Can biomedical data be boiled down to Amazon.com-style recommendations?

miinome x
Image via MIT Technology Review

“We have recommendations for you,” announces the website Amazon.com each time a customer signs in.

As Katharine Miller reported in Biomedical Computation Review in 2012, this now ubiquitous greeting from the world’s largest online marketplace may spread beyond the retail market and foreshadow a revolution in medicine.

These days, this sort of “Big Data Analytics” permeates the worlds of commerce, finance, and government. … Where is Amazon’s equivalent in healthcare and biomedical research? Do we have a “learning healthcare system” that, like Amazon.com, can glean insights from vast quantities of data and push it into the hands of users, including both patients and healthcare providers?

Three years ago, she concluded, “not even close.” Today? Closer

Citizen scientists have begun to play an important role in creating new data sets for biomedical researchers to learn from. Many of these projects are being launched on crowdfunding platforms due to their community-focused nature and an increasing hobbyist and at-home interest in genetics and biology. Such large datasets mean researchers must learn to work within a new framework, as the correlations in big data do not always mean causation; but they also mean that important discoveries can be made more rapidly than ever.

As Rob Knight of the University of Colorado has explained in a Wired article, “The role of the big data projects is to sketch the outlines of the map, which then enables researchers on smaller-scale projects to go where they need to go,”

uBiome, for example, sequences users microbiomes, which has been shown to be an important determining factor in overall health. The company believes that the microbiome may play a role in a range of unsolved diseases, such as diabetes, hypertension and depression. Researchers using uBiome’s data can more easily test these and a range of other hypothesis based on the data, then conduct more specific studies to find well-targeted therapies.

Similarly, the company that I run, Titanovo, now offers an at-home telomere testing kit through Indiegogo, which we hope will be the first of many easy a accessible and relatively inexpensive kits useful for health and science enthusiasts, as well as (and perhaps especially) for scientific researchers. The length of telomeres (the protective end-caps for chromosomes) has been shown to be strongly correlated to a number of health metrics, with many studies concluding that a healthy lifestyle is likely to maintain longer telomeres.

Positive lifestyle changes, such as regular meditation and exercise, quitting smoking, and dieting were for the first time correlated to lengthening telomere length in 2013. However, the study recommends that a larger trial must be conducted in order to validate the findings.

The focus on a mass public is based on the belief that through citizen participation, data can be used to validate breakthrough ongoing research, and conduct new studies useful in creating novel therapies by its ability to quickly adapt to different research requests. For example, genome-turned-ancestry company 23andMe recently partnered with Genentech to research potential cures for Parkinson’s disease. 23andMe’s ability to draw in clients interested in participating in cutting edge medical research while also offering direct commercial benefits to consumers makes the company a strong contender for conducting large-scale studies.

As Miller wrote:

Right now, biomedical infrastructure lags well behind the curve. Our healthcare system is dispersed and disjointed; medical records are a bit of a mess; and we don’t yet have the capacity to store and process the crazy amounts of data coming our way from widespread whole-genome sequencing. And then there are privacy issues (see “Privacy in the Era of Electronic Health Information,” a story also in this issue). Moreover, while Amazon can instantly provide up-to-date recommendations at your fingertips, deploying biomedical advances to the clinic can take years.

Despite these infrastructure challenges, some researchers are plunging into biomedical Big Data now, in hopes of extracting new and actionable knowledge. They are doing clinical trials using vast troves of observational health care data; analyzing pharmacy and insurance claims data together to identify adverse drug events; delving into molecular-level data to discover biomarkers that help classify patients based on their response to existing treatments; and pushing their results out to physicians in novel and creative ways.

The future, while still hazy, will undoubtedly prove bountiful. It is even possible for potentially harmful pollutants to be discovered based on the data garnered. In areas where it isn’t commonly known that pollutants exist, researchers may notice a phenomena like shorter telomeres in a specific region and discover harmful environmental factors based on the large datasets. A 2012 study concluded that air pollution in Beijing shortens telomeres, supporting the idea that data may be used in such a manner.

While large datasets pose the challenge of correlations without causation, there is an important place for them in the hard sciences. As biologists and medical researchers continue to learn the best role for big data in scientific studies, important biological discoveries and innovations may soon be made more rapidly than ever.

Oleksandr Savsunenko is Titanovo’s co-founder. He earned his Ph.D. in Macromolecular Chemistry at the University of Toulouse

{{ reviewsTotal }}{{ options.labels.singularReviewCountLabel }}
{{ reviewsTotal }}{{ options.labels.pluralReviewCountLabel }}
{{ options.labels.newReviewButton }}
{{ userData.canReview.message }}
screenshot at  pm

Are pesticide residues on food something to worry about?

In 1962, Rachel Carson’s Silent Spring drew attention to pesticides and their possible dangers to humans, birds, mammals and the ...
glp menu logo outlined

Newsletter Subscription

* indicates required
Email Lists
glp menu logo outlined

Get news on human & agricultural genetics and biotechnology delivered to your inbox.