Netflix-style algorithm maps cancer genome

The science behind predicting your Netflix viewing habits could one day be used to guide doctors in treating some of the most intractable cancers, a study from the University of California San Diego and University College London shows.

Researchers have used artificial intelligence to analyze and classify the size and scope of DNA changes in the genome as cancer starts and grows. After analyzing the genomes of 9,873 patients with 33 types of cancer, the scientists found 21 categories of common changes in the structure and number of chromosomes in the genetic material of tumors.

These categories of common DNA changes, known as copy number signatures, can be used to create a plan to predict how the cancer might progress and develop the most effective treatments. The results are reported in an article published June 15 in Nature.

“Cancer is a complex disease, but we have shown amazing similarities in the changes that occur in chromosomes as different types of cancer develop and develop,” said Lyudmil Alexandrov, professor of bioengineering and cellular and molecular medicine at the University of California, San Diego. who is a co-author of the study.

When cancer sets in, mutations in the DNA can cause large-scale disruptions throughout their entire genome. These deficiencies can result in too few or too many chromosomes compared to normal cells. Tumors can also cause malfunctions in the mechanisms designed to repair their DNA, which in turn leads to further malfunctions in the structure of DNA in chromosomes, as well as errors when DNA tries to make copies of itself.

Researchers were interested in studying these large-scale genomic errors in various types of cancer. Enter Alexandrov’s lab’s SigProfiler AI toolkit, which scans cancer patient sequencing data and identifies common patterns of chromosomal changes in various types of cancer.

“Based on these changes that have previously occurred in the genome, our algorithm can predict how your cancer is likely to behave – similar to how Netflix can predict which series you will choose to watch next based on your previous viewings.” Alexandrov said. .

This algorithm was key in identifying the 21 copy number signatures found in this study. It also allowed researchers to predict how some of the most difficult-to-treat cancers would behave.

One of the copy number signatures produced by the algorithm is associated with an event known as chromotripsis, when chromosomes in tumors fragment and rearrange. The researchers found that this digital signature was associated with the worst survival outcomes. Take, for example, patients with a deadly, fast-growing brain cancer called glioblastoma. It was found that, on average, patients with glioblastoma whose tumors did not undergo chromotripsis survived six months longer than those whose tumors did.

“Mutations are key drivers of cancer, but most of our understanding is focused on changes in individual genes in cancer. We are missing the bigger picture of how huge arrays of genes can be copied, moved or deleted without catastrophic consequences for the tumor,” said Nishalan Pillay, professor of sarcoma and genomics at University College London and co-author of the study. the study. “Understanding how these large-scale genomic events occur will help us regain our advantage over cancer.”

The researchers made SigProfiler and other software tools used in the study available to other scientists so that they can use the tools to create their own Netflix-style libraries of DNA chromosomal changes based on tumor sequencing data.

“As reading the human genetic code completely becomes faster and cheaper, we hope that our plan will be widely used to navigate this code and help doctors offer better and more personalized cancer treatment,” Aleksandrov said.

As part of their next steps, researchers are investigating some of the identified categories of copy number changes as clinical biomarkers to predict response to cancer therapy.

Paper: “Signatures of copy number changes in human cancer.”

This work was supported by the Cancer Grand Challenge award from Cancer Research UK.

Leave a Reply

Your email address will not be published.

Previous post What is the movie “Spider Head” based on? Netflix movie inspired by New Yorker article.
Next post Women’s football to host two big 12 rivals as part of fall 2022 schedule