Project description
Climate change is increasing the need to develop crops that can withstand drought, heat, salinity, and other environmental stresses. However, identifying the genes underlying these complex traits remains challenging. This project will combine plant genomics, artificial intelligence, and evolutionary biology to integrate multi-omics and functional information across plants and identify genes associated with stress resilience.
The position is part of the Novo Nordisk Foundation Emerging Investigator grant project “Driving innovation in crop resilience through Comparative QTLomics.” The selected candidate will contribute to five main objectives:
1. Apply large language models (LLMs) to collect, extract, and standardise functional information
2. Develop computational tools that integrate evolutionary and functional information using comparative genomics and deep learning approaches
3. Apply these methods across different crops to identify conserved patterns of stress resilience
4. Identify candidate genes associated with key agronomic traits related to resilience
5. Contribute to software and web development
- PhD degree in Bioinformatics, Computational Biology, Computer Science, Mathematics, Physics, or a related field
- Strong experience with programming in Python, R, or similar languages
- Background in machine learning or deep learning methods, including Graph Neural Network (GNN)
- Experience with Large Language Models (LLMs) applied to biological data collection, extraction, and standardization
- Knowledge of multi-omics integration and plant biology is an advantage
- Familiarity with large biological datasets and high-performance computing is desirable
- Ability to work independently and collaboratively in an interdisciplinary research environment
- Proficient in written and spoken English