Ellen Phiddian
Cosmos science journalist
An international team of researchers have used AI to map signals across the entire genome that herald the beginnings of cancer.
The researchers, who say that their algorithm is similar to that used by Netflix, have identified 21 common faults that occur in human DNA when cancer begins to grow.
“Cancer is a complex disease, but we’ve demonstrated that there are remarkable similarities in the changes to chromosomes that happen when it starts and how it grows,” says Dr Ludmil Alexandrov, an associate professor at the University of California, San Diego, US, and co-lead author on a paper describing the research, published in Nature.
“Just as Netflix can predict which shows you’ll choose to binge watch next, we believe that we will be able to predict how your cancer is likely to behave, based on the changes its genome has previously experienced.”
More on AI and medicine: Are machine-learning tools the future of healthcare?
The researchers used their algorithm to examine genomic data from 9,873 patients, who had 33 different types of cancer. It helped them identify 21 “copy number alterations” (changes in the structure and length of the chromosomes) in the genomes.
At least one of these 21 signatures was present in 97% of the samples they analysed. These signatures could then be linked to different characteristics of the cancers – including how aggressive and survivable the tumour was.
“To stay one step ahead of cancer, we need to anticipate how it adapts and changes,” says Dr Nischalan Pillay, an associate professor at University College London, UK, and co-lead author of the research.
“Mutations are the key drivers of cancer, but a lot of our understanding is focused on changes to individual genes in cancer. We’ve been missing the bigger picture of how vast swathes of genes can be copied, moved around or deleted without catastrophic consequences for the tumour.
“Understanding how these events arise will help us regain an advantage over cancer. Thanks to advances in genome sequencing, we can now see these changes play out across different cancer types and figure out how to respond effectively to them.”
The team is now developing a blueprint that researchers can use to predict how aggressive a cancer will be, and where it has weak spots or vulnerability to possible treatments. They’re hoping doctors will be able to use the blueprint as well.
They’ve made the algorithm and their other software tools freely available to other researchers, so that other scientists can develop their own libraries.
“We believe that making these powerful computing tools free to other scientists will accelerate progress towards a personalised cancer blueprint for patients, giving them the best chances of survival,” says first author Dr Christopher Steele, a postdoctoral researcher also at University College London.