SOPHiA GENETICS™ celebrated a significant milestone, reaching 1 million genomic profiles analyzed by our data analytics platform SOPHiA DDM™. While this certainly marked a meaningful achievement for us as a company, it has even greater significance for the accuracy of our machine-learning pipelines.
Our decentralized model has generated data in over 70 countries, adding diversity to our database and enabling the platform to identify variants not present in other reference databases. Nearly 19% of valuable variants identified by SOPHIA DDM™ are yet to be identified in other databases. We asked some of our internal experts how this exposure to such a vast genomic data set impacts our algorithms.
First, we chatted with Emily Paul, PhD, a Product Director on our Platform team, leading enhancements to SOPHiA DDM™. Emily expressed that the 1 million genomic profiles milestone is significant in three ways:
- Growth of the community
- Exposure to more variants
- Identification of rare variants
Sequencing 1 million profiles would not have been possible without our growing community of institutions embracing next-generation sequencing (NGS). As the access to NGS testing increases, sharing knowledge worldwide also becomes possible. With 1 million profiles sequenced, the platform has seen exponentially more variants, increasing the possibility of identifying those with previously unknown significance through community flagging. This large amount of data provides our machine learning algorithms with an additional source of information, allowing them to identify variants that would not traditionally be flagged. This milestone increases the platform’s exposure to a vast number of variants. It strengthens the power of SOPHiA DDM™,leading to better detection and enhanced classification of rare variants, which can result in better patient outcomes.”
We were also able to catch up with Zhenyu Xu, PhD, Chief Scientific Officer at SOPHiA GENETICS™. We asked him what the 1 million profiles mean for the platform and how valuable he sees this data.
These 1 million genomic profiles capture the bias inherent to different NGS technologies and library preparation methodologies, as well as the diversity of ethnicities and diseases. Together, they give our algorithms access to a wealth of information, allowing for a more comprehensive understanding of the relationship between genetic diversity and pathology. They also empower us to build more robust cohorts for future research. As a result, we have fine-tuned our pipelines for more precise analyses and can now pinpoint individual profiles for our customers faster and more efficiently.
We are proud of this accomplishment and excited about how we can use this information to create more accurate analytical pipelines to support your research. You can learn more about SOPHiA DDM™ here.
