Illustration prédire les phénotypes
Prediction
DIGIT-BIO metaprogramme
Themes
Prediction

Prediction

Axis 2: Predicting phenotypes and their responses to changes in stress fields

This axis deals with the prediction of phenotypes from the cell to the individual and population levels, their functionalities and responses to changes in stress fields (biotic and abiotic environment, management methods, practices).

One of the challenges of digital biology is to develop, compare and improve learning methods, adapting them to integrate multi-source data (omics, sensors, environment, data from participatory approaches). The modelling of biological and physiological processes to develop predictive approaches and the simulation of complex biological systems are also major challenges. In particular, the robustness of the models built in axis 1 must be tested by subjecting them to fluctuating conditions (internal or external).

This research includes predictive approaches based on modelling, data assimilation and the coupling of "data-driven" and "concept-driven" approaches, taking into account the essential dimensions of prediction, i.e. planning, quantification of uncertainties and evaluation of forecasts.

Research themes

  • Genomic prediction;
  • Taking account of all transmissible factors in predicting an individual’s potential to transmit characteristics to its descendants;
  • Application of these methods to identify bio-markers for an organism’s state or potential (resistance or stress levels, etc.), and  genetic targets to optimize networks;
  • Predicting the impacts of complex chemical and biological exposure scenarios on physiology;
  • Mobilizing information on states and knowledge of processes, at organism (and sub-organism) levels, to predict the functioning and trajectories of populations at different spatial and/or temporal scales.

Methodological challenges

  • Select the learning methods best suited to a given problem, determining their contributions and limitations for detecting complex structures or weak signals in the data;
  • Build and simulate integrative models with good predictive capabilities, allowing the effects of confounding factors in the data to be identified;
  • Access unobservable quantities through model inversion (e.g. trait value estimation);
  • Improve the quality and robustness of predictions (underlying issues: planning and sampling, uncertainty assessment, taking account of changing environments).

In this folder

EPINIUM © Wirestock, Freepik

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

Know more

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.

Jumeaux numériques de systèmes microbiens © katemangostar, Freepik

Digital twins for microbial systems

Know more

The Arte-mis consortium will bring together an interdisciplinary community of researchers working at the interface between the experimental and digital sciences to overcome methodological barriers to the creation of digital twins in microbial ecology.

Photo vache dans une étable

Improving selection performance in dairy cattle through phenomic selection

Know more

In plant and animal genetics, selection programmes aim to identify individuals whose performance (yield, resistance to disease or environmental stress) meets previously defined criteria. This selection requires the acquisition of data, in the field or in breeding, which can be costly or time-consuming.

cultures d'arabidopsis

Predicting plant response to combined stresses (CO2 and Heat)

Know more

Plants are constantly threatened by biotic and abiotic stresses, especially in the current context of climate change. The complexity of the stress response involves different levels of biological organisation, from genomes to metabolites.

Early categorisation of bovine embryos to boost IVF success

Know more

A major issue in in vitro fertilisation (IVF) is the selection of the "best" embryo, i.e. the one most likely to implant in the uterus. The objective of the BovMovie2Pred consortium is to propose solutions to assist in the selection of bovine embryos in order to increase the percentage of viable births from in vitro produced embryos.

Artificial Intelligence for Cross-Species Genetics in Agronomy

Know more

Thesis by Noémien Maillard (2023 - 2025, UMR GenPhyse).

Machine learning and high-throughput epigenotyping: a new lever to improve phenotype predictions in cattle

Know more

Thesis by Alexandre Asset (BREED /MIA-PS, 2024 - 2026). Building on the work of EPINUM, this thesis proposes to investigate the most appropriate AI approaches that integrate epigenetic data into phenotype prediction models.

Comparative analysis of 3D genomics data

Know more

Thesis by Elise Jorge (GenPhyse, 2023-2025). This thesis, at the interface between statistics, molecular biology and functional genomics, seeks to develop a differential analysis method for Hi-C data to identify regions in the 3-D genome structure where modifications occur.

Deep learning on graphs for morphofunctional analysis and comparison of brains

Know more

Thesis by Antoine Bourlier (PRC, 2022-2025). This thesis seeks to create new algorithms for anato-functional comparison of brain data from growing lambs using both traditional graph theory and new graph-based deep learning methods to study the differences between individuals and over time.

Illustration thèse confinancée

Interoperability and multi-source data integration in metabolomics for the identification common Metabomic Syndrome phenotypes

Know more

Thesis by Elfried Salanon. This thesis sets out to study the developmental trajectories of metabolic syndrome (MetS). This syndrome is increasingly widespread, making it an important issue in public health, especially in older populations suffering from chronic illness and disease.

  • 1 (current)

Modification date: 12 March 2025 | Publication date: 10 January 2022 | By: Com