Show side menu

GenoDrawing, an AI tool for predicting complex traits in plants

Image of the GenoDrawing software (Photo: CRAG).

A scientific team led by María José Aranzana, researcher from IRTA, has developed a tool that can predict the shape of apples from their genetic markers

The software uses Deep Learning to analyse complex traits, which are difficult to measure with traditional methods

The study demonstrates the potential of AI for advancing plant breeding and agriculture

A team of researchers led by María José Aranzana, a researcher from the Institute of Research and Technology in Food and Agriculture (IRTA) and head of the Genomics and Biotechnology program at the Center for Research in Agrigenomics (CRAG), has developed an innovative tool based on generative artificial intelligence to predict complex traits in plants.

The tool, named GenoDrawing, introduces a new methodology that predicts the physical traits of an apple variety from its genetic information, generating images that closely resemble reality. The study has been published in the journal Plant Phenomics.

The researchers used a deep learning approach – or machine learning – to train the GenoDrawing model on a dataset of more than 10,000 images of apples and their genetic information (SNP markers), and then tested its effectiveness on a separate dataset.

The results show that GenoDrawing is capable of predicting the shape of apples and reproducing it in images based solely on information from SNP markers with high accuracy.

Collage with stock apple image, DNA pipetting, and the GenoDrawing software (Credit: CRAG).

One of the advantages of GenoDrawing is that it can be used to predict a complex trait, such as shape, and could potentially predict other characteristics, such as color, leaf morphology, or plant architecture, in future studies.

This is important because traditional plant phenotyping methods, such as visual inspection, are slow and expensive and may not provide accurate results.

Furthermore, GenoDrawing allows researchers to quickly and easily predict plant traits without the need to grow them or wait for them to bear fruit, which could lead to more efficient and effective breeding programs.

A tool with multiple applications

The researchers emphasized that the power of GenoDrawing relies in the utilization of AI: “Our study shows that AI can be used in new ways to link visual and genetic information thus predicting complex traits in plants”
states Federico Jurado-Ruiz, the first author of the published manuscript.

Dr. Aranzana is confident in the potency of the tool: “We believe that this tool could have a wide range of applications, not only in plant breeding and agriculture but also in different fields of life research, and we look forward to exploring its potential in future research.”

The use of generative AI in the GenoDrawing tool represents a significant step forward in the field of plant phenotyping and breeding. The scientific team of this project hopes now that their work will inspire new research and will lead to new advances in the field of agriculture.