Search

Background: As genome sequencing becomes better integrated into scientific research, government policy, and personalized medicine, the primary challenge for researchers is shifting from generating raw data to analyzing these vast datasets. Although much work has been done to reduce compute times using various configurations of traditional CPU computing infrastructures, Graphics Processing Units (GPUs) offer opportunities to accelerate genomic workflows by orders of magnitude. Here we benchmark one GPU-accelerated software suite called NVIDIA Parabricks on Amazon Web Services (AWS), Google Cloud Platform (GCP), and an NVIDIA DGX cluster. We benchmarked six variant calling pipelines, including two germline callers (HaplotypeCaller and DeepVariant) and four somatic callers (Mutect2, Muse, LoFreq, SomaticSniper). Results: We achieved up to 65 × acceleration with germline variant callers, bringing HaplotypeCaller runtimes down from 36 h to 33 min on AWS, 35 min on GCP, and 24 min on the NVIDIA DGX. Somatic callers exhibited more variation between the number of GPUs and computing platforms. On cloud platforms, GPU-accelerated germline callers resulted in cost savings compared with CPU runs, whereas some somatic callers were more expensive than CPU runs because their GPU acceleration was not sufficient to overcome the increased GPU cost. Conclusions: Germline variant callers scaled well with the number of GPUs across platforms, whereas somatic variant callers exhibited more variation in the number of GPUs with the fastest runtimes, suggesting that, at least with the version of Parabricks used here, these workflows are less GPU optimized and require benchmarking on the platform of choice before being deployed at production scales. Our study demonstrates that GPUs can be used to greatly accelerate genomic workflows, thus bringing closer to grasp urgent societal advances in the areas of biosurveillance and personalized medicine. [ABSTRACT FROM AUTHOR]

The biomedical research community is investing heavily in biomedical cloud platforms. Cloud computing holds great promise for addressing challenges with big data and ensuring reproducibility in biology. However, despite their advantages, cloud platforms in and of themselves do not automatically support FAIRness. The global push to develop biomedical cloud platforms has led to new challenges, including platform lock-in, difficulty integrating across platforms, and duplicated effort for both users and developers. Here, we argue that these difficulties are systemic and emerge from incentives that encourage development effort on self-sufficient platforms and data repositories instead of interoperable microservices. We argue that many of these issues would be alleviated by prioritizing microservices and access to modular data in smaller chunks or summarized form. We propose that emphasizing modularity and interoperability would lead to a more powerful Unix-like ecosystem of web services for biomedical analysis and data retrieval. We challenge funders, developers, and researchers to support a vision to improve interoperability through microservices as the next generation of cloud-based bioinformatics. [ABSTRACT FROM AUTHOR]

The thesis presented here is that biomedical research is based on the trusted exchange of services. That exchange would be conducted more efficiently if the trusted software platforms to exchange those services, if they exist, were more integrated. While simpler and narrower in scope than the services governing biomedical research, comparison to existing internet-based platforms, like Airbnb, can be informative. We illustrate how the analogy to internet-based platforms works and does not work and introduce The Commons, under active development at the National Institutes of Health (NIH) and elsewhere, as an example of the move towards platforms for research. [ABSTRACT FROM AUTHOR]