DNA sequence deep learning to map genome-wide genetic variants underlying complex traits and disease

This project aims to develop and apply new methods for identifying genetic variants that are causal for human traits and diseases.

The primary approach will focus on leveraging DNA foundational models to improve the prioritisation of such variants. Training of DNA foundational models, especially when coupled with other sources of data (e.g., protein-level data), is notoriously computationally challenging. Throughout the project, you will, therefore, develop and optimise GPU parallelisation and sub-network isolation to run inference across the entire genome.

Beyond optimisation, you will also develop new methods to quantify (prior to training) information content in a given dataset. This work will build nonlinear mixed models literature.

Finally, the project will integrate predictions from DNA foundational models into various statistical genetics analyses such as polygenic scores and fine-mapping.

You will join the Statistical Genomics Laboratory led by Professor Yengo (Snow Fellow) to conduct cutting-edge research at the intersection of data science and human genetics.

The mission of the Yengo lab is to improve prevention and treatment of common disease by discovering genes and biological pathways involved in the etiology of human complex traits.

The Yengo lab develops scalable analysis tools that can maximise the utility of genetics studies across all human populations. These tools are generally applied to analyse large scale biobank datasets available worldwide.

The project will be a unique opportunity for an outstanding and curious mind to grow an international profile in statistical genetics.  

This project is supported by the Research project scholarship.

Learn more about the Research project scholarship.

Your application will be assessed on a competitive basis.

We take into account your:

• previous academic record
• publication record
• honours and awards
• employment history.

A working knowledge of genome-wide association studies and Python programming would be of benefit to someone working on this project.

You will demonstrate academic achievement in the fields of bioinformatics, statistical genetics, and/or machine learning and the potential for scholastic success.

A background or knowledge of Pytorch for neural network architectures/training is highly desirable.

You must submit an expression of interest (EOI) by 25 September, 2026 25 September, 2026.

Before you apply

1. Check your eligibility for the Doctor of Philosophy (PhD).
2. Prepare your documentation.
3. If you have any questions about whether the project is suitable for your research interests, contact Professor Loic Yengo (l.yengo@uq.edu.au).

When you apply

To apply, submit an expression of interest (EOI) for the program. You don't need to apply separately for the project or scholarship. How to submit an EOI

In your EOI, complete the ‘Scholarship/Sponsorship’ section with the following details:

1. Are you applying for an advertised project: 'Yes'
2. Project: 'Research project scholarship'
3. Scholarship Code Listed in the Advertisement: TRAITS-YENGO
4. Link to Scholarship Advertisement: https://study.uq.edu.au/study-options/phd-mphil-professional-doctorate/projects/dna-sequence-deep-learning-map-genome-wide-genetic-variants-underlying-complex-traits-and-disease

Submit an EOI