Editor’s note: In commemoration of National Women Physicians Day on February 3, the Women’s Oncology Group at Moffitt Cancer Center will highlight how women physicians and researchers are contributing to cancer prevention and treatment. is emphasized.
In a world overflowing with data, its impact often goes unnoticed. Data plays a subtle but essential role in shaping our lives. This powers suggestions for upcoming shows from your favorite streaming service. Autocomplete the following text message. It provides the fastest route to your destination. Studying data helps us better understand the world and prepare for the future.
At Moffitt Cancer Center, data comes in from every angle. Electronic health records. Biological specimen. DNA. Clinical trial. There are endless sources. By collecting individual data and combining them, scientists can tell a broader story. These stories ultimately guide how we treat patients, evaluate outcomes, and develop new treatments.
At the heart of these efforts are a small number of innovative women scientists who are harnessing the power of data to shape the future of cancer care.
Dr. Dana Rollison is the narrator of the story that data tells. As Chief Data Officer and Director of the Associate Center for Data Science, she lends her expertise and vision to power Moffitt’s cancer research. Rolison is a multifaceted leader, known for her passion as a gourmet, her love of photography, and her talent as a ballroom dancer. But at heart, Rollison is a passionate data scientist.
The journey that led Rolison to the world of cancer research began with her mother’s experience with Hodgkin’s lymphoma. In the 1970s, Hodgkin’s lymphoma became one of the first cancers to be successfully treated with radiation therapy, and her mother was one of the early beneficiaries of this life-saving treatment. Sadly, her mother’s battle with cancer didn’t end there. She was then diagnosed with breast cancer and a spinal tumor. She eventually died at the age of 49.
Rolison’s childhood and early adulthood were marked by his mother’s bravery. “She is the inspiration behind what I do,” Rolison said.
Although Rolison has had a lifelong interest in medicine, clinical care was not her focus. Instead, she was drawn to understanding the factors that put her at risk for the disease. This passion led her to cancer research, and she joined Moffitt in 2004.
“An algorithm is only as good as the data that goes into it.”
– Dr. Dana Rollison, Chief Data Officer
Data has the potential to save lives, Rolison said. As an example, she points to the increasing incidence of colorectal cancer in young people and the decreasing mortality rate from cervical cancer. These are not just statistics. These represent key insights gained from meticulous data collection in cancer registries.
Almost 20 years ago, Moffitt began investing in data science, which quickly evolved into Total Cancer Care research protocols. Total Cancer Care uses data and biospecimens collected from patients over time to improve personalized treatment and prevention efforts. However, initially, the data was not collected in a centralized source, making it difficult to exploit its full potential. Patient-reported data, tumor information, cancer registry clinical records, and electronic medical records were distributed across various platforms.
In 2010, Moffitt made the important move to invest in a centralized data warehouse and establish an access team to serve as the front door to this valuable resource. As the amount of data expanded, so did Rollison’s role in shaping the data environment.
Under her leadership, the data warehouse underwent a major transformation. The introduction of more complex data types, such as textual information and image data in electronic medical records, has revealed challenges for downstream analysis. Rollison embarked on a multi-year journey to harness the power of cloud computing.
Recognizing the need for data scientists at the undergraduate level and understanding the importance of multimodal algorithms and the integration of various data sources, Moffitt, under Rolison’s leadership, created a mathematical oncology program that integrated biostatistics and bioinformatics. We established the Department of Quantitative Sciences, a collaborative effort that integrates with science. Moffitt was also one of the first cancer centers to implement a machine learning program specifically for cancer research.
“An algorithm is only as good as the data that goes into it,” Rollison explains. She emphasizes the importance of data quality in the development and implementation of artificial intelligence algorithms. Trust is key and physicians need to have confidence in the algorithms built into their clinical care.
For Dr. Alexandra Karolak, the story told through data starts with DNA. A dry-erase whiteboard hanging in her office has a genetic sequence embedded next to a rainbow-colored triathlon medal. Handheld models of her molecules decorate her desk. Karolak gets excited about all things science and research, but it’s drug discovery that excites her the most.
Dr. Alexandra Karolak focuses her research on how artificial intelligence and other computational tools, such as molecular simulation, can be used to speed up mutational analysis and drug discovery.
Karolak originally completed his postdoctoral research as part of Moffitt’s Department of Integrative Mathematical Oncology from 2015 to 2018. When he rejoined Moffitt for the machine learning program in 2021, Karolak brought a background in computational chemistry, mathematical modeling, and machine learning. This background has given her a unique perspective and allowed her to track data from DNA tissue to proteins. Mutations to the need for new drugs targeting different clinical pathways. Her lab is currently focused on how to use artificial intelligence (AI) and other computational tools, such as molecular simulation, to speed up mutational analysis and drug discovery.
The key to success, she says, is being able to test the potential of new molecules, experiment, make changes, and continue testing. “It’s not just about designing new compounds,” she said. “The important thing is to test them and make sure they work.”
Of course, AI’s capabilities are limited by the amount and quality of available data. To gain insights from small data sets, Karolak is collaborating with other researchers across Moffitt and collaborators at other cancer centers to expand the data. This typically means identifying related datasets that can be combined, such as image data and molecular data that are related but presented in different formats.
We also share insights with physicians that show how machine learning can help analyze patient data, provide early diagnosis, and identify drug targets.
“We have a huge advantage working in a hospital,” Karolak said. “We have research facilities where ideas can be quickly communicated and tested. In this way, we are adding AI as a tool that can automate multiple levels of drug discovery. And we We believe there is an opportunity for successful drug discovery and optimization to successfully address the problem of resistance.”
Most people think of statistics and informatics as crunching numbers and looking at mathematical formulas, but Moffitt’s biostatistics and bioinformatics team helps researchers investigate cancer. We develop methods and tools that directly impact the way we do things. The team’s expertise includes bioinformatics, biostatistics, and statistical genomics. One of his members is his Dr. Xiaoqing Yu.
For Yu, an avid LEGO architect outside of work, embarking on a project requires a strong vision of the big picture before building the first building blocks. Ultimately, the success of cancer research is determined by the first steps in the research design.
Dr. Xiaoqing Yu helps personalize treatment approaches in clinical studies by continuously evaluating data and interpreting results in real time to inform researchers if changes are needed.
At Moffitt, our biostatistics and bioinformatics teams are involved in clinical trial design from inception to evaluation. The biostatistics side helps set up the trial design and determines the number of patients needed to obtain statistically relevant results. They can also help determine treatment dosing strategies. Similar to Yu’s lab, the bioinformatics side is helping to personalize therapeutic approaches in clinical research. Through genome sequencing or analysis of microarray gene expression data from patients, bioinformaticians can identify mutations and genetic variations that may influence response to treatment.
The team constantly evaluates data, interprets results in real time, and informs researchers if changes are needed. He also helps answer some of the most complex questions, such as how to improve immunotherapy, one of the fastest growing areas in cancer research.
In his day-to-day work, Yu works with clinicians and other data scientists to find patterns in data. She accomplishes this by developing bioinformatics tools to analyze data and make it happen. One of her current projects focuses on bladder cancer, analyzing raw data from patients before and after treatment to identify somatic mutations unique to these patients. She then predicts whether a given mutation can be identified as a unique antigen and later used as a target for immunotherapy.
“The key is to find the patterns, the right biomarkers, and determine whether we can move forward from the experimental side towards further validation,” Yu explained, adding that these discoveries could improve personalized medicine. He pointed out that there is a gender.
Like Karolak, Yu also uses machine learning and artificial intelligence to study single-cell data analysis.
“Analyzing data can be very time-consuming,” Yu says. “We collect huge amounts of single-cell data. Can we build models and make predictions from this already analyzed data? We are using deep learning to make it happen. We’re designing AI models.”
The potential uses for your data are endless. In 2023, Rollison’s team launched his Moffitt Cancer Analytics Platform, known as MCAP. The platform integrates a wide range of high-quality data sources and analytical tools that improve clinical and operational decision-making, cancer research, and care delivery. Going forward, Rolison hopes Moffitt will continue to build on the data available to the clinic and add tools to empower researchers.
“Moffitt is ahead of the curve in how we think about data and how we build an enterprise-wide data strategy,” she said. “We are focused on building synergies between our clinical and research efforts, and we are investing in data infrastructure that will benefit many people. Very few institutions have it.”
