Data Science

Accelerating Discoveries

Revolutionizing Cancer Research

Much of what we seek to understand about cancer and other diseases is discoverable in digital code. Two decades ago, it cost $95 million to sequence a single human genome. Today it costs a mere $1,200 — and the task can be accomplished in a day rather than a dozen years. At Fred Hutch, we invest heavily in data science infrastructure and expertise so we can get to new discoveries faster using the vast and growing amounts of available genetic and health data. 

Using machine learning, deep neural networks, natural language processing and cloud computing, we have the power to find more meaning in data, at much deeper levels, than previously imagined — to learn the genetic causes of disease, streamline drug discovery, develop more targeted and personalized treatments, and more. Much of this work at Fred Hutch takes place within the Translational Data Science Integrated Research Center, Shared Resources and our Center IT — in collaboration with research partners across the country and around the world.

Precision Medicine

Data science research is helping us develop more targeted and personalized treatments for patients, also known as precision medicine, by linking a patient’s clinical data with genomic data about that person’s tumor or disease and then integrating that information with data from thousands of other patients. Precision medicine holds the promise of improving patient care — and reducing costs — by identifying which treatments are most likely to be effective and avoiding harsh and expensive treatments that are unlikely to be beneficial. Our growing involvement in precision medicine includes collaboration with UW Medicine and Seattle Children’s in the recently established Brotman Baty Institute for Precision Medicine, as well as the co-development of innovations such as the MERGE algorithm, which helps predict how tumor cells from individual patients will respond to specific chemotherapy drugs.


Translational Data Science IRC

The Translational Data Science Integrated Research Center, established in 2018, facilitates collaboration between Fred Hutch researchers, data scientists and technology partners such as Amazon and Microsoft, with the goal of ensuring that our investigators can benefit from the latest data science techniques in their quest for new discoveries. 

Data Science Infrastructure

At Fred Hutch, we facilitate collaborative research across our divisions and with outside partners., allowing investigators to store, share and analyze their research data in the cloud. Our data-sharing culture has also led to the creation of Oncoscape, an online data portal that draws on publicly available molecular, genetic and medical information from the national Cancer Genome Atlas. Another data analytics tool that supports collaborative research is our HICOR IQ informatics platform, which integrates cancer registry and health insurance claims data from across Washington state.

Scientist working at a computer.

Data-Intensive Bioscience

Biomedical research has become increasingly data-intensive, requiring new tools, expertise, and collaborations between lab researchers and data scientists. At Fred Hutch, we support our investigators in making the most of their data by providing state-of-the-art data infrastructure and data science support in areas that include data engineering, data integration, data mining, database development, natural language processing, machine learning, computer vision, mobile app development, and bioinformatics.

Data visualization marquee platforms.

Data Visualization

Working within the intersection of biology, mathematics, and computer science, the Fred Hutch Data Visualization team applies cutting-edge web technologies to distill and disseminate the knowledge embedded in scientific datasets. These free and open source licensed tools enable scientists to bring their data sets to life and lead to life-saving discoveries.

Big Data Collaborations

Fred Hutch researchers are engaged in numerous large-scale studies that rely on data sharing with institutions and investigators across the country and around the world. One such study, which analyzed more than 32,000 genes from more than 500 people, uncovered a set of genes that predict whether the flu vaccine will work in adults up to age 35. Another study analyzed the genomic landscape of acute myeloid leukemia, an aggressive blood cancer, in children and young adults and found critical molecular differences compared to the same cancer in older adults. Results of another study suggest that it is possible to detect patterns recorded in an individual’s immune cells, thereby revealing previous viral exposures and shared genetic traits.