Converging on cancer seminar series – Dr Maggie Cheang and Dr Pedro Ballester

Please join us for our webinar on the 3rd November 15.00–16.00 at which Professor Axel Behrens (Cancer Research UK Convergence Science Centre Scientific Director) is pleased to host Dr Maggie Cheang and Dr Pedro Ballester.

 

 

 

In this series of webinars brought to you by the Cancer Research UK Convergence Science Centre at Imperial College London and The Institute of Cancer Research, London, researchers across the two organisations will discuss key challenges facing cancer research and opportunities for new convergence science approaches to address these. Join us to consider how novel approaches and technologies could shed light on unresolved problems in cancer biology, to innovate new ways to address challenges in cancer and bring pioneering treatments to cancer patients faster.

 

Hosted by the Convergence Science Centre's Scientific Director Professor Axel Behrens, the series aims to support the Centre's mission to facilitate collaboration between traditionally separate and distinct disciplines.

 

Please join us online on Thursday 3rd November, from 15.00-16.00, for a talk from:

 

Dr Maggie Cheang – Clinical Trials and Statistics Unit, Division of Clinical Studies, The Institute of Cancer Research and The Royal Marsden NHS Foundation Trust

 

“Integrative analysis of multi-omics data in clinical trials to predict treatment response”

 

My group is embedded within the CRUK Clinical Trials and Statistics Unit at The Institute of Cancer Research (ICR-CTSU), and my research passion has always been to identify and develop robust multi-parametric or multi-modal signatures for molecular stratification that would be clinically relevant, by unravelling the tumour complexities and undertaking discovery science within trials. In this presentation, I would discuss, with the aid of a few exemplars, the multidisciplinary approaches that we have applied on understanding the molecular characteristics of tumours to develop better diagnostics tools (e.g. companion diagnostic assay) to pair patients with optimal anti-cancer treatments, informing future trial designs and to tackle the challenges of heterogeneity in treatment response.

 

Dr Maggie Cheang is the Leader of the Integrative genomics analysis in clinical trials at the ICR-CTSU, Division of Clinical Studies, ICR. Her primary research focus is to identify biomarkers that would be clinically relevant. Combining biological knowledge and advanced statistical analytics to model the “omics data” with clinical outcome, her team has been developing multi-parametric molecular classifiers to predict sensitivity and resistance of tumour biological subtype to therapeutic agents and testing the performance of one of these integrated omics/mathematical algorithms within a Phase III clinical trial at this moment. She co-invented the 50 genes-based classifier for the intrinsic subtypes of breast cancer, commonly known as PAM50, which is licensed as Prosigna® and has been implemented into multiple international clinical practice guidelines. She chairs the UK National Cancer Research Institute (NCRI) Clinical Trial Pathology Advisory Group, a group that spearheaded the concept of implementing a multidisciplinary proposal guidance. She also sits on various grant review panels including the MRC/UKRI and Breast Cancer Now scientific grant committee.

 

 

 &

 

 

Dr Pedro Ballester – Department of Bioengineering, Imperial College London

 

“The promise of Artificial Intelligence for Precision Oncology”

 

Inter-patient differences typically result in large drug treatment response variability across patients despite having the same cancer type and being administered the same drug. There is hence a need for computational models able to anticipate which patients will respond to a given drug from data characterising their tumours. Artificial Intelligence (AI) models embody an optimal combination of tumour features able to predict drug response. However, this AI application is notoriously hard at the patient level due to inconsistencies, irrelevance, scarcity and fragmentation of the available datasets. Furthermore, even if these issues could be reduced to a minimum, the resulting supervised learning problems are also challenging, as data is often high-dimensional, class-imbalanced, multi-modal, and biased as well as contains many irrelevant and correlated features. To make things worse, validation shortcomings may grossly overestimate how well the model generalises to patients beyond the study. Here I will overview these issues and how we have addressed them to make progress towards this highly promising, yet challenging, AI application.

 

Dr. Ballester is a Royal Society Wolfson Fellow & Senior Lecturer at Imperial College London, where he heads a group in Artificial Intelligence for Healthcare. Prior to this, he was Assistant Professor at INSERM in France after several postdoctoral fellowships at the University of Oxford, the University of Cambridge and the European Bioinformatics Institute in the UK. His research interests include the development and application of computational approaches for predicting patient response to drug treatments exploiting heterogeneous multi-omics and clinical data sources.

 

 

 

 

 

Registration

 

To receive information about how to access this event please email icr-imperial-convergence.centre@imperial.ac.uk

 

Please note: This webinar is exclusively available only to colleagues across the Institute of Cancer Research, Imperial College London, the Royal Marsden Hospital and Imperial College Healthcare.

 

Load more comments
Comment by from