Research focus

Studying tumour ecology

The main focus of the Yuan lab is to study spatial heterogeneity of the tumour microenvironment. We develop machine learning algorithms for high-throughput pathological image analysis and biinformatics integration. Understanding how genetically diverse cancer cells adapt to their microenvironment is key to appreciating how they develop and evolve. Our work has changed the way we think of the microenvironment and its critical roles in different cancers by studying tumour spatial architecture with spatial statistics.

We are part of the new Centre for Evolution and Cancer at the ICR. The novel concept of tumours as evolving ecosystems may help us understand why cancer is so difficult to treat, and direct new therapeutic interventions - akin to draining the swamps to get rid of mosquitoes as one way of eradicating malaria. We are now working on developing computational approaches to study the influence of tumour microenvironment on cancer progression and evolution.

Through building highly interdisciplinary programmes, our goals are to deliver scientific advances and clinical innovations by dissecting the spatial and molecular heterogeneity of tumour microenvironment, to foster new developments in machine learning for applications in oncology and pathology, and to develop objective methodologies for directing cancer therapeutic strategies.


Deciphering the tumour microenvironment

Histopathological images can provide spatial mapping of the tumour microenvironment. With computer vision technologies, we quantify the spatial dependencies between different types of cells, and use machine learning methods to advance our understanding in intra-tumour heterogeneity which is a major challenge in cancer therapeutics. This integrative study aims to reveal the functional roles of normal cells including fibroblasts and lymphocytes in cancer progression.

Computational pathology to explore tumour spatial dimensions

Cancer and normal cells exhibit both co-operative and competitive relationships, analogous to living organisms. Considering the tumour as an ecological habitat, we use a combination of ecological statistics and medical advances to analyse the ecological relationships in tumours using data derived from tumour histology. This novel way of studying the tumour microenvironment can expand our knowledge of cancer progression and reveal new clinical prognosticators. Read our review paper Computational pathology: Exploring the spatial dimension of tumour ecology
Nawaz S, Yuan Y* Cancer Letters (2015)


Centre for Evolution and Cancer & Division for Molecular Pathology,
The Institute of Cancer Research, London
Centre for Molecular Pathology,
The Royal Marsden Hospital

Selected publications

Relevance of spatial heterogeneity of immune infiltration for predicting risk of recurrence after endocrine therapy of ER+ breast cancer.
Heindl A, Sestak I, Naidoo R, Cuzick J, Dowsett M, Yuan Y*
JNCI (2017)

We provide a missing link between tumour immunity and disease outcome in ER+ disease by examining tumour spatial architecture. The association between immune spatial scores and late recurrence suggests a lasting memory of protumour immunity that may impact disease progression and evolution of endocrine treatment resistance, which may be exploited for therapeutic advances.

Biopsy variability of lymphocytic infiltration in breast cancer subtypes and the ImmunoSkew score.
Khan AM, Yuan Y*
Nature Scientific Reports (2016)

We systematically investigate biopsy variability for the lymphocytic infiltrate in 998 breast tumours using a novel virtual biopsy method. Interestingly, biopsy variability of lymphocytic infiltrate differs considerably among breast cancer subtypes, with the HER2+ subtype having the highest variability.

Microenvironmental heterogeneity parallels breast cancer progression: A histology-genomics integration analysis
Natrajan R, Sailem H, Mardakheh FM, Arias MG, Dowsett M, Bakal C, Yuan Y*
PLOS Medicine (2016) [Sweave; R package beta version]

We propose a clinically relevant role of tumour microenvironmental diversity for advanced breast tumours and highlight that ecological statistics can be translated into medical advances for identifying new biomarkers and for understanding the synergistic interplay between the microenvironment and cancer genomics.