Taking Precision Medicine Mainstream with Data and Compute
Private companies, research institutions and healthcare professionals around the globe have long been on the hunt for the technological muscle to treat diseases using precision medicine—and it seems the wait is over.
In New York, Mount Sinai’s Icahn Institute for Genomics and Multiscale Biology is one organization on the forefront of the next generation of medicine driven by supercomputing.
“We’ve built one of the largest computer centers in academic medicine,” says Adam Margolin, Ph.D., Senior Associate Dean of Precision Medicine and Professor and Chair of the Department of Genetics and Genomic Sciences.
The advances in computational power, as well as the data analysis to make sense of how billions of genomic indicators match with gene therapy treatments, is poised to change the way the industry approaches medicine and healthcare in the not-too-distant future.
Precision Medicine Leveraging Supercomputing and Data
Founded in 2011, the information-driven medicine branch of the Icahn School of Medicine utilizes an entire room of supercomputers to diagram an individual patients’ disease down to the molecular level, then compares it with millions of records to devise a highly-personalized treatment plan.
In cancer, Margolin explains, the protocol looks like this:
- A cancer patient has a tumor biopsy taken at a local clinic.
- The sample is sequenced to the molecular level with the resulting data either sent back to the medical institution or housed in the cloud.
- Researchers then use a variety of techniques to explore that patient’s sequencing against a growing database of millions of similar tumors, along with the outcomes of various treatments for those tumors. Labs can also grow more cells from the tumor in a dish, and test specific treatments, to further narrow the best choice.
While the idea of individualized treatment approaches inherent in precision medicine is nothing new, the power of precision medicine is taking off in recent years thanks to …
- The proliferation of data—enabled by digital data entry tools and a growing class of IoT devices.
- The power to store, process and analyze all that data.
The more data a machine has access to, the more insights it’s able to draw about a specific variety of cancer or other disease—and the more accurately it’s able to predict the best possible treatment for each patient.
Read More: What Dark Data Can Teach Us About Healthcare
The Price of Precision
“The servers at Mount Sinai crunch genetic sequences around the clock,” says Margolin, “and the institution is currently trying to grow to 20,000 computational cores, a key measure of capacity.”
But the data analysis and supercomputing power that drives precision medicine doesn’t come cheap. Researchers like those at Mount Sinai are conducting studies to justify the costs of precision medicine through demonstrated results.
One study of treatments targeted toward oncology patients with a specific genetic mutation found survival rates of 13.4 months, compared to 9 months in patients whose treatment was not specifically matched with their genetic aberration.1
The Demand of Precision
In 2017, Mount Sinai had such a high demand for sequencing the molecular structure of tumors and other conditions that it spun off a private, for-profit company, Sema4, to expand the work and take on contracts in the public and private world.
This accelerating demand for more computational power comes as the task of genomic sequencing grows simpler—and cheaper.
“The price to sequence a genome has fallen faster than almost any technology in history,” Margolin says.
“When it was first done in 2000, it cost several billion dollars2 to sequence one genome. Now, the cost is approaching $1,000, and continues to drop toward $100. It’s now at the point where genomic sequencing is becoming a routine assay used in the clinic.”
Now Margolin says the major costs have shifted from the generation of data (ie; the mapping of a genome) to the storage and computational analysis of the billions of data points generated by the mapping. “The computational needs are growing as data generation grows easier,” he says.
“In the genomic space particularly, we use machine learning to identify predicted causes of disease and predicted therapies that an individual will respond to,” Margolin says.
Bringing Precision Medicine to the Masses
For most in the field, the growing mountain of data and the accompanying analytical power are incredibly promising. A growing array of studies in U.S. medicine are beginning to prove the effectiveness of precision medicine in oncology, Alzheimer’s disease, cardiology, macular degeneration and other common ailments.
And the more data is generated, the better researchers and doctors can understand these diseases, how they manifest in different individuals, and what kind of treatments or preventative measures apply. Imagine the possibilities of one day being able to sequence your genome, run a predictive model and be given a course of treatment proven to work.
“Over the next 5 or 10 years there will be hundreds of millions of patients around the world who have billions of data points relative to their disease that are now measured,” Margolin says. “If we can learn from all of that data, we can revolutionize our understanding of the causes of disease and what subtext of disease are likely to respond to specific interventions.”
Also on the horizon? Using precision medicine to treat not only disease-states, but also to monitor and predict risk factors for healthy patients whose genomic mapping shows variances that put them at risk for future diseases. Using artificial intelligence, doctors can produce individualized preventative treatment plans or recommendations such as specific diets or exercises.
The more medical data gathered, and the more supercomputing power applied to these questions, the more we’ll see the healthcare industry scale these individualized, effective treatments to larger and larger populations.
Learn more about how data collection and access is revolutionizing healthcare:
This content is produced by WIRED Brand Lab in collaboration with Western Digital Corporation.
FORWARD-LOOKING STATEMENTS: This article may contain forward-looking statements, including statements relating to expectations for storage products, the market for storage products, product development efforts, and the capacities, capabilities and applications of Western Digital products. These forward-looking statements are subject to risks and uncertainties that could cause actual results to differ materially from those expressed in the forward-looking statements, including development challenges or delays, supply chain and logistics issues, changes in markets, demand, global economic conditions and other risks and uncertainties listed in Western Digital Corporation’s most recent quarterly and annual reports filed with the Securities and Exchange Commission, to which your attention is directed. Readers are cautioned not to place undue reliance on these forward-looking statements and we undertake no obligation to update these forward-looking statements to reflect subsequent events or circumstances.