Deep learning for molecular and cellular biology

Back to campaign's jobs listing

INRAE presentation

INRAE, the French National Research Institute for Agriculture, Food, and Environment, is a public research organization bringing together 12,000 employees across 272 units in 18 centers across France. As the world’s leading institute specializing in agriculture, food, and the environment, INRAE plays a key role in supporting the necessary transitions to address global challenges.

Faced with population growth, food security challenges, climate change, resource depletion, and biodiversity loss, INRAE is committed to developing scientific solutions and supporting the evolution of agricultural, food, and environmental practices.

Work environment, missions and activities

Context and partnerships
The project is part of an initiative to drive the development of artificial intelligence (AI), particularly deep learning, and to strengthen capabilities in modelling complex systems (INRAE 2030 SP 5.2 (https://www.inrae.fr/en/about-us/inrae2030) and the DIGIT-BIO metaprogramme (https://eng-digitbio.hub.inrae.fr/digit-bio-metaprogramme)). Deep learning methods and generative models are advancing rapidly in the fields of molecular biology, synthetic biology and sequence analysis, helping to address complex questions in ways never before possible such as predicting protein structures, genotype-phenotype prediction and, in particular, predicting the effects of sequence variants. They may open up new avenues to assist the challenges posed by the agro-ecological transition in the context of climate change. Spinoffs are likely in most of the other Scientific Priorities (SPs) identified by INRAE 2030, and in particular, within the framework of this Junior Professorship (JP) focused on applications at molecular level, in SPs 1.1 and 2.2 (supporting the transition of crop systems and livestock farming through a better understanding of biological regulation), and SP 3.1 (supporting the creation of innovative biocatalytic systems / green chemistry). The JP’s research theme is integrated into the major scientific priorities of the MathNum research division’s strategic plan, in particular the priority centred on data and its processing. This chair project aims to facilitate the integration of the extremely rapid developments in the field to address questions in the fields of synthetic biology or relating to the understanding of the molecular mechanisms, while also addressing the specific challenges posed by the data generated within the INRAE context (such as the need to transfer data and models obtained from model organisms). It naturally falls within the field of probability, statistics and machine learning, an area in which the Toulouse Applied Mathematics and Computer Science (MIAT) Research Unit possesses considerable expertise, with a distinct and growing focus on deep learning approaches. The MIAT research unit is organised into four thematic areas, and this JP falls within the Computational Biology (BioComp) area. BioComp raises specific questions relating to the study of DNA/RNA sequences, for which large language models are effective. Whilst BioComp is already conducting research in the field of deep learning (graph neural networks, generative AI models, and applications in signal processing or genome assembly), it lacks a person with cutting-edge scientific expertise in deep learning at the intersection between statistics and computer science, as well as proven expertise in genomics, and the ability to develop new methods. 

Nature and purpose of the research project
Neural networks deliver unprecedented performance across a range of topics of interest to INRAE: automatic genome annotation, image analysis for high-throughput phenotyping, or analysis of Nanopore sequencing signals, prediction of the impact of genome mutations, or learning the sequence-structure-function relationships of proteins. However, the field of AI is evolving rapidly making it difficult keeping up to date with the latest knowledge. Your work will focus in the long term on these technological and methodological developments, which will provide realistic support for the unit’s commitment to this area. You are a mathematician or computer scientist with strong skills in AI (e.g. generative AI, transfer learning or physics-informed AI models), and proven experience in bioinformatics (genome functions, particularly in animals or plants, systems biology, etc.). Nature and purpose of the teaching project You will help meet the growing demand for teaching in AI in the Toulouse region. Several local educational institutions (INSA, ISAE Supaéro, the Department of Mathematics at the University of Toulouse, and the Master's degree in Bioinformatics at the University of Toulouse) have formally expressed their interest in hosting all or part of the teaching provided by the successful candidate, covering topics such as machine learning, deep learning and machine learning for bioinformatics. 

Funding and related resources 
ANR Package : €200 000 
INRAE Package : €100 000 
Others : €60 0000 
Total : €360 000

Within the framework of your activities, you will be required to travel within France and abroad. You will be required to take on responsibilities within national, European and international networks and projects.

Training and skills

You hold a PhD in statistics or computer science, specialising in Artificial Intelligence. You are recognised for your work in the field of statistical learning or deep learning (e.g. generative AI, transfer learning or physics-informed AI models). You have proven experience in bioinformatics (e.g. genome function, particularly in animals or plants, systems biology). You have considerable experience in research, as well as experience in developing and managing projects. A keen interest in research at the interface is essential. You enjoy working as part of a team and have excellent interpersonal skills; you show initiative and can work independently.

INRAE's life quality

By joining our teams, you benefit from:

- 30 days of annual leave + 15 days "Reduction of Working Time" (for a full time);
- parenting support: CESU childcare, leisure services;
- skills development systems: training, career advise;
- social support: advice and listening, social assistance and loans;
- holiday and leisure services: holiday vouchers, accommodation at preferential rates;
- sports and cultural activities;
- collective catering.

International scientists, please visit your guide to facilitate your arrival and stay at INRAE.

Type of contract

Tenure-Track Junior Professor Chair enables recruitment of scientists based on a research and teaching project that lasts three years. At the end of this period, and following an assessment of your scientific achievements and professional capabilities, you may obtain a full-tenure position as Research Director (DR2).

A research and teaching agreement will specify the path you will follow towards full-tenure and enable you to acquire the qualifications necessary to become a full-tenure Research Director in your field.

You have until June 22, 2026 to submit your application. Only candidates previously selected on file by the selection committee will be invited to the hearing.

How to apply

1. I download the applicant guide Guide for applicants pdf - 5.06 MB
2. I note the profile number CPJ26-MATHNUM-1
3. I apply GO