Tempus, a technology company advancing precision medicine through the collection and analysis of molecular and clinical data at scale announced today that it was selected by Leidos Biomedical Research Inc. (Leidos Biomed) to abstract and structure follow-up clinical data for The Cancer Genome Atlas (TCGA) Project for submission to the National Cancer Institute’s Genomic Data Commons (GDC).
The Cancer Genome Atlas (TCGA) Project Background
There are 230 distinct investigators that contributed samples to TCGA, with 10,000 cases represented by 100 contributing institutions. While the genomic data from TCGA has been transformative for research, continuing to enrich the dataset can increase its usefulness for researchers and clinicians. To make the TCGA resource even more useful, Tempus is working with Leidos Biomed on behalf of the NCI to obtain up-to-date medical records for clinical data abstraction.
Collaboration Details
As part of this collaboration, Tempus will reach out to these contributors and/or their institutions to obtain up-to-date medical records for clinical data abstraction. Then, using its Tempus O platform, which employs a sophisticated combination of technologies, such as optical character recognition and natural language processing algorithms, along with qualified healthcare professionals, Tempus will clean and structure the collected data, which will then get paired with the corresponding molecular data. This ‘upgraded’ TCGA dataset will then be made publicly available for researchers around the world, as the current TCGA data is today.
“A current limitation of the TCGA’s genomic dataset is the modest amount of follow-up clinical data that is available,” said Kevin White, President of Tempus. “We are pleased to support the NCI and the many medical centers whose investigators have contributed to TCGA, and we are eager to integrate these important datasets in pursuit of research and improved patient care.”
“We chose Tempus for this task because of their track record of successful partnerships with NCI designated cancer centers and their advanced technology for abstracting the required clinical data for this project,” said Nancy Roche, Director, Leidos Biomed Biospecimen Research Group.
The TCGA genomic dataset is a landmark cancer genomics program that has molecularly characterized over 20,000 primary cancer and matched normal samples spanning 33 cancer types. This joint effort between the National Cancer Institute and the National Human Genome Research Institute began in 2006.