18/06/2026
"It assumes that gene effects are additive and model environments as discrete categories instead of giving them full environmental covariates. So in reality, things can be much messier. Interactions between genes, interactions between genes and environment is not generally linear. And can involve complex combinations. And that is where machine learning and deep learning come into picture. This gap can be filled by that."
In the first episode of our new “Make Sense of Science” explainer series, a new podcast format for breaking down complex topics in a clear and accessible way, Computomics machine learning scientist Alaukik Saxena explains why genomic prediction in plant breeding is not as simple as it may sound.
Classical statistical models remain highly valuable, but they can reach their limits when biology and environment interact in more complex ways. This is where machine learning and deep learning can help fill the gap.
Listen to the episode to learn more about deep learning for genomic prediction in plant breeding. 🎧 👉 https://www.computomics.com/news-reader/podcast-s7e10.html