My institutional context (a research-focused appointment based at CMRI) offers limited opportunity for conventional coursework teaching, so my education contribution is centred on research training: HDR co-supervision, postdoctoral mentoring, thesis examination, and informal mentorship of clinician-researchers and computational early-career researchers. Below is a summary of my current teaching and supervision activities.
Project: Non-invasive diagnosis and classification of nevi and early-stage melanoma combining machine learning with imaging and proteomic data
Computational methodology, model development, data analysis, interpretation. First formal HDR supervision role at the University of Sydney, undertaken after completing the USyd Higher Degree Research Student Supervisor Training Course (2024).
Project: Generative proteomic foundation models with federated learning for multi-hospital cancer research (CINSW Early Career Fellowship)
Research direction, generative AI and multi-omics skills development, mentorship for scientific writing and independent career development. A substantive emerging leadership role in researcher development, building on prior collaborative mentorship.
Project: GAIN-DANN: A Domain-Adversarial Generative Model for Missing Data Imputation in Proteomics
Critical assessment of the written thesis and participation in the oral defence (20-minute presentation followed by 40 minutes of discussion). Invited to this role based on expertise in machine learning for proteomics; the candidate successfully defended her thesis.
Beyond formal roles, a significant part of my education contribution is through mentoring colleagues and emerging researchers at CMRI. I regularly advise clinician-researchers and junior team members on bioinformatic analysis, machine learning approaches, and project design. These mentoring interactions help researchers from clinical and biological backgrounds engage confidently with computational methods outside their original training, contributing to broader capability building in cancer data science.
Mentorship of Dr Emma Boys (medical oncologist and PhD candidate) on machine-learning methods for Cancers of Unknown Primary contributed directly to a co-authored publication in Cancer Discovery (2025).
Ongoing technical guidance for Dr Liz Connolly (medical oncologist and PhD candidate) on bioinformatic analysis, differential expression, and survival analysis for prostate cancer research.
Supported the integration of Dr Di Xiao into the Cancer Data Science team, with guidance on computational platforms and analytical tools.