Computomics is presenting at the online 21st EUCARPIA General Congress

Computomics is excited to present at the EUCARPIA Congress!

The European Association for Plant Breeding (EUCARPIA), is a scientific association with the primary goal of fostering international cooperation in the field of plant breeding. Although primarily focused on Europe, EUCARPIA has gained worldwide recognition and is one of a kind.  About 1,000 members across the globe are active in the diverse disciplines of science-based plant breeding, including molecular genetics, practical plant breeding, variety testing and seed commerce.

The General Congress 2021
EUCARPIA’s main event – the General Congress – is held every four years at different locations. As a result of the corona crisis, EUCARPIA had to postpone the 2020 Congress for one year. The General Congress will now be held online at 23-26 August 2021. On this occasion, experts and researchers from all over the world will present and discuss their findings and visions for meeting the great challenges that plant breeding will face in the next decades to integrate the many new technologies, skills and human experience into coherent breeding strategies under the theme: Breeding: the key to innovative solutions.

Dr. Sebastian Schultheiss, Managing Director of Computomics will speak on Wednesday, 25 August 2021 at 13:45 - 14:05 about:

"Higher-order Machine Learning Models Act as an Approximation of Biological Regulatory Mechanisms"

Abstract:
Plant breeding needs to accelerate to supply new varieties for a growing population and a rapidly changing climate. New breeding technologies like gene editing and genomic prediction help bring about this acceleration, but are often used independently without sharing useful preexisting knowledge. Here, we present a method for discovering both new gene editing targets and higher-accuracy predictions. By using interpretable machine learning models specifically developed for genomic data, complex genetic mechanisms can be rapidly understood and visualized. Multi-genic traits show up in the visualization of feature importance and positional genomic importance. We apply this method to a dataset derived from a shelf-life experiments for 200 Capsicum varieties. Genotypes, manual scoring and plant image data is correlated to train a regression machine learning algorithm that identifies an ethylene-linked gene cluster responsible for shelf life and plant senescence. New breeding technologies require these kinds of insights into biological regulation to identify new editing targets quickly and reliably.

All details including the full program and registration can be found here.

In case you have questions about our machine learning technology please reach out to us.

Go back