Cancer specialists turn to the same artificial intelligence programs that Netflix uses

LONDON – The same algorithms that determine your Netflix viewing habits could soon create a cancer treatment plan.

Scientists have created a machine learning tool to investigate cancer-caused DNA changes that uses artificial intelligence programs used by the streaming giant. The program classifies DNA changes throughout the cell’s genetic code during the appearance and growth of tumors.

The international team identified 21 common errors related to the structure, order, and number of copies present. They are called digital signatures, offering hope for personalized therapy for patients.

Netflix generates data about the types of movies and series you like, how often you watch them, and whether you give them a thumbs up or a thumbs down. The math formula analyzes vast amounts of information to find patterns in content, then makes recommendations as you scroll.

The cancer algorithm is similar, it sifts through thousands of lines of genomic data and picks out common patterns. Finding out how sections of DNA or chromosomes are ordered helps to identify the types of errors that can occur. During the tests, the scientists looked for patterns in the fully sequenced genomes of 9,873 patients with 33 different types of cancer.

Algorithm can predict how cancer will behave

Findings in the journal Nature will create a blueprint that researchers can use to assess how aggressive the cancer will be, find its weaknesses, and develop new treatments.

“Cancer is a complex disease, but we have shown amazing similarities in the chromosome changes that occur when it starts and how it grows,” says co-author Professor Ludmil Aleksandrov from the University of California, San Diego. a Press release.

“Just like Netflix can predict which series you will choose to watch next, we believe we can predict how your cancer will behave based on the changes that have previously occurred in its genome,” Alexandrov continues.

“We want to get to the point where clinicians can look at a patient’s fully sequenced tumor and match key characteristics of the tumor with our genomic error plan. Armed with this information, we believe that doctors will be able to offer better and more personalized cancer treatment in the future.”

The scientists had previously studied how these large-scale defects occur in sarcoma and wanted to find ways to study these changes in different types of cancer. Using software called SigProfilerExtractor, developed by Dr. Alexandrov, the algorithm uses complex calculations to scan cancer patient sequencing data.

It reveals general patterns in how chromosomes reorganize in different types of diseases. The scientists further investigated the copy number signatures that most strongly influenced patient outcomes.

Of the 21 tumor-specific features in which chromosomes are destroyed and rearranged, known as chromothripsis, were associated with the worst survival rates. For example, a study found that patients with glioblastoma, an aggressive type of brain tumor, had worse outcomes if their tumor underwent chromotripsis. On average, glioblastoma patients without chromotripsis survived six months longer than others.

Scientists want to create a “personalized cancer treatment plan”

Scientists hope that further refinements will allow doctors to figure out how cancer might behave based on the original genetic traits and those it acquires as it spreads.

“To stay ahead of cancer, we need to anticipate how it adapts and changes,” says study co-author Professor Nishalan Pillay of University College London (UCL).

“Mutations are key drivers of cancer, but most of our understanding is focused on changes in individual genes in cancer. We’re missing the bigger picture of how massive arrays of genes can be copied, moved, or deleted without catastrophic consequences for a tumor.”

“Understanding how these events occur will help us regain our edge over cancer. Thanks to advances in genome sequencing, we can now see how these changes manifest themselves in different types of cancer and figure out how to effectively respond to them.”

SigProfilerExtractor and other software tools have been made freely available to other scientists. They can use the algorithm to create their own libraries of Netflix-style chromosomal changes based on tumor sequencing data.

“We believe that making these powerful computing tools available free of charge to other scientists will accelerate progress towards a personalized cancer treatment plan for patients, giving them the best chance of survival,” concludes first author Dr. Christopher Steele of the University of California, London.

South West News Service writer Mark Waghorn contributed to this report.

Leave a Reply

Your email address will not be published.

Previous post Another football team of football stadium developer Pawtucket attracts few fans
Next post Stephen Curry’s legacy cemented after NBA Finals win