The way Joe Biden tells it, the fight against cancer is in great measure a big data problem.
In remarks at an oncology convention in Chicago this week, the vice president delivered a message of open data and interdisciplinary collaboration as keys in the search for better cancer diagnosis and treatment.
[ Related: Big data essential to cancer moonshot ]
Biden took the occasion to announce the public availability of the Genomic Data Commons, a repository of the anonymized genomic and clinical data of some 12,000 cancer patients that will open the door for researchers to analyze a broad collection of tumor genome sequences.
“It is our hope that Genomic Data Commons will prove pivotal in advancing precision medicine, where physicians attempt to tailor therapies to specific characteristics from a particular patient’s cancer,” Biden said. “Our aim and the aim of Genomic Data Commons is for researchers to have information at their fingertips about the relationship between abnormalities or mutations of genes and clinical outcomes.”
Open data, collaboration key to cancer moonshot
Biden’s announcement is the latest step forward in the so-called cancer moonshot initiative that he is spearheading, an effort to achieve a decade’s worth of progress in preventing, diagnosis and treating cancer within five years.
[ Related: CIOs join forces to battle cancer ]
In some ways, that effort parallels other administration programs such as the ongoing work to free up government data, making it publicly available and putting it in searchable, standardized and machine-readable formats so that developers, researchers, entrepreneurs and others can glean new insights and develop novel applications around it.
Biden says the same ethos will attend the Genomic Data Commons, which aims to present data in a searchable format accompanied by Web-based visualization tools and interactive features that will enable researchers to store, analyze and share information from the database.
That effort, which Biden hopes will continue to grow as more members of the cancer research community share their own data, is a significant departure for the National Cancer Institute, which has struggled to bring together disparate data sets that, taken in aggregate, could be a boon for scientists and researchers.
“Because of new DNA sequencing technology we’ve been able to rapidly generate vast troves of cancer data, genomic data, but the information [is] scattered among different government and academic repositories,” Biden said. “Most of it is out of the reach of scientists. We’re bringing it into one place.”
[ Related: How CIOs can prepare for healthcare data tsunami ]
Biden wants to see that same spirit of breaking down barriers between siloed datasets gain traction in the medical and research communities, a system that he says is “still based on the cult of the individual” where too often experts fail to collaborate.
“What’s required today extends beyond any individual or individual discipline, beyond medicine itself,” Biden said. “We have to use every weapon at our disposal if we’re going to meet our goal, help patients even more than you’re already helping them today. And to be honest with you, it requires somewhat of a change in mindset, requires a lot more openness, open data, open collaboration, and above all open minds.”