21/05/2026
"When you have a candidate that you have DNA fingerprints on, and you try to predict the performance of that candidate based on other individuals that have the same DNA fingerprints, and you also have evaluated out in the field, the initial focus was to try to use machine learning to predict, yield, predict moisture, predict plant height, predict other traits. So basically, doing the same things that we already do and trying to see if we can do it better. And now we're working into realms of, well, can we actually predict what a breeder would select? Can we do that? And our answer is yes." 🧬🤖
In this episode of the Computomics podcast, Dr. Rex Bernardo discusses the evolution of predictive plant breeding, from early molecular markers to today’s machine learning and AI approaches. He explains how these tools can support not only trait prediction, but also more complex breeding decisions, such as whether a line is likely to be selected or become a successful variety. The conversation also highlights community-focused work on leafy African vegetables in Minnesota. It reflects on how plant breeding education must evolve to prepare future breeders for a more interdisciplinary, data-driven field.
Listen to the conversation on new technologies and not leaving anyone behind 🎧 👉 https://www.computomics.com/news-reader/podcast-s7e9.html
