The science behind Netflix viewing habits could soon be used to guide doctors in cancer management, scientists suggest.
The researchers used artificial intelligence (AI) to study and categorize the size and magnitude of changes in DNA across the genome – the complete genetic code of a cell – when cancer begins and grows.
Using this data, they identified 21 common defects that occur as the disease begins and develops.
These defects, called copy number signatures, could help guide doctors to treatments that reflect tumor characteristics, the researchers suggest.
It is hoped that one day doctors will be able to examine a patient’s fully sequenced tumor and match its key features with the map of genomic defects, and offer more personalized cancer treatment.
When people watch Netflix, data is generated about the type of program or movie watched, how often they are watched, and whether a thumbs-up or thumbs-down is given.
An algorithm is used to analyze this massive amount of data, find patterns, and then recommend new movies and TV series next time.
A team of researchers led by Dr. Nischalan Pillay of University College London (UCL) and Dr. Ludmil Alexandrov of the University of California, San Diego (UC San Diego), built a similar algorithm.
It can sift through thousands of lines of genomic data and identify common patterns in the way chromosomes organize and arrange themselves.
According to scientists funded by Cancer Research UK and Cancer Grand Challenges, the algorithm can then categorize patterns that emerge and help scientists establish the types of defects that can occur in cancer.
Dr Alexandrov, co-lead author of the study, said: “Cancer is a complex disease, but we have demonstrated that there are remarkable similarities in the changes in the chromosomes that occur during its onset and progression. growth.
“Just as Netflix can predict which shows you choose to watch next, we believe we will be able to predict how your cancer is likely to behave, based on the changes its genome has already undergone.
“We want to get to the point where doctors can look at a patient’s fully sequenced tumor and match key tumor features with our blueprint for genomic defects.
“Armed with this information, we believe doctors will be able to offer better and more personalized cancer treatment in the future.”
Using the algorithm, the scientists searched for patterns in the fully sequenced genomes of 9,873 patients with 33 different types of cancer and identified 21 common defects.
These will now be used to create a blueprint that researchers can use to assess how aggressive the cancer is, find its weak spots and design new treatments.
Of the 21 signatures identified by the algorithm, the scientists found that tumors where chromosomes broke and reformed were associated with the worst survival outcomes.
Scientists hope they can refine the algorithm to allow doctors to find out how a person’s cancer is likely to behave, based on the genetic traits they acquired early on and the genetic changes they acquire over time. as it grows.
Dr Pillay said: “To stay ahead of cancer, we need to anticipate how it adapts and changes.
“Mutations are the main drivers of cancer, but much of our understanding focuses on changes to individual genes in cancer.
“We lacked the big picture of how large swaths of genes can be copied, moved or deleted without catastrophic tumor consequences.
“Understanding how these events occur will help us regain an edge over cancer.
“Thanks to advances in genome sequencing, we can now see these changes happening in different types of cancer and figure out how to respond to them effectively.”
The software called SigProfilerExtractor and other software tools used in the study were made freely available to other scientists.
Dr Christopher Steele, postdoctoral researcher at UCL and first author of the research, added: “We believe that making these powerful computational tools free for other scientists will accelerate progress towards a personalized cancer plan for patients. patients, giving them the best chance of survival.”
The results are published in Nature.