Powering genomics tools and analysis with cloud computing
Microsoft continues to work alongside researchers and industry partners to bring cloud-based genomics analytics tools and solutions to the market. These solutions are critical in deciphering the code embedded in our individual and collective genetic blueprint. A better understanding of the genetic code will be important for improving diagnosis, developing new precision therapeutics, tailoring treatments, and optimizing therapies in ways so we deliver better healthcare and positively impact human lives.
A turnkey solution to genomics analysis
Microsoft Genomics is a highly scalable cloud-based service to perform secondary analysis of the human genome and generates durable genetic variant datasets in hours, versus days. More importantly, the service is ISO-certified and compliant with HIPAA regulations, a critical requirement for the integration of genomics in clinical pipelines. Organizations such as the St. Jude Children’s Research Hospital and the Seattle Children’s Hospital have been using the Microsoft Genomics service to build high-quality clinical genomic data sets for pediatric diseases.
Microsoft alongside its partner DNAnexus continues to support St. Jude Children’s Research Hospital in enabling pediatric cancer research with the continued global adoption of the St. Jude Cloud, a platform to aggregate high-quality clinical genomic data for pediatric diseases. St. Jude Cloud now hosts 10,000 whole genomes from pediatric cancer and other childhood catastrophic diseases. Since the launch of St. Jude Cloud in the spring of 2018, more than 50,000 users from across the world have accessed the site, including more than 1,000 registered users from 49 institutions in 15 countries. This research effort is already having an impact on helping children with the rarest of rare diseases.
The Integrative Brain Research Institute of Seattle Children’s Hospital is working with Microsoft and Veritas Genetics in building the first cloud-based genetic and phenotypic database focused on infant mortality and Sudden Infant Death Syndrome (SIDS). This database will allow researchers to harness the power of Microsoft Genomics and AI services on Azure to analyze how genetic variation contributes to infant mortality. You can learn more about this collaborative effort here.
Cromwell and WDLs flowing on Azure
Today I’m excited to announce the release of an open-source project on GitHub from Microsoft Genomics: Cromwell on Azure. Cromwell is a workflow management system geared toward scientific workflows, originally developed by the Broad Institute. Cromwell on Azure uses the GA4GH Task Execution Service (TES) backend and orchestrates the dynamic provisioning of computing resources via Azure Batch. With Cromwell on Azure, researchers can now take advantage of the hyperscale compute capabilities of Azure to execute their genomics pipelines. This open-source project is fully backed by the Microsoft Genomics engineering team, and we are actively driving the development of this code base and enabling new analytic pipelines. We also know that this project will only get better with the feedback and contributions from the community and customers such as Answer ALS. Answer ALS is a multi-institution organization focused on advancing research and stopping Amyotrophic Lateral Sclerosis (ALS) using a multi-disciplinary approach. The Answer ALS research teams will be using Cromwell on Azure for their multi-omics analysis platform to analyze the genome, epigenome, RNA, proteins and cellular metabolism of healthy people and ALS patients.
Genomics sample-2-answer showcase at the American Society of Human Genetics annual meeting
Microsoft Genomics team will be at the American Society of Human Genetics (ASHG) 2019 Annual Meeting in Houston, Texas from Oct. 15-19 alongside the world’s leading genomics researchers sharing advances in genomic analysis technologies. We will be featuring EPAM and Tag.Bio, two of the partners who are leveraging the power, performance, scalability, and security of Azure to innovate and scale their solutions and services. The EPAM Cloud Pipeline is an open-source, web-based cloud environment for building and running the scripts and workflows used for genomics analysis and modeling, and can be easily customized with your tools and pipelines. The Tag.Bio platform empowers doctors and scientists to perform complex, robust, reproducible data analyses in seconds – with proven, best-practices techniques in data science, machine learning, and AI delivered via user-friendly apps. Both EPAM and Tag.bio can be easily customized with your tools and integrated with the Microsoft Genomics service.
Stop by our booth (#1421) at American Society of Human Genetics 2019 annual meeting (ASHG 2019) to learn more about how Microsoft and its partners are making genomic analysis easier and more accessible on Azure.
