Artificial Intelligence/Deep Learning to Develop Risk Score for Glaucoma

Project Code: 10477471

Faculty: Faculty of Medical and Health Sciences

Department: Ophthalmology

Main Supervisor: Professor Helen Danesh-Meyer

Application open date: 05 Jul 2021

Application deadline:

Enrolment information: NZ Citizens, NZ Permanent Residents, International


Every individual has an underlying genetic susceptibility for disease. The successful applicant will use machine learning to utilise large international datasets to predict, from thousands of environmental, physical, and biological parameters (including genetics), the clinically relevant features which best predict risk for glaucoma and predict disease progression. Predicting risk from such alterations is fundamentally and technically challenging (combinatorically enormous number of ways that a genome can be altered), but our successfully established computational/bioinformatic approaches provide functional interpretation of the impact of genetic variation to identify personalised risk factors.

This project will be supervised by Professor Helen Danesh-Meyer (Ophthalmology, University of Auckland, New Zealand) and Dr William Schierding (Liggins Institute, University of Auckland, New Zealand), as part of a very productive and supportive research team.

What we are looking for in a successful applicant

Applicants should have a demonstrated background or eagerness to learn genetics, bioinformatics, statistics, or related subjects. Applicants must fulfil all conditions for admission to the doctoral programme at the University of Auckland.


1. Identify potential mutations that can act as drivers influencing glaucoma susceptibility, initiation, and progression.

2. Extend previously developed computational approaches (machine learning) to predict, from thousands of genomes, which genomic elements contribute the most to glaucoma risk.

3. Provide a functional interpretation of the impact of genetic variation, genome structure, and gene expression to identify personalised risk factors.

4. Translate the new molecular understanding into risk prediction (diagnostic reports) that can be used in clinical practice.

Other information

Applications should include a full CV, an academic transcript, and a cover letter outlining your interests in relation to our research. Applications will close once a suitable applicant has been identified, so please submit your application soon.