AWS paves the way for advanced genetic research at scale with Amazon Omics

Amazon Web Services Inc. said today it is doubling down on genetics research with the launch of a new purpose-built service called Amazon Omics.

Announced at AWS re:Invent, Amazon Omics is designed to help healthcare providers and life science organizations store, query, and analyze genomics, transcriptomics, and other types of “omics” data, and then generate information that can help improve health and advance scientific discovery.

In a blog post, AWS Senior Developer Counsel Channy Yun explained that healthcare and life sciences companies typically collect myriad types of biological data, with the goal of use this information to improve patient care and advance scientific research. This is a study that connoisseurs call “omics”.

“These organizations map an individual’s genetic predisposition to disease, identify new drug targets based on protein structure and function, profile tumors based on genes expressed in a specific cell, or study how gut bacteria can influence human health,” Yun explained.

The value of omics is that by collecting genetic data from thousands of individuals, comparing and analyzing it, researchers can generate new information to predict disease as well as the effectiveness of various different drugs and treatments. . Omics are therefore essential to advance medical research and drug discovery.

The big problem with omics research is that, by necessity, it has to be done on a large scale. This can cause problems for healthcare companies and life science organizations that are not equipped to deal with it.

“There are so many complexities with this kind of data,” Taha Kass-Hout, AWS Chief Medical Officer and Vice President of AI Technology Health, told SiliconANGLE in an interview. “This explosion of data around the biology of the cell is beyond the human capacity to understand.”

Omics research involves juggling petabytes of data, so researchers need a cost-effective way to store this information and an easy way to access it. “You need to scale the computation across millions of biological samples while maintaining accuracy and reliability,” Yun said. “You also need specialized tools to analyze genetic patterns in populations and train machine learning models to predict disease.”

This is where AWS believes it can make a difference with Amazon Omics, which is designed to support large-scale analysis and collaborative research on omics data. Not only does it provide an efficient way to store this information, but researchers can easily tap into other AWS services to analyze genomic data from entire populations. Amazon Omics also automates the provisioning and scaling of bioinformatics workflows, allowing researchers to run large-scale analysis pipelines.

The service, intended for bioinformaticians, researchers and scientists, has three main components. It offers omics-optimized object storage to store and share data efficiently at lower cost; managed computation for bioinformatics workflows, simplifying data analysis; and data stores optimized to enable population-wide variant analysis.

Amazon Omics is really about enabling analytics, and to that end it’s compatible with services like Amazon SageMaker, which can be used to train machine learning models for very specific purposes. For example, users can train machine learning models to analyze omics data and predict whether certain individuals might be predisposed to certain types of diseases. It’s also possible to combine an individual’s genomic data with their medical history in Amazon HealthLake, Amazon said.

Amazon Omics is now available in the US East (N. Virginia), US West (Oregon), Asia Pacific (Singapore), Europe (Frankfurt), Europe (Ireland), and Europe (London) regions of AWS.

With reporting by Robert Hof

Photo: WangXiNa/Freepik