The FDA has awarded DNAnexus a five-year, $20 million contract to run the agency’s cloud-based platform-as-a-service, with an eye to enhancing its capabilities beyond its work to date in linking government, academic, and industry users to crowd-source a reference standard for validating bioinformatics pipelines by assessing genomic variation.
DNAnexus said it will partner with Deloitte to enhance the precisionFDA Collaborative Omics Environment in the Cloud by upgrading the platform’s sponsor-reviewer interaction, adding support for multi-omics, and offering a library of analytical, statistical, and machine learning applications that are both accessible to reviewers and sufficiently powerful for bioinformaticians.
“We understand FDA’s evolving needs for data stewardship, security, and quality, and the increasing complexity of bioinformatics in regulatory review,” DNAnexus CEO Richard Daly said in a statement. “We look forward to our expanded relationship with FDA, extending the use of technology, data, and stakeholder engagement on precisionFDA to enhance the regulatory process and provide better options for patients and healthcare providers.”
DNAnexus previously developed the precisionFDA Challenge Construction Toolkit, which has been used by the FDA and partners to design, deploy, and present cloud-based scientific challenges.
In the current challenge—which began November 1 and expires February 1, 2020—the FDA and the Georgetown Lombardi Comprehensive Cancer Center and Innovation Center for Biomedical Informatics at Georgetown University Medical Center are challenging researchers to develop and evaluate computational algorithms for brain tumor biomarker identification and patient outcome prediction using gene expression, DNA copy number, and clinical data.
Previously, precisionFDA has fostered the creation of a standard for germline variant comparison. In addition to variant calling accuracy, applications covered by precisionFDA have included food-borne pathogen and biothreat detection; representation and reproducibility of NGS pipelines; assessment of tumor mutation burden; and use of machine learning and artificial intelligence models using multi-omics data to identify biomarkers and predict brain cancer patient outcomes.
precisionFDA is authorized under the Federal Risk and Authorization Management Program, or FedRAMP.
Since precisionFDA’s launch in December 2015, it has grown into a community that connects more than 4,000 users across 1,200 government, commercial, academic, patient advocacy, and healthcare organizations, DNAnexus said.
“precisionFDA contributes to an optimized and independent review process by making tools available that empower reviewers to assess the accuracy of analytic pipelines without requiring bioinformatics expertise and enabling effective sponsor−reviewer interaction on a secure, cloud-based platform,” Elaine Johanson, Acting Director of Health Informatics within the Office of the Chief Scientist at FDA, said in a statement.