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

Bowel cancer patients going undiagnosed due to COVID distruption

A new study led by the University of Oxford has found that since the first coronavirus lockdown the number of people diagnosed with bowel cancer in England has fallen sharply, with a deficit persisting up to October 2020
Prof Ahmed Ahmed in his lab

“The Oxford Classic” classification system uncovers new information about ovarian cancers

Oxford cancer researchers have developed a new way of subtyping ovarian cancer that enables the accurate prediction of patient outcome and sheds light onto the role the immune system plays in ovarian cancer response to treatment.

Oxford spin out financed $6.8m for research into oncolytic therapies

Oxford spin out company Theolytics has closed a $6.8m deal to support their work into developing novel cancer therapies from viruses

Being a part of cancer drug discoveries

Susan Cakebread, gives her account of being on an experimental drug trial here in Oxford
National Foundation for Cancer Research

Investigating the effects of co-morbidities on liver cancer risk

Dr Philippa Matthews and colleagues review the associations between liver cancer risk and co-morbidities and other metabolic factors in individuals with chronic hepatitis B virus infection.

Potential of DNA-based blood tests for detecting pancreatic cancer earlier

Dr Shivan Sivakumar and colleagues evaluate the current progress and future potential in using genetic and epigenetic methods for detecting pancreatic cancer DNA in the blood

Bioengineering the human gut

An interdisciplinary collaboration generates an advanced model of the human gastrointestinal tract with broad applications for disease research and regenerative medicine

Pancreatic Cancer Awareness Month

A round up of Pancreatic Cancer Awareness Month at the University of Oxford

SCALOP team discover new pancreatic cancer biomarker

The SCALOP clinical trial team have uncovered a new therapeutic target for locally advanced pancreatic cancer. Read more about it and the next steps for the SCALOP-2 trial.