Using Big Data to Drive Precision Medicine

Located in the heart of Cambridge, Mass., Genospace is a fast-growing cloud-based software company whose mission is to harness data to pioneer solutions in precision medicine.

“The world is awash with genomic data,” says Mick Correll, the company’s CEO.

Currently, the volume of genomic data collected is experiencing exponential growth, doubling every seven months, and by 2025, scientists predict approximately 1 billion people will have their genomes sequenced. This pace of growth makes data storage a priority in the genomics space, and makes data analysis the best opportunity to translate this resource into scientific discoveries and better clinical care.

By creating new ways of analyzing, visualizing, and delivering genomic data, Genospace is at the forefront of this effort. It was launched in 2012 by Mick and genome scientist John Quackenbush, who together had previously established the Center for Cancer Computational Biology at the Dana-Farber Cancer Institute.

In Becoming CEO, Mick discusses his most important lesson learned as CEO, his vision for data sharing in health care, and the key growth areas for the genomics industry.

Slone Partners: Genospace is a well-known brand with a reputation for solving big data issues. How do you think about the brand and incorporate it into your company culture?

Mick Correll: It has been incredibly rewarding to see the growing recognition of the Genospace brand and reputation in connection with solving some of the most challenging big data problems in health care. I can tell you, brand and culture weren’t something we put a lot of time and energy into during the early years….We were just too busy focusing on the work itself.

When we started out, we were a lean team composed primarily of scientists and engineers. The company culture grew organically out of the mission and values that had brought us all together in the first place. We were passionate about applying data and technology to produce better outcomes in health care, we all felt a tremendous sense of responsibility in being good stewards with the data our clients and their patients had entrusted with us, and we took great pride in actively seeking out and tackling the hardest problems that stood between us and achieving our mission.

Slone Partners: What is a key lesson you have learned as CEO?

Mick Correll: One of the most important lessons I’ve learned in running a startup is that you can’t hold on too tight and expect that you’ll be able to control everything. While there are many factors that are within your control, there will undoubtedly be bumps and obstacles along the way that you’ll never see coming. The best analogy I can think of is skiing moguls. Planning, training, and preparation are important, but at the some point you just need to pick your line, point your skis downhill, and then stay loose and be prepared to handle whatever adversity the mountain throws at you.

Genospace has a dynamic team, with people focused on software engineering, interactive design, data science, etc. Do you have a particular approach when vetting a new leader?

Mick: Our approach to building the team has been pretty straightforward. We seek out individuals who have skills and experience that are complementary to the rest of the team and who share our passion for improving outcomes in health care.

An important element of our company culture is that we seek to use data to help drive our decisions whenever possible. We’ve brought this approach to our hiring process as well. We spend a lot of time developing exercises for candidates in different job functions. Part of our hiring process is to invite people into our office for a day to work on an exercise. Importantly, we don’t give them all the information they need to complete the task, and we encourage them to engage with the rest of the team to find what they need. This gives us the opportunity to not only evaluate their work product, but also to observe their process and how they operate in a highly collaborative, cross-disciplinary environment. I believe it also gives the candidates a chance to experience our culture first-hand to see if this is a place where they would be happy working.

Your platform has many uses—research, clinical development, lab medicine, clinical care. What growth areas do you see?

Mick Correll: Right now we are seeing tremendous opportunity in the molecular and genomics lab market. The growth and uptake of high-dimensional molecular profiling has exceeded our expectations, and we think this trend will only accelerate in the years to come. DNA sequencing technologies provide insight into the molecular basis of human development and disease pathogenesis. It is hard to think of any area of medicine that won’t benefit from these insights. The software services that Genospace provides are a critical component of operationalizing these technologies into mainstream clinical care.

Looking forward, we expect we’ll also see significant growth with our population analytics offering for clinical and translational research. The world is awash with genomic data. But genomic data on its own has limited value. The challenge is connecting genomic data with well-characterized phenotypes. Our services enable clients to connect information silos such as EMRs and patient registries, and to bring structure to messy real-world clinical data such that it can be analyzed in combination with genomics longitudinally, and at a population scale.

What is your view on data sharing in the health care industry?

Mick Correll: Few people would argue that data sharing and an open-access data culture wouldn’t have the potential to drive discovery in health care. The challenge is in balancing open access with individual privacy. Privacy is a tricky business. What one person may be perfectly comfortable sharing may be perceived as a violation of privacy by another. This issue is further complicated in the realm of genetics, where sharing information may have implications not just for an individual but for his or her family as well. This dynamic makes it very difficult to develop a one-size-fits-all policy, and inevitably leads to a conservative approach (i.e., little or no data sharing)….

We believe a potential solution lies in empowering individuals to make these decisions for themselves. It is common sense that people should have access to their own health and medical records, and this creates an opportunity for them to participate in open-access programs. This must be done in a responsible way. Informed consent has and will continue to be an essential foundation for medical research. But fundamentally, we believe it should be an individual’s choice, and our role as technologists is to help inform and empower them with options.

You and John Quackenbush established the Center for Cancer Computational Biology at the Dana-Farber Cancer Institute. What lessons did you learn during that process?

Mick Correll: Our experience in establishing the CCCB was highly influential in developing our strategy and business plan for Genospace. Running a DNA sequencing facility we experienced first-hand the remarkable creativity and diversity of how these instruments could be applied to bring insight to the inner workings of our cells. I think there is a common misperception that DNA sequencing is only used for understanding inherited DNA. The fact is these instruments are molecular microscopes that can explore not only the transmission of traits across generations, but how entire networks of genes are expressed and regulated in different tissues, how changes and disruptions to these networks can impact the growth and development of an organism over time, and how our own genes interact and are influenced by the environment and the world around us. We believe this remarkable diversity of applications will proliferate in the clinic just like we saw them proliferate in research labs.

We also learned from direct experience how the same underlying data could be used to support many different use cases. We saw how molecular profiling had the potential to inform the diagnosis and treatment plan for individual patients, but also how the same information in aggregate and in combination with phenotypic data could be used to drive discovery in both academic and industry research. In this context, one of the most important lessons we learned was that the disease experts themselves (i.e., clinicians and biologists) had virtually no means of exploring and analyzing these population-scale datasets. We developed our tools to bridge this gap, and to democratize access for a much broader range of users. We believe that the wonderful serendipity behind so many scientific discoveries arises when an individual with a depth of understanding and intuition can explore new data and information that is presented in a useful way.

About Mick Correll

Mick’s 15+ year career has tracked the path of genomics from basic research to clinical care. Over this time he has held leadership positions in academia and industry, and has developed informatics solutions for pharma/biotech R&D, ag-bio, and academic, government, and community health care providers. Prior to launching Genospace, he and partner John Quackenbush established the Center for Cancer Computational Biology at the Dana-Farber Cancer Institute. Mick began his career at Lion Bioscience Research Inc. and U.K.-based informatics provider InforSense.

Mick earned a B.S. in computer science and a B.A. in molecular biology from the University of Colorado at Boulder.

Read our exclusive interview with Andy Fish, Executive Director at AdvaMedDx.