Having successfully acquired an ARC Industry Laureate Fellowship valued at approximately $3.95 million from the Australian Research Council (ARC) and $1.5 million from industry, Distinguished Professor Jie Lu’s approach to translating research is based on developing long-term collaborations and aligning her research with industry needs to drive innovation and real-world solutions.
Leveraging research outcomes for long-term partnerships and innovation
Caption
Jie and colleagues were named NSW Merit Recipients in the Technology Platform category of the prestigious iAwards 2025 for advancing healthcare innovation by translating AI into genomics for personalised medicine. From the left: Mr Mark Grosser and Dr Hua Lin from 23Strands, Dr Kairui Guo, Distinguished Professor Jie Lu and Associate Professor Yi Zhang from UTS.
Jie recently shared insights in the UTS Research Cafe from her experience leveraging ARC Laureate Research outcomes and contract research to build strong industry partnerships.
Starting small and building a relationship
Jie began by explaining how she started collaborating with an Australian startup company called 23Strands Pty Ltd about a decade ago. A leading scientist in machine learning, Jie discovered that the company was looking for a way to develop predictive models of associations between genes and diseases.
“I first met the founder of 23Strands Pty Ltd, a genetic research company, when I delivered a seminar at an industry workshop,” Jie said. “After a few years, we met again and talked about potential collaborations.”
The mission of 23Strands Pty Ltd was to find associations with certain diseases from human genes to support clinical staff to identify early warning signs and make informed decisions about personalised health management plans.
Jie began working with them to find machine learning solutions.
Our goal in the project was to develop a model for genomic analysis and personalised recommendations using autonomous machine learning that can deal with huge datasets.
“Our collaboration started with a couple of small contract research projects, and having completed them successfully, we decided to go for an ARC linkage grant.” Jie said.
The team was successful. Their ARC Linkage Project entitled: “Transfer Learning for Genome Analysis and Personalised Recommendation” attracted $700,000 from the ARC and $300,000 from 23Strands.
“Our goal in the project was to develop a model for genomic analysis and personalised recommendations using autonomous machine learning that can deal with huge datasets,” Jie said.
More recently, the partners received funds for a project from the Digital Health Cooperative Research Centre (DHCRC) entitled: “AI for Endometriosis: From Genomics to Personalised Management.”
Transferring knowledge to support predictions
Australia has a very small number of genetic data compared with the UK and the US. Jie and her collaborators proposed developing advanced transfer learning models to transfer knowledge learnt from those countries’ collections in ways that would support Australian predictions.
In the meantime, Jie received a prestigious ARC Laureate Fellowship for a project entitled: “Autonomous learning for decision making in complex situations.” For this project she created a set of autonomous machine learning theories and algorithms to deal with complex data issues.
Now with the support of an esteemed ARC Industry Laureate Fellowship, Jie is leading a project entitled: “Personalised Machine Learning to Support Women’s Quality of Life”.
Using the results of the Linkage project, the CRC project, contract research and her Laureate project, Jie and her team are taking their research further by working with three companies: 23 Strands Pty Ltd, Axis Health Co. Pty Ltd and Australian Women's Health Alliance.
Their interdisciplinary collaboration focuses on developing advanced personalised machine learning that can support women's quality of life.
“We’ll be pioneering new computational technologies to achieve personalised machine learning that supports women’s lifetime health journeys, analysing things like IVF, pregnancy, menopause, and other health data over a woman’s whole life to improve their health outcomes,” Jie said.
Through advanced and human-centred AI approaches, this project will drive genomic association analysis and early states prediction for fertility, pregnancy and post-menopausal issues. It will educate a new generation of emerging scientific leaders and engineers in transformative personalised machine learning methodologies that tackle varied and highly complex data sources.
We’ll be pioneering new computational technologies to achieve personalised machine learning that supports women’s lifetime health journeys, analysing things like IVF, pregnancy, menopause, and other health data over a woman’s whole life to improve their health outcomes.
Jie hopes that the project’s research outcomes will potentially lead to higher impact and lower-cost women’s healthcare service in the future.
Maintaining strong relationships
To ensure that her industry collaborations remain strong, Jie holds regular meetings with her industry partners and team members. She has also asked partner to participate in PhD supervision and place UTS PhD research candidates in their businesses.
“I have found our industry partners are very happy to locate PhD researchers in their companies as they gain so much valuable knowledge from having them there,” she said. “I also invite partners to be co-supervisors of PhD students and co-authors on papers.”
Jie strongly recommends that other researchers working with industry collaborators consider ensuring that their projects involved:
- PhD co-supervision
- PhD co-location
- presentation of joint seminars
- author publications
- joint awards applications and
- joint media releases
- monthly meetings.
“These kinds of arrangements go a long way in keeping relationships strong,” she said.