Genomics and Machine Learning Lab

The Genomics and Machine Learning Lab (GML) studies cancer and infected tissues in patient samples and mouse models. They generate novel data from spatial and single cell technologies and develop new computational and statical methods to find clinically important patterns from this complex data. They pioneered the merging of two big data fields, sequencing, and imaging, to advance understanding of pathological processes one cell at a time and across all cells within a diseased tissue. By mapping cell types, their spatial organisation and cell-cell interactions in tissues, GML focuses on discovering new patterns and cellular regulation mechanisms that are hidden from traditional research approaches. Examples of outcomes include cell and gene markers for predicting cancer progression risks, stratifying disease subtypes, discovering new drug targets to modulate the immune systems, and adding new capabilities for prioritising drugs most effective to each patient.

 

CURRENT RESEARCH

  • Developing next generation machine learning for diagnosis and prognosis from integrating spatial sequencing data and histopathological images (Spatial Cellular Pathology)
  • Predicting metastasis and disease progression using spatial data
  • Discovering new immunotherapy drug targets using ligand-receptor screening from spatial and single cell data
  • Studying neuroinflammation across space and time in the injury context (e.g., spinal cord injury, traumatic brain injury), and in aging context (e.g., neuronal degenerative diseases)
  • Developing spatial multiomics technologies and computational methods to integrate spatial data with single cell and genomics data.
  • Aging related neuronal degenerative diseases
  • Brain cancer
  • Breast cancer
  • Colorectal cancer
  • Infection: studying virus infected tissues (e.g., Covid lung tissues, HPV infected tissues)
  • Neuroinflammation: spinal cord injury, traumatic brain injury, motor neural diseases
  • Skin cancer

Staff

  • Dr Albert Xiong, Lab manager
  • Andrew Causer, Affiliate
  • Andrew Su, PhD Student (non-review)
  • Chi Trung Ha, Affiliate
  • Claire Cheng, PhD Student (Non-Review)
  • Eun Ju Kim, Affiliate
  • Feng Zhang, Visiting Student
  • Gianna Pavillion, Student
  • Hani Vu, Affiliate
  • Hsu-Yao Chao, Student
  • Jacky Xie, Affiliate
  • Lai-Ying Zhang, PhD Student
  • Levi Hockey, Affiliate
  • Onkar Mulay, PhD Student (Non-Review)
  • Prakrithi Pavithra, PhD Student (Non-Review)
  • Samual Macdonald, Affiliate
  • Wilson Cheng-Han Wang, Visiting Student
  • Dr Xiao Tan, Affiliate
  • Xinnan Jin, PhD Student (Non-Review)
  • Yuanhao Jiang, Affiliate
  • Yuyang Li, PhD Student (Non-Review)

Internal Collaborators

  • Professor Vicki Whitehall
  • Assoc Professor Simon Phipps
  • Dr Lachlan Harris
  • Andrew Masel
  • Professor Bryan Day
  • Professor Christian Engwerda
  • Katia Nones
  • Paul Collins
  • Nigel Waterhouse
  • Professor Sudha Rao

External Collaborators

  • Ankur Sharma
  • Andrew Barbour
  • Brandon Wainwright
  • Christian Nefzger
  • Di Yu
  • Grant Montgomery
  • Hanlee Ji
  • Ian Frazer
  • Kiarash Khosrotehrani
  • Joseph Powell
  • Jessica Mar
  • Nathan Palpant
  • Marc Ruitenberg
  • Pete Simpson
  • Spatial industry partners
  • NHMRC Investigator Grant
  • NHMRC Ideas Grant
  • National Breast Cancer Foundation
  • Cancer Council Queensland
  • Australia Research Council
  • Pharmaceutical companies and Industry partners
  • US Department of Defence
  • WingForLife Foundation

STUDENT PROJECTS

Machine learning analysis of imaging and sequencing data for cancer diagnosis and prognosis.

This project is suitable for students with experience in computational programming, with a good theoretical background in statistics and machine learning, and are familiar with sequencing data and imaging data.  BACKGROUND Almost all suspected cancer patients undergo tissue biopsies stained and examined by pathologists using light microscopy. This method is highly variable, blind to cancer […]

Find Out More