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

An animated drawing of the DNA double helix on a background of DNA sequence (a, c, g, t)

Developing a system to simultaneously detect genetic and epigenetic information

Dr Benjamin Schuster-Böckler wins funding to develop algorithms that can identify both genetic variation and DNA methylation from the same sequencing data, with applications in biomedical research and detection of diseases such as cancer.

Early Detection of Cancer Month

A summary of Early Detection Month in Oxford, February 2021

New Oxford spin-out Singula Bio launches

Singula Bio, co-founded by Professors Ahmed Ahmed, Enzo Cerundolo and Enda McVeigh from the Nuffield Department of Women’s & Reproductive Health, aims to become a world leader in developing neoantigen-based individualised cell therapies to use against difficult-to-treat solid malignancies such as ovarian cancer.

New Oxford technology assesses cancer patient vulnerability to COVID-19

New research from Prof Julia Hippisley-Cox has resulted in thousands of cancer patients being given prioritised access to the COVID-19 vaccine.

Finding extracellular vesicle biomarkers for oesophageal cancer early detection

Prof Deborah Goberdhan’s lab is investigating extracellular vesicles and the proteins they express as potential biomarkers for the progression from Barrett’s Oesophagus to oesophageal cancer

Detecting for multiple cancers in one simple test

Prof. Jason Davis is working alongside clinicians to introduce his biomarker assays into the clinic. Using a range of electroanalytical methods, together with electrode arrays and microfluidics, the platform has the potential to test for many types of cancers all at once, and at an earlier, pre-symptomatic stage.
A molecule of DNA with a radiating light representing mutation

Understanding how inherited and acquired mutations interact to affect cancer

Development fund awardee Gareth Bond is investigating how different types of genetic mutations cooperate to influence cancer risk, progression and response to therapy
Atovaquone molecule

Reprogramming tumour cells using an antimalarial drug

Results from the ATOM clinical trial at the University of Oxford have shown that the anti-malarial drug Atovaquone can reduce very low oxygen tumour environments. This has the potential to make cancers behave less aggressively and to improve the impact of everyday cancer treatments.

Studying viral genetics to aid liver cancer early detection

Professor Ellie Barnes and Dr Azim Ansari receive funding to identify cancer-associated strains of hepatitis C in Pakistan to improve assessment of liver cancer risk