Discover how a deep learning algorithm, GIInger™, leverages low-coverage sequencing data to identify homologous recombination deficiency (HRD)-induced genomic instability.
We’re often asked how we avoid overfitting when developing predictive machine learning models for clinical research. This technical note explains how.
Capturing the complexity of human health and disease through machine learning analysis of multimodal data has the potential to drive the future of healthcare.
Companion Diagnostics (CDx) are important tools in the practice and application of precision medicine. This introductory blog provides an overview of their development through clinical trials, regulatory implications, and clinical utility.
SOPHiA GENETICS™ is excited to participate in the "9ème congrès de la SFMPP" taking place...
Deep learning-based approaches to genomic instability assessment can help overcome the limitations of current methods and maximize insights from tumor samples.
This guide deciphers the jargon associated with machine learning in healthcare and explains why artificial intelligence is invaluable to revolutionize the capabilities of HCPs in improving patient care.
SOPHiA GENETICS™ is excited to be a part of the Healthcare Information and Management Systems...
Every person is unique. We can clearly see this within the more than one million genomic profiles from 70 different countries analyzed by our technology.
Learn about the technology behind the SOPHiA DDM™ Homologous Recombination Deficiency (HRD) Solution from the lead developer, Dr. Christian Pozzorini.
Larger panels may cast wider nets, but optimization with patented algorithms through our universal platform gives more actionable insights without sacrificing data quality.
By leveraging expertly curated evidence, powered by JAX-CKB, and SOPHiA GENETICS’ patented algorithms through the SOPHiA DDM platform, users can then use OncoPortal™ Plus to accurately identify clinical associations and actionable biomarker profiles.
