To advance clinical understanding at the point of care and help determine the best treatment or prevention options for patients, Amazon Web Services has launched a service that uses artificial intelligence (AI), machine learning, and machine learning. as other AWS and partner products and services to run IT-heavy bioinformatics workflows.
WHY IT IMPORTANT
As announced by AWS, clinicians can query thousands of variants across multiple genes at once to understand how genomic variation, combined with corresponding clinical data, may affect human health or predict clinical outcomes.
Tehsin Syed, general manager of health AI at AWS, and Dr. Taha Kass-Hout, vice president of machine learning and chief medical officer at AWS, said in their blog post that it’s size, integration The rapid accumulation, complexity and heterogeneity of data challenge existing computational tools used in research and precision medicine.
AWS built Amazon Omics to support large-scale genomic analysis and collaborative research for two main reasons, the company says:
- Syed and Kass-Hout explain that generating genomic, transcriptional, and other omics data insights makes it difficult for existing tools and systems to attempt to manage these workflows. .
- The level of data required for sequencing also presents privacy, security, data ownership, governance, and equity challenges for the health care and life sciences and must exist in a safe, compliant environment.
Amazon Omics users can reduce the time spent setting up and running complex Extract-Convert-Load processes by storing original data in optimized query-ready formats (such as Apache Parquet) and APIs. They do not need to focus on providing the underlying infrastructure to run their bioinformatics programs.
Customers can bring their existing workflows into the platform, which is compliant with HIPAA, GDPR, and other data privacy regulations. According to AWS, access control, logging, and auditing lines are also built-in.
There are three components in Amazon Omics.
- Omics-Aware object storage for raw string data.
- Omics workflows for processing raw string data at scale – in Omics Storage or in S3.
- Omics Analytics is for analytics through variations (or spikes) and query-ready annotations.
Omics users can combine data with other publicly available reference datasets in the Open Data Registry on AWS, including the 1000 Genomes Project, to be used as a control for understanding disease risks; Genome Aggregation Database (gnomAD), which combines disease frequency data to improve disease detection; and more than 60 other genomic datasets.
Users who want to search for the clinical significance of DNA sequence analyzes – raw genomic variants in Variant Call File (VCF) form – where results such as faulty genes that make proteins can be found cancer.
With Amazon Omics, they can “import their VCFs into the Variant Repository and seamlessly convert them to a query-ready schema available as an Apache Iceberg Table. It also supports importing variant annotations into Annotation repository Customers can manage access through AWS Lake Formation and apply granular access controls to filter out individual patients.
“This helps define custom patient groups and manage patient consent for compliance regimes, such as GDPR, without having to duplicate data. This also allows querying and analyze these variations using Amazon Athena and incorporate data from other modalities, such as clinical data in Amazon HealthLake or in a customer’s AWS Glue Data Catalog,” said Syed and Kass-Hout .
Because the platform is part of the AWS ecosystem, partners like Lifebit and Ovation access large genomic data stores faster and can accelerate their work and innovation on their biomedical data solutions. .
TREND TO BIGGER
Relevant genomic inferences can be difficult to make when genomic data is not accessible or in an easy-to-use format, such as those that electronic health records can often display. town.
John Quackenbush, chair of the Department of Biostatistics at the Harvard TH Chan School of Public Health, professor of accessing all genomic data stores in one place allows machine learning to make the best therapeutic predictions for each patient. computational biology and bioinformatics at the Channing Department of Network Medicine and the Dana-Farber Cancer Institute, and a former member of the Human Genome Project.
“We need to know something about the health and well-being of each individual whose genome has been sequenced if we are to get to a point where we can draw meaningful conclusions,” he said. . Healthcare IT News before the HIMSS keynote on big data and analytics.
Since that time, investments in precision medicine have focused on technologies that can provide computing power and decision support, including EHRs.
Last year, Epic announced a partnership with Boston-based gene profiling company Foundation Medicine to order, receive, and view results in existing EHR workflows, and Allscripts purchased 2bPrecise.
In July, Joel Diamond, CMO of 2bPrecise, said that precision medicine has moved from a niche with genomics quickly becoming the standard of care, such as in cancer treatment.
ON PROFILE
“At Children’s Hospital of Philadelphia, we know that having a holistic view of our patients is critical to providing the best care possible, based on the most innovative research. Multi-clinical integration is fundamental to achieving this.With Amazon Omics, we are able to extend our understanding of our patients’ health, all the way down to their DNA,” said Jeff Pennington, MSCS , vice president and director of research informatics at Children’s Hospital of Philadelphia, said in the announcement.
Andrea Fox is the senior editor of Healthcare IT News.
Email: [email protected]
Healthcare IT News is a publication of HIMSS.
