Research projects & supervision summary

My group offers research projects in computational systems biology, with a focus on developing interpretable AI, statistical, and systems biology methods for understanding cell identity, cell-fate decisions, and disease. Projects can be tailored for PhD, Honours, summer research, and visiting students, depending on background and interests. Students with training in statistics, computer science, bioinformatics, data science, molecular biology, biomedical science, and/or related areas are encouraged to enquire.

 

Project Opportunities

Title: Interpretable AI for single-cell, spatial, and multimodal omics

Summary of opportunity:

This project develops interpretable machine-learning and statistical methods for analysing single-cell, spatial and multimodal omics data. The goal is to move beyond prediction alone and identify the genes, regulatory programs and cell states that drive biological outcomes.

Opportunity synopsis:

Students will develop and apply computational models for tasks such as cell-state representation, feature selection, cell-type annotation, data integration, spatial mapping and multimodal learning. Projects may involve deep learning, ensemble learning, statistical modelling, benchmarking and open-source software development. Applications include stem-cell differentiation, organoid systems, disease modelling and therapeutic prioritisation.

 

Project Opportunities

Title: Reconstructing regulatory programs that control cell identity and cell-fate decisions

Summary of opportunity:

This project investigates how molecular programs across signalling, transcriptional, epigenomic and post-transcriptional layers regulate cell identity and cell-fate decisions.

Opportunity synopsis:

Students will analyse multi-omics and trans-omics datasets from stem-cell, progenitor-cell and organoid systems. The project will use computational and statistical methods to reconstruct trans-regulatory networks, identify key regulatory nodes, and model how these programs change during differentiation or disease. The work is suitable for students interested in computational biology, regulatory genomics, machine learning and systems biology.

 

Project Opportunities

Title: Computational modelling of stem-cell and organoid systems

Summary of opportunity:

This project uses single-cell, spatial and multimodal profiling to study stem-cell differentiation, organoid development and organoid fidelity.

Opportunity synopsis:

Students will develop computational approaches to compare organoids with primary tissues, identify molecular controls of differentiation, and assess how experimental protocols influence cell fate, maturation and regional identity. Current applications include retinal organoids, brain organoids and stem-cell-derived disease models. Projects may combine computational analysis with close collaboration with experimental biologists.

 

Project Opportunities

Title: Disease-state modelling and therapeutic prioritisation from omics data

Summary of opportunity:

This project develops computational methods to identify disease-associated cell states and regulatory programs from high-dimensional omics data.

Opportunity synopsis:

Students will work on models that separate disease signals from patient, batch and cohort effects, identify altered pathways across genes and cell types, and connect disease-state programs to candidate regulators or therapeutic interventions. Projects may involve single-cell data, spatial omics, phosphoproteomics, public disease datasets and collaborative experimental studies.

RESEARCH PROJECTS & ACTIVITIES

  • RESEARCH-BASED DEGREE SUPERVISION
    Causal Spatial-Omics for Tissue Programs: Interpretable, Perturbation-Aware Models for Development and Disease
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational methods for single cell omics data analysis
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational statistical methods for data-guided experimental design and analysis in omics studies
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational systems approaches for exploring cell fate dynamics across developmental systems
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational systems approaches for reconstructing trans-regulatory networks for decoding cellular mechanisms
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational systems approaches to spatial and multi-omics analysis of tissues and organoid models
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational Tools For The Integrative Analysis Of Multi-Omics Data To Decipher Trans-Omics Networks
  • RESEARCH-BASED DEGREE SUPERVISION
    Computational-guided stem cell differentiation and organoid generation
  • RESEARCH-BASED DEGREE SUPERVISION
    Deep Learning for Single-cell Omics Data Analysis
  • RESEARCH-BASED DEGREE SUPERVISION
    Deep Learning for Spatiotemporal Biological Systems
  • RESEARCH-BASED DEGREE SUPERVISION
    Developing a Macula in Stem Cell-Derived Human Retinal Organoids
  • RESEARCH-BASED DEGREE SUPERVISION
    Development of statistical methods for integrative omics analysis in precision medicine
  • RESEARCH-BASED DEGREE SUPERVISION
    Efficient Algorithms for Applications in Bio-medical Data Processing
  • RESEARCH-BASED DEGREE SUPERVISION
    Elucidating the role of key signalling pathways in human retina development
  • RESEARCH-BASED DEGREE SUPERVISION
    Identifying Spatially Informative Genes for Cell Mapping and Comparative Analysis
  • RESEARCH-BASED DEGREE SUPERVISION
    Interpretable analytical methods for characterizing disease-associated phenotypic modulation of cells
  • RESEARCH-BASED DEGREE SUPERVISION
    Interpretable deep learning-based approaches for omics
  • RESEARCH-BASED DEGREE SUPERVISION
    Methods towards precision bioinformatics in single cell era
  • RESEARCH-BASED DEGREE SUPERVISION
    Novel deep learning-based methods for improved prediction and feature-learning in high-throughput proteomic and transcriptomic data
  • RESEARCH-BASED DEGREE SUPERVISION
    Pseudo spatial-multi-omics generation method and a framework for deconvolution of spatial multi-omics by cross-modality learning
  • RESEARCH-BASED DEGREE SUPERVISION
    Statistical Modelling for Cell Reprogramming