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

Professor David Hunter honoured by the Academy of Medical Sciences

OxCODE Associate Director Professor David Hunter has been elected as a Fellow of the Academy of Medical Sciences.

New prostate cancer risk tool

A new calculator has been developed by Professors Julia Hippisley-Cox and Carol Coupland to help GPs prioritise patients at high risk of prostate cancer.

Adrian Hill elected to Royal Society

Six scientists from the University of Oxford have joined the Royal Society as Fellows, including vaccine and cancer researcher Prof. Adrian Hill

Understanding mutation progression to detect ovarian cancer earlier

Nina Wietek from the Ahmed lab is investigating fallopian tube tissue to see what we can understand about precancerous mutations in the tissue from which ovarian cancers develops.

New study investigates how growth factors in our gut could initiate cancer

Dr Francesco Boccellato is investigating the mechanisms of tissue regulation in the healthy stomach and in a pre-cancerous condition known as atrophic gastritis. This may help to identify those who may have cancer, as well as find new ways to prevent cancer from progressing
Schematic drawing of the DNA double helix

New method for cost-effective genome-wide DNA methylation analysis

Dr Chunxiao Song’s team build on its TAPS method to develop an alternative to costly whole-genome sequencing for the detection of DNA methylation.

Using Herpesvirus to fight cancer

The Seymour lab at the Department of Oncology, University of Oxford, has published a new paper investigating the use of oncolytic herpes virus-1 as a vector to augment immunotherapy in cancer

Oxford success at the early detection sandpit on pancreatic cancer

Professor Eric O’Neill and Dr Pui San Tan receive funding as part of teams applying novel approaches for the early detection of pancreatic cancer.

Further funding secured to hunt out cancer using innovative radiotherapy techniques

Initial success leads to new award for Oxford researcher pushing forward new cancer-hunting radiotherapy.