Predicting response in cancer patients using machine learning models

Current clinical decision making for colorectal cancer (CRC) patients is based on a relatively small number of clinical and pathological hallmarks. Developments in the cost effectiveness and robustness of genome-wide molecular phenotyping greatly expand the number of features that can feed into decision making. The Computational Biology and Integrative Genomics Lab and associated researchers in the Bioinformatics Hub, use machine learning to develop and validate clinical classifiers, based on multi-omic data, which can predict treatment response for cancer patients. If successful, this would allow treatment to be individually tailored, meaning that patients receive the most effective treatment in the first instance.

Recently, Dr. Sanjay Rathee, postdoctoral working under the direction of Prof. Francesca Buffa, developed a model to predict treatment response for CRC patients undergoing chemotherapy, radiotherapy, and oxaliplatin treatment using data from the S:CORT consortium led by Prof. Tim Maughan. Looking at concordant predictions between different methods, this approach addresses the challenge of discovering decision-making genes with minimum noise, ensuring models are general and reliable.

In the first analysis of S:CORT samples (131 rectal cancer samples) from patients treated with radiotherapy and capecitabine, the model gives an accuracy of 90%. Whilst initial accuracy is quite high on retrospective cohorts, the results needs to be validated in external, independent cohorts. If validated, the model could predict response for a new patient based on a pre-treatment biopsy. Finding out whether a treatment is likely to be effective could greatly minimise the number of unnecessary interventions and associated side effects (and cost) whilst also increasing the chance of the chosen intervention being an effective treatment strategy.

Find out more about our research below

Breast tissue growing in the new hydrogel

New hydrogel technology has promise in breast cancer modelling

A new hydrogel technology from the Farnie group has provided cancer researchers with a new way to faithfully model breast tumours and discover new therapeutic targets

Using big data in breast cancer research

The Cancer Epidemiology Unit has been using the largest epidemiological data set of its kind to unlock the secrets of breast cancer, what can be done to prevent it, and which women are most likely to develop it

Funding boost for OxPLoreD early detection study

UK Research and Innovation provides additional funds for whole genome sequencing as part of the OxPLoreD programme of research into high-risk conditions for blood cancer

A new FRONTIER for breast cancer

Latest news from FRONTIER, the trial investigating the potential of the radiotracer Fluciclovine in the subtyping and staging of breast cancers

Oxfordshire-based SCAN pathway wins BMJ award

A pathway designed to investigate individuals with non-specific but concerning symptoms of cancer wins the BMJ Awards 2020 Cancer Care Team of the Year

Understanding breast cancer management in women of different ethnicities

Dr Toral Gathani investigates the associations between ethnicity and the surgical management of breast cancer, to help understand any observed differences in patterns of treatment in women of different ethnic groups.

Prof. Ellie Barnes comments on the 2020 Nobel Prize for Medicine

Prof Ellie Barnes comments on the recent Nobel Prize in Medicine, awarded to Harvey J. Alter, Michael Houghton and Charles M. Rice for their discovery of the Hepatitis C virus, a major global health problem and a cause of cancer

How chemotherapy impacts the body

A new study has investigated how chemotherapy impacts oesophageal cancer patients and if this determines a patient’s risk of post-operative complications

New AI technology to help research into cancer metastasis

DeepScratch is a new AI technology that can be used to analyse how cells move in response to wound, building on the latest advances in deep learning