EPINIUM © Wirestock, Freepik
EPINUM Consortium (2024-2026)

Machine learning and high throughput epigenotyping: a new lever to improve phenotype prediction in cattle?

Hit by the impacts of a changing climate, cattle farming must adapt to changes in agro-ecological practices. To meet these challenges, a new generation of finely tuned, rapid and minimally invasive phenotyping tools must be developed to ensure the continued compatibility of animal/environment pairings. The EPINUM consortium proposes to deploy machine learning approaches to improve phenotypic prediction based on epigenotyping data.

Context and key challenges

Epigenetic modifications are molecular processes that have to potential to influence the phenotypic variability of individuals in the course of their lives, from the periconceptional period onwards. Their study enables us to understand the effects of environment on the functioning of the genome. The epigenetic monitoring of animals could thus be of use in the development of management recommendations to support agro-ecological transition while optimising the profitability and sustainability of livestock farms.
The EPINUM pathway will assess the potential of machine learning approaches for the improvement of phenotypic prediction based on epigenotyping data.

Goals and methodology

The EPINUM consortium will build on the work of the H2020 RUMIGEN programme that addresses the impact of climate change on ruminant farming. It will make use of a DNA methylation data set obtained using an epigenotyping chip in 5,500 cattle during the RUMIGEN project.

The methodological challenges will be to:

  • select the learning methods best suited to the data that has been generated;
  • build predictive models integrating genetic and epigenetic information;
  • assess the quality and robustness of predictions based on one of the largest cohorts ever used to generate epigenetic data, through reference to quantitative genetic models.

This interdisciplinary collaboration, combining skills in epigenetics (BREED, Eliance), modelling and machine learning (MIA-PS, Eliance), quantitative genetics (GABI) and benefiting from access to biological resources (Eliance), will enable us to meet the methodological challenge presented by the size, structure and distribution of epigenotyping data, along with the biological challenges associated with the role of DNA methylation in the construction of phenotypes.

The project is expected to help dairy herds to realise their potential through the introduction of new criteria based on the epigenome. The ultimate goal is to develop new tools to help dairy herds adapt to the changed environmental conditions resulting from agro-ecological transition and climate change.

Contact

Participating INRAE units and external partners 

INRAE participating units

Scientific divisions Research unitsExpertise
PHASEUMR BREEDEpigenetics, reproductive biology
GAUMR GABIQuantitative genetics
MathNumMIA Paris-SaclayStatistical modelling, machine learning, prediction

External partners

Institution/organisationExpertise
Eliance fédérationEpigenetics, data analysis, access to biological resources