Computational systems oncology

Computational systems oncology

The Computational systems oncology (CSO) program aims to advance cancer research by making it more quantitative and predictive through the complementary integration of cutting-edge computational modelling, bioinformatics, machine learning and AI with experimental biology.

Cancer is an extraordinarily complex disease where multiple molecular pathways and cellular processes are dysregulated and interlinked through intricate feedback mechanisms. Understanding and treating cancer effectively requires sophisticated computational and data-driven approaches to make sense of unprecedented volumes of molecular and clinical data, from individual cell through to population levels. 

By working deeply and collaboratively with clinical cohorts, experimental platforms, cross-disciplinary collaboration and computational infrastructure, our goal is to foster a synergistic ecosystem that drives breakthrough discoveries and personalised therapeutic strategies for cancer prevention, diagnosis and treatment.

Group Leader - Dr Fuyi Li

Our group specialises in the intersection of Artificial Intelligence (AI) and Big Data in Bioinformatics. Our research revolves around harnessing the power of AI and leveraging Big Data analytics to address various bioinformatics challenges in cancer studies.  By developing AI-driven bioinformatics tools, platforms, software, pipelines, and resources, our research aims to unravel the complexities of cancer and contribute to advancements in the field.

One key aspect of our research involves exploring gene regulation mechanisms in cancer. We aim to uncover the intricate interplay between genetic factors and their impact on cancer development and progression by utilising AI algorithms and analysing large-scale genomic and epigenomic data.  Understanding these mechanisms can provide crucial insights into identifying biomarkers, potential therapeutic targets, and novel treatment strategies.

Additionally, our research focuses on developing innovative approaches for multi-omics data processing in cancer research.  With the integration of diverse omics datasets, such as genomics, transcriptomics, proteomics, and metabolomics, we aim to unravel the complex molecular networks underlying cancer.

By developing advanced machine learning approaches, our research aims to extract meaningful patterns and correlations from multi-omics data, enabling a comprehensive understanding of cancer biology.  Through our research endeavours, we strive to contribute to the field of Bioinformatics by providing novel insights and tools that facilitate precision medicine, personalised therapies, and improved patient outcomes in cancer research and treatment.

Group Leader - Dr Stefano Mangiola

The lab's research is centred on elucidating the intricate interplay between cancer and the immune system through sophisticated multi-omic profiling and advanced computational strategies.

Dr Mangiola and his team employ high-throughput and cutting-edge next-generation technologies, such as spatial and single-cell sequencing, coupled with metabolomics, to intricately map the immune response and trace the pathways of cancer progression and metastasis.

The lab’s focus on modelling the immune tissue and tissue biology through large-scale data modelling will be propelled by novel, highly scalable analysis pipelines and the use of machine learning techniques on demographic-scale datasets.

Group Leader - Professor Lan Nguyen

Cancer cells operate through complex networks of interlinked molecular pathways that control their growth, survival, and response to treatment.  Understanding these intricate networks and predicting their behaviour requires sophisticated approaches that can capture the dynamic interplay between multiple pathways and processes at a systems level.

Our lab develops and applies innovative systems biology approaches that combine predictive mechanistic modelling with experimental validation to tackle major challenges in cancer research.  Our work spans several key areas:  understanding adaptive drug resistance through network remodelling, developing novel combinatorial therapeutic strategies including optimally timed and multi-low-dose approaches, identifying accurate response biomarkers through AI, and advancing personalised treatment through digital twin development.  While our current primary disease focus is breast, prostate and lung cancer, our approaches are applicable across cancer types.  A distinct feature of our lab is the integration of both computational and experimental capabilities under one roof where theory and experiment go hand in hand, enabling powerful and rapid cycles of prediction, validation, and discovery.

We have developed >30 sophisticated models of critical signalling pathways driving important cellular processes, including PI3K-AKT, mTOR, FGFR, MAPK ERK, JNK, Hippo-YAP, Rac-Rho, TGF-b, and more.  Our work has led to several important advances in cancer biology, including the discovery of critical feedback mechanisms controlling cell fate decisions, development of novel algorithms for predicting effective drug combinations, and identification of network-level vulnerabilities in cancer.  Through close collaboration with experimental and clinical partners, we are working to translate these insights into personalised treatment strategies that can improve patient outcomes. Our ultimate goal is to make cancer treatment more precise and predictive through the power of computational systems approaches.

Data Sciences Lead – Dr Simran Kaur 

The Data Sciences Unit within the Computational Systems Oncology program is responsible for data stewardship and provides core biostatistical support, as well as enabling the design, analysis, and interpretation of complex biomedical data with a strong focus on integrative and translational research. The Unit has expertise in the management and analysis of multi-omics datasets, including genomics, proteomics, lipidomics, and metabolomics, and works closely with researchers to ensure robust study design, reproducibility, and statistical inference.

Key Focus Areas:

  • Integration and analysis of multi-omics datasets across diverse study designs.
  • Application of advanced statistical and computational methods (e.g. longitudinal modelling, genetic association studies).
  • Data management, harmonisation, and reproducible workflow development.
  • Support for study design, power calculations, and rigorous statistical analysis.
  • Contribution to translational research, including biomarker discovery and patient stratification.
  • Training and capacity building in bioinformatics, biostatistics, and data science for students and researchers.