“Thousands of lines of undocumented C…”
As the world’s health providers and financial markets buckle under the impact of an overwhelming COVID-19 pandemic that is still in its early stages, major technology providers are stepping in to help with high-end processing capabilities, analytical tools and expertise in everything from coding to front-end design.
One example set to be closely watched is Microsoft and GitHub’s work with the UK’s MRC Centre for Global Infectious Disease Analysis at Imperial.
Pandemic Simulation Code: Web Portal Coming Soon…
Neil Ferguson, Director of the MRC Centre and Abdul Latif Jameel Institute for Disease and Emergency Analytics (J-IDEA) revealed late on Sunday that the two companies were stepping to “document, refactor and extend” a sprawling pandemic simulation code base the centre is using to model control measures against the pandemic.
As he explained a series of posts on Twitter, “I wrote the code (thousands of lines of undocumented C) 13+ years ago to model flu pandemics.”
With Microsoft and GitHub stepping in to offer support, the JRC Centre/J-IDEA plan to develop a “web-based front end to allow public health policy makers from around the world to make use of the model in planning” he said, adding that “we hope to make v1 releases of both the source and front end in the next 7-10 days…”
That will help policy makers plot responses to the pandemic as it continues to escalate, with over 14,000 deaths now recorded, including 5,476 deaths in Italy less than eight weeks after the first coronavirus infection was recorded in the country.
Immunology Data Analysis
Microsoft is also using its existing partnership with Seattle-based Adaptive Biotechnologies to identify and map out the immune response to COVID-19.
This involves collecting blood samples from individuals who are fighting the virus or have successfully recovered. These samples are processed using Illumina platform technology, a DNA and RNA sequencing system. The collected data is being uploaded to Microsoft’s Azure cloud platform, where machine learning is being used to improve the accuracy and detection of immune response signatures.
I am happy to say that @Microsoft and @GitHub are working with @Imperial_JIDEA and @MRC_Outbreak to document, refactor and extend the code to allow others to use without the multiple days training it would currently require (and which we don’t have time to give)…
— neil_ferguson (@neil_ferguson) March 22, 2020
Chad Robins, CEO and co-founder of Adaptive Biotechnologies commented: “We can improve our collective understanding of COVID-19 by decoding the immune system’s response to the virus and the disease patterns that can be inferred from studying these data at the population level. Immune response data may enable detection of the virus in infected people not showing symptoms and improve triaging of newly diagnosed patients, potentially solving two of the challenges we are facing.”
Nvidia Provides Free Genomics Analytics
Chipmaker Nvidia is providing its genomics analytical tool Parabricks for free to researchers over the next three months, meanwhile.
Parabricks is essentially GPU-boosted software for genomics processing that can analyse samples 50 times faster than traditional CPU tools.
VP of Healthcare at Nvidia Kimberly Powell wrote : “Given the unprecedented spread of the pandemic, getting results in hours versus days could have an extraordinary impact on understanding the virus’s evolution and the development of vaccines.”
For researchers working with Oxford Nanopore long-read data, a repository of GPU-accelerated tools is available on GitHub. Its pipeline reduces the time required to analyze a whole human genome from about 30 hours (BWA-GATK4) to 45 minutes on servers with 8 GPUs, Nvidia said in a blog over the weekend.
High Performance Computing Consortium
In the US, the White House Office of Science and Technology announced a new public-private COVID-19 High Performance Computing (HPC) Consortium.
The consortium brings together HPC enterprises IBM, AWS, Google and Microsoft to provide capabilities for academic institutions MIT and Rensselaer Polytechnic Institute. The processing power will also be available to US government departments.
Currently the consortium is providing access to 16 supercomputing systems, including Oak Ridge Summit the world’s fastest supercomputer.
All together these 16 systems represent more than 330 petaflops of processing power, fuelled by 775,000 CPU cores and 34,000 GPUs.
Peter Lee, VP of AI and research at Microsoft commented that: “The solution to COVID-19 is not likely going to come from one person, one company or one country. This is a global issue, and it will be a global effort to solve it.”