Scientists used artificial intelligence to predict how cancer will develop and evolve.
This could help physicians develop the most effective treatment for each patient.
A team from the Institute of Cancer Research London (ICR) and The University of Edinburgh developed a new technique known as the Reveated Evolution of Cancer.
This method identifies patterns in DNA mutation in cancers and uses the information to predict future genetic changes.
The researchers said this was ever-changing The nature of the tumors was one of the biggest challenges in cancer treatment ̵
However, if physicians can predict how a tumor will develop, they could earlier intervene on cancer in its footsteps before it had a chance to develop or develop resistance, increasing the patient's chances of survival.
The team also found a link between certain episodes of repeated tumors of our mutations and our survival outcome.
This suggests that repetitive patterns of DNA mutations could be used as an indicator of prognosis to shape future treatment.
For example, researchers found breast tumors that had a sequence of defects in the genetic material coding for them, the tumor-suppressing protein p53, followed by mutations in chromosome 8, survived less time than others similar trajectories of genetic alterations.
The research team developed a new machine learning method that transfers knowledge about tumors in similar patients  This method identifies patterns in the order that genetic mutations occur in tumors that are repeated both inside and between patients' tumors, using a tumor
The researchers used 768 tumor samples from 178 patients reported in previous studies for lung, breast, kidney and colon cancers, and analyzed the data within each cancer to match changes in both cancers Recognizing and Comparing
By identifying repetitive patterns and combining them with current knowledge about cancer biology and evolution, scientists could predict the future development of tumor development.
If tumors with specific patterns of resistance develop a special treatment, this new method could be used to predict whether patients will develop resistance in the future.
The research is published in the journal Nature Methods.
Dr. Andrea Sottoriva, who led the study, is team leader in English: bio-pro.de/en/region/stern/magazine/…1/index.html evolutionary genomics and modeling at the ICR: "We have a powerful tool for artificial Intelligence designed to predict the subject The future steps in the evolution of tumors based on certain mutational patterns that have hitherto been hidden in complex datasets.
"With this tool we hope to remove one of the trump cards of cancer – the fact that it develops unpredictably, without We can know what will happen next.
"Looking ahead, we could use this AI tool to intervene earlier and predict the next step in the cancer."
ICR Director-General Professor Paul Workman said, "Cancer evolution is the biggest challenge we face in developing treatments that work more effectively for patients."
"If we can predict how a tumor will develop , Adaptation and Drug Resistance Treatment May Be Changed (19659007) "This new approach, using AI, could allow the treatment to be personalized in more detail and earlier than before, to tailor it to the character of each tumor and predictions about what this tumor will look like in the future. "