Summary:

“Traditionally, cancer has been viewed as primarily a result of genetic mutations,” Hilary Coller, a professor of molecular, cell, and developmental biology at UCLA, said. “However, the emergence of advanced next-generation sequencing technologies has made more people realize that the state of the chromatin and the levels of epigenetic factors that maintain this state are important for cancer and its progression.”

Researchers from UCLA Health Jonsson Comprehensive Cancer Center explored how epigenetic factors impact cancer progression. Analyzing RNA sequencing data from various cancer types in public databases, they identified 720 epigenetic factors related to the «addition, removal, and recognition» of DNA. The study revealed that 10 out of 24 cancers showed significant differences in clinical outcomes based on epigenetic factors alone, predicting progression-free survival, disease-specific survival, and overall survival.

Five of these cancers, originating from diverse areas like the liver, lungs, brain, kidneys, and adrenal glands, demonstrated strong predictive power across all three outcomes. In comparison, traditional grade-based forecasts were effective for only one or two cancer types. The findings suggest that epigenetic factors could enhance traditional measurements.

The researchers also employed an artificial neural network, Cox-nnet, to predict patient outcomes based on the identified epigenetic factors. The AI successfully predicted clinical outcomes, showcasing its potential for broad applicability in cancer prognosis.

The study proposes that specific epigenetic factors may collaborate to modulate tumor-suppressing genes, offering a potential roadmap for predicting patient outcomes and developing targeted therapies. While the study is preliminary, with a focus on 720 epigenetic factors and the need for further research in pediatric cancers, it lays the foundation for improving AI models to guide cancer treatment and enhance survival predictions.

Article written by Kevin Dickinson| Image by Memorial Sloan Kettering Cancer Center / Freethink

18/12/2023

Source:

Freethink

https://engineering.jhu.edu/news/using-computer-vision-to-catch-early-stage-s