← Back

A topological map of the genetic components of grapevine-Admixture meets SOMmelier machine learning

General • February 20, 2026

A topological map of the genetic components of grapevine-Admixture meets SOMmelier machine learning is drawing significant interest across the industry.

Author summary Populations are shaped by both evolutionary processes and human activities such as breeding, which is especially evident in cultivated animals and plants. The genetic variation within these populations is encoded in their genomes, and can often be described as a combination of distinct genetic “admixture” components using standard computational approaches. In this study, we ask: How does this admixture-based view of population structure compare to the representation provided by machine-learning–based Self-Organizing Maps (SOMs)? SOMs offer an intuitive way to explore complex molecular data and reveal relationships that might be missed by conventional methods. Using cultivated grapevine as a model—an economically important, globally distributed crop with a long history of domestication—we show that our SOMmelier approach not only recapitulates known genomic components but also constructs a topology-aware genetic landscape. This landscape reflects the geographic distribution of grapevine accessions across Europe and West Asia, and preserves genetic footprints of cultivation history spanning the past 11,000 years. Importantly, SOMmelier both complements and extends genetic admixture analysis, highlighting its potential for broad application in population genetics beyond grapevine.

Experts suggest this could influence future trends and innovation in the sector.

More updates are expected as the story develops.

Related Articles

Source: Original →