LONDON — The same algorithms that figure out your viewing habits on Netflix could soon create a treatment plan for cancer.
Scientists have created a machine learning tool to investigate the DNA changes triggered by cancer which utilizes the artificial intelligence programs the streaming giant uses. The program categorizes DNA changes across a cell’s complete genetic code when tumors start and grow.
The international team identified 21 common faults that occur to the structure, order, and number of copies present. They are called copy number signatures, offering hope of personalized therapies for patients.
Netflix generates data about the type of films and TV series you like, how frequently you watch them, and whether you give them a “thumbs up” or “thumbs down.” A mathematical formula analyzes massive amounts of information to find patterns in the content and then makes recommendations as you scroll through.
The cancer algorithm is similar, sifting through thousands of lines of genomic data and picking out common patterns. Identifying how stretches of DNA, or chromosomes, arrange themselves helps establish the types of faults that can occur. In tests, the scientists looked for patterns in the fully sequenced genomes from 9,873 patients with 33 different types of cancer.
The algorithm can predict how cancer will behave
The findings in the journal Nature will create a blueprint researchers can use to assess how aggressive the cancer will be, find its weak spots and design new treatments.
“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 co-lead author Professor Ludmil Alexandrov from the University of California-San Diego in a media release.
“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,” Alexandrov continues.
“We want to get to the point where doctors can look at a patient’s fully sequenced tumor and match the key features of the tumor against our blueprint for genomic faults. Armed with that information, we believe that doctors will be able to offer better and more personalized cancer treatment in the future.”
The scientists previously studied how these large-scale faults occur in sarcoma and wanted to find ways to study these changes across different types of cancer. Using software called SigProfilerExtractor, developed by Dr. Alexandrov, the algorithm uses complex calculations to scan sequencing data from cancer patients.
It spots common patterns in how the chromosomes are reorganized in different types of the disease. The scientists further investigated the copy number signatures which most strongly affected outcomes for patients.
Of the 21 specific signatures, tumors where the chromosomes have shattered and reformed, known as chromothripsis, were associated with the worst survival rates. For example, the study found that patients with glioblastoma, an aggressive type of brain tumor, had worse outcomes if their tumor had undergone chromothripsis. On average, glioblastoma patients without chromothripsis survived six months longer than others.
Scientists look to create ‘a personalized cancer blueprint’
Scientists hope further refinement will enable doctors to find out how cancers are likely to behave based on original genetic traits and those it picks up as it spreads.
“To stay one step ahead of cancer, we need to anticipate how it adapts and changes,” says co-lead author Prof. Nischalan Pillay from University College London (UCL).
“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 tumor.”
“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.”
SigProfilerExtractor and other software tools have been made freely available to other scientists. They can use the algorithm to build their own Netflix-style libraries of chromosome changes from DNA, based on data obtained from sequencing tumors.
“We believe that making these powerful computing tools free to other scientists will accelerate progress towards a personalized cancer blueprint for patients, giving them the best chances of survival,” first author Dr. Christopher Steele from UCL concludes.
South West News Service writer Mark Waghorn contributed to this report.
