Australia Centre for AI in Medical Innovation (ACAMI) at La Trobe University - PhD Scholarships

The Australian Centre for Artificial Intelligence in Medical Innovation (ACAMI) is jointly funded by the Victorian State Government and La Trobe University. ACAMI is the world’s first university innovation centre specialising in the application of AI to accelerate the discovery and development of immunotherapies, vaccines and medical innovation, focusing on collaborative research, workforce development and clinical research. It is powered by Australia's first NVIDIA DGX H200 computer. 

Benefits of the scholarship

• a stipend scholarship for three and a half years, with a value of $35,000 per annum, to support your living costs (2025 value)
• a fee-relief scholarship for up to four years 
• opportunities to work with La Trobe's outstanding researchers, and have access to our suite of professional development programs

Available projects

There are six scholarship available with projects outlined below, competitively awarded with selection based on academic merit and suitability to the project. Please contact the lead supervisor for more information about your preferred project.

Project: Accelerating Cardiovascular Disease Risk Prediction with Artificial Intelligence

Scholarship code: SRS-25020

Lead supervisor: Dr Corey Giles

As an applicant, you will be at the forefront of accelerating cardiovascular disease (CVD) risk prediction using artificial intelligence. CVD remains a leading cause of death in Australia and around the world, highlighting the urgent need for improved methods of disease detection and prevention. The primary objectives are to develop AI-driven risk prediction models for incident disease and underlying disease progression, as well as providing new insights into disease processes. This project will leverage the newly established Australian Cardiovascular disease Data Commons.

The Australian Cardiovascular disease Data Commons brings together approximately 400,000 individuals from 18 cohorts nationwide, many with high-dimensional data such as genomics, lipidomics, metabolomics, proteomics, epigenetics, and imaging. As part of this project, you will harness these richly harmonized datasets to create next-generation prediction models, paving the way for high-impact publications and practical clinical applications. Through close collaboration with leading experts in AI, medicine, and data science, you will be uniquely positioned to drive transformative research for the benefit of patients and practitioners alike.

Additional eligibility: 

• open to domestic and international applicants
• applicants must have demonstrated experience in artificial intelligence, machine learning, bioinformatics, biostatisitics, or big-data analytics
• applicants must have proficiency in coding languages such as R or Python and familiarity with high-performance computing environments

In selecting successful applicants, we prioritise applications from candidates who:

• have a background or understanding of cardiovascular disease, 'omics/clinical data analysis, or related life-science field
• have evidence of peer-reviewed publications, conference presentations, or significant research outputs demonstrating capacity for high-impact research.

Project: Leveraging AI to Predict Relapse Risk in Breast Cancer and Colorectal Cancer

Scholarship code: SRS-25021

Lead supervisor: Dr Zhen He

In this project we aim to use AI algorithms to perform a broad sweep for novel biomarkers in breast cancer and colorectal cancer. These biomarkers will allow us to stratify patients into low or high risk groups in terms of cancer relapse risk, which can help guide oncologists develop a treatment plan. Applicants for this project should have a strong interest in applying AI to medical image analysis. 

Additional eligibility: 

• open to domestic and international applicants
• applicants must have a background in computer science and have experience developing AI solutions to solve computer vision problems
• it is desirable for candidates to have experience applying AI solutions to previous digital pathology projects

Project: Rapid Development of Membrane Active Peptides as Next Generation Antibiotics

Scholarship code: SRS-25022

Lead supervisor: Dr Wenyi Li

As an applicant, you should have a strong interest in developing membrane active peptides as next generation antibiotics by using biophysical chemistry with proteins/peptides, computational modelling, machine learning, artificial intelligence etc. Your project will design new approaches to develop peptide antibiotics, a significant and critical field for antibiotic resistance, which substantially impacts our community and Australia's long-term future. 

Additional eligibility:

• open to domestic and international applicants
• applicants must have a good knowledge of chemistry, protein biochemistry, or microbiology
• applicant should also have experience in the programming languages, which will be suitable for machine learning or AI programming

Project: Artificial Intelligence Enabled Medication Adherence Digital Solution

Scholarship code: SRS-25023

Lead Supervisor: Professor Nilmini Wickramasinghe 

As an applicant, you must demonstrate a strong desire to develop skills in digital health and medical innovation powered by AI and ML. In addition, you must demonstrate motivation, a desire to strive for excellence and initiative in this area.

The scholarship will carry an additional possibility to access $2,500 per annum funded under the Optus chair as research support allowance usable for high quality journal publications.

Additional eligibility:

• open to domestic applicants only
• applicants must hold a Bachelor’s or a Master’s degree in Computer Science, Artificial Intelligence, Data Science, Biomedical Engineering, or a related field
• strong academic record with a focus on AI, machine learning, or healthcare technologies

Technical skills:

• proficiency in programming languages such as Python, R, MARLAB or Java
• experience with machine learning frameworks (e.g., TensorFlow, PyTorch)
• knowledge of data analysis and statistical methods

Soft skills:

• design thinking
• strong analytical and problem-solving skills
• excellent written and verbal communication skills
• ability to work independently and as part of a multidisciplinary team

Project: AI-enabled Clinical Decision Support Tool (ACDST) for Predicting Emergency Admissions

Scholarship code: SRS-25024

Lead Supervisor: Professor Damminda Alahakoon

This project will develop an AI-enabled clinical decision support tool to predict whether patients should be admitted or discharged from the Emergency Department based on their presenting complaints, demographics, and clinical manifestations. ACDST aims to improve patient flow by expediting bed allocation, reducing waiting time, and enhancing patient safety and care quality. The project will build upon collaborations between Centre for Data Analytics and Cognition (CDAC), La Trobe University and The Emergency Department of a leading hospital in Melbourne.

As an applicant, you should have interest in working with AI and Machine Learning algorithms, and the application of such algorithms and tools for medical applications. You should also be able to work in teams made up of researchers and practitioners in technology and healthcare domains. 

Additional eligibility:

• open to domestic and international applicants
• applicants must have a background in Artificial Intelligence and Machine Learning. Applicants with NLP and generative AI skills and expertise is given priority
• since the candidate will be required to work in teams across academic and healthcare domains including external researchers and practitioners, very good communication skills (both verbal and written) are important

Project: Neoantigen Identification and mRNA Sequence Design in Cancer Immunotherapy Based on Foundation Models

Scholarship code: SRS-25025

Lead Supervisor: Professor Wei Xiang

Building on the transformative potential of foundation models in Artificial Intelligence (AI), this PhD project pioneers their application in addressing two critical challenges in mRNA-based cancer immunotherapy, namely the special mechanism of cancer cells to avoid detection by the immune system, and the design of proper mRNA sequences from vast expanse of the human genome. Unlike existing approaches with insufficient training data and poor generalizability, the proposed research utilizes large-scale, pre-trained foundation models fine-tuned on multi-modal biomedical data such as large-scale patient and multi-omics data to uncover complex tumor representations and features. The models can develop a broad understanding of tumor features and learn to identify the specific-tumor neoantigens triggering a strong and precise immune response against cancer cells, and are capable of effectively designing and optimizing mRNA sequences tailored to the unique characteristics of cancer cells. Specifically, this PhD project aims to develop novel foundation models achieving accurate and reliable neoantigen identification, and design mRNA sequences for effective and efficient translation, automating the selection of high-performing mRNA candidates for cancer immunotherapy. 

Additional eligibility:

• open to domestic and international applicants
• applicants must have a background in computer science/engineering and have experience developing Graph Neural Networks for computer vision problems
• applicants should understand basic concepts of bioinformatics to investigate AI-driven solutions to cancer immunotherapy problems; and
• applicants should also have strong coding capability with Python or R, and have experience with machine learning frameworks such as PyTorch