intelligence and digital health tools; the adoption of accepted best practices related to precision medicine; knowledge translation and dissemination; and population health studies.

“Improving the delivery of cancer-related healthcare and ensuring that new innovations are properly introduced into clinical use is an essential part of improving outcomes for cancer patients,” says Dr. Christine Williams, Deputy Director and Interim Head, Clinical Translation, OICR. “The projects funded today will help integrate more leading-edge technologies and practices – such as artificial intelligence, immunotherapies and precision medicine – into Ontario’s healthcare system. OICR is proud to help enable improvements in frontline care for the people of Ontario through these projects.”

In total, the projects announced today will receive more than $2.7 million in funding over the next two years. These projects were awarded funding after a competitive process, including review by an expert panel. Together, these projects are a key arm of OICR’s Clinical Translation initiative, which is driving the translation of research findings into patient impact by partnering with the healthcare system.

“I congratulate the researchers who have received funding today and laud their efforts to optimize how we prevent, diagnose and treat cancer in Ontario,” says Hon. Merrilee Fullerton, Ontario’s Minister of Training, Colleges and Universities. “As new technologies and best practices emerge, it is important that Ontario use its research expertise to deliver these advancements to the people as quickly and efficiently as possible.”

For details about the funded projects please visit: https://oicr.on.ca/research-portfolio/health-services-research/

(more…)

Predicting the course of pancreatic cancer

Dr. Benjamin Haibe-Kains, Senior Scientist at the Princess Margaret Cancer Centre and OICR Associate poses for a photo in a data centre.
Dr. Benjamin Haibe-Kains, Senior Scientist at the Princess Margaret Cancer Centre and OICR Associate.

Meta-analysis of 1,200 patients with pancreatic cancer reveals a new way to identify those with very aggressive tumours who may benefit from alternate treatment approaches

Only half of pancreatic cancer patients who undergo standard chemotherapy and surgery live a year after their initial diagnosis. In the face of these dismal statistics, patients are faced with the challenge of deciding whether they want to proceed with treatment that may have unpleasant side effects. If clinicians could identify patients who would not benefit from standard therapies, they could help these patients make more informed treatment decisions or recommend alternative palliative treatment approaches.

As part of OICR’s Pancreatic Cancer Translational Research Initiative (PanCuRx) team led by Dr. Steven Gallinger, Dr. Benjamin Haibe-Kains recognized that computational modeling can be used to help inform these decisions, but to design a robust predictive model he would need much more data than any individual study had ever collected.

Building the data foundations

Haibe-Kains, who is a Senior Scientist at the Princess Margaret Cancer Centre and OICR Associate, began his investigation with a dataset from PanCuRx – the largest collection of genomic and transcriptomic data on primary and metastatic pancreatic tumours to date. He and his lab then incorporated an additional 1,000 cases of pancreatic tumours from studies around the world that had collected both patient samples and information about how each patient responded to treatment.

“The datasets that we aggregated were a mixed bag of different types of data collected through different profiling platforms by different institutions,” says Haibe-Kains. “We took on the challenge of harmonizing the heterogeneity of these resources which nobody else had done.”

Previously, the Haibe-Kains Lab developed a computational method that could make incompatible transcriptomic data compatible. They had used this method to find four new breast cancer biomarkers to predict treatment response and they recognized that they could apply similar methods to harmonize pancreatic cancer data as well.

The dataset resulting from the harmonization is now the largest pancreatic cancer dataset, and Haibe-Kains has made it freely available for other researchers to use and study through the MetaGxPancreas package.

Making a predictive model

Haibe-Kains and his team set out to develop a computational model that could predict if a patient would survive for a year after their biopsy. They used machine learning techniques to exploit their rich dataset, find common patterns in the genomic data of aggressive tumours, and developed PCOSP – the Pancreatic Cancer Overall Survival Predictor.

“Our approach was to look at how one gene was expressed relative to another and relate that to how long a patient lived after biopsy,” says Haibe-Kains. “That may sound simple, but that means dealing with nearly 200 million pairs of genes, which is a significant amount of data to compute.”

As recently described in JCO Clinical Cancer Informatics, the group refined PCOSP using ensemble learning – the combination of several machine learning techniques to improve a model’s accuracy of predictions.

“PCOSP is actually a combination of hundreds of models and not just one,” says Haibe-Kains. “We tested about a thousand models, selected the models that could predict early death very well and combined them to make a stronger classifier.”

Using prediction to power patient decisions

Haibe-Kains says that as the infrastructure for routine sequencing progresses, PCOSP can be translated into clinical practice to help clinicians determine which patients would not benefit from standard treatment and which may benefit from alternative treatment approaches.

“Pancreatic cancer is a challenging disease but if we can predict the course of the disease, we can give clinicians and patients more information. With that information, they can make more personalized decisions to improve their treatment and ideally, their lives.”

Read more about PanCuRx on OICR News.