New Publication from Binder Lab in PLOS Computational Biology

ABI's Binder Lab has published a new paper in PLOS Computational Biology titled:

“A topological map of the genetic components of grapevine—Admixture meets SOMmelier machine learning.”

In this study, the team explores how natural evolutionary processes and human-driven influences such as domestication and breeding shape genomic variation. Because these complex patterns are not always fully captured by standard methods, the researchers investigated whether machine learning — specifically Self-Organizing Maps (SOMs) — could provide a clearer and more intuitive view of population structure.

Using cultivated grapevine as a model, the study shows that SOMs not only recover known genetic patterns but also generate a genetic “landscape map” reflecting geography across Europe and West Asia, while preserving signals of grapevine cultivation history reaching back approximately 11,000 years.

Overall, the work demonstrates how combining admixture analysis with SOM-based machine learning can support and extend traditional approaches for studying population structure in grapevine and potentially many other species.

Read more here.