News, Culture & Society

New AI technique could enable doctors to predict how cancer tumours will mutate

A new AI technique could enable doctors to predict how cancer tumours will mutate and allow them to personalise each patient’s treatment earlier.

The technology, known as Revolver (repeated evolution of cancer), picks out patterns in DNA mutations within cancers and uses the information to predict future genetic changes.

The scientists claim the ever-changing nature of tumours is one of the biggest challenges in treating cancers, which often evolve to be drug-resistant.

Lead author Dr Andrea Sottoriva, from The Institute of Cancer Research (ICR), London: ‘With this tool we hope to remove one of cancer’s trump cards – the fact that it evolves unpredictably, without us knowing what is going to happen next.’

ICR’s chief executive Professor Paul Workman added: ‘This new approach using AI could allow treatment to be personalised in a more detailed way and at an earlier stage, tailoring it to the characteristics of each individual tumour.’ 

Image shows a stock picture of a tumour. Scientists are using AI to predict how cancers will progress, which could help doctors come up with the most effective treatment for patients


Breastfeeding reduces a woman’s risk of breast cancer, a report suggested in August 2017.

For every five months a woman breastfeeds, her risk of developing breast cancer is lowered by two percent, a study review found.

Researchers believe breastfeeding protects women against the condition as it makes them temporarily stop getting periods, which reduces their lifetime exposure to the hormone oestrogen.

High oestrogen levels have previously been linked to developing breast cancer.

Breastfeeding may also help to remove cells with damaged DNA that may otherwise lead to tumor onset.

The researchers, from the American Institute for Cancer Research and the World Cancer Research Fund, analysed 18 studies that examined breastfeeding.

Of these, 13 investigated the effects of the length of time spent lactating. 

The report also found that carrying excess weight after menopause increases a woman’s risk of developing breast cancer, yet it is protective while women are still able to conceive.

For both pre- and postmenopausal women, alcohol increases their risk of breast cancer and exercise reduces it, the report adds.

Babies who are breastfed are also less likely to gain weight in later life, the study found.

Study author Alice Bender said: ‘It isn’t always possible for moms to breastfeed but for those who can, know that breastfeeding can offer cancer protection for both the mother and the child.’ 

‘AI could allow treatment to be personalised’ 

To create Revolver, the researchers analysed 768 tumour samples from 178 patients reported in previous studies for lung, breast, kidney and bowel cancer.

They analysed the data within each cancer type respectively to detect and compare changes in each tumour.

By identifying repeating patterns and combining this with existing knowledge of cancer biology and evolution, the scientists could predict the future of a tumour’s development.

If tumours with certain patterns are found to develop resistance to a particular treatment, Revolver could be used to predict if patients will develop resistance in the future.

Speaking of the findings, published in the journal Nature Methods, Professor Workman said: ‘Cancer evolution is the biggest challenge we face in creating treatments that will work more effectively for patients.

‘If we are able to predict how a tumour will evolve, the treatment could be altered before adaptation and drug resistance ever occur, putting us one step ahead of the cancer.

‘This new approach using AI could allow treatment to be personalised in a more detailed way and at an earlier stage, tailoring it to the characteristics of each individual tumour and to predictions of what that tumour will look like in the future.’

‘We could use AI to predict cancer’s next move’  

The scientists also found a link between certain sequences of repeated tumour mutations and a patient’s survival chances.

This suggests that repeating patterns of DNA mutations could be used as an indicator of treatment prognosis, helping to shape future therapies.

For example, the researchers found that breast tumours with a sequence of errors in the DNA that codes for the tumour-suppressing protein p53, followed by mutations in chromosome 8, survive for less amounts of time.  

Dr Sottoriva said: ‘We’ve developed a powerful AI tool which can make predictions about the future steps in the evolution of tumours based on certain patterns of mutation that have so far remained hidden within complex data sets.

‘By giving us a peek into the future, we could potentially use this AI tool to intervene at an earlier stage, predicting cancer’s next move.’   



Comments are closed.