Machine learning model predicts which patients with nasopharyngeal cancer respond to radiation
Peer-Reviewed Publication
Updates every hour. Last Updated: 11-Sep-2025 18:11 ET (11-Sep-2025 22:11 GMT/UTC)
A research team from Southern Medical University has developed a machine learning-based gene model that predicts whether nasopharyngeal cancer (NPC) patients will benefit from radiotherapy. This predictive tool, called the NPC-RSS, was validated in both cell lines and patient samples. The model may guide personalized treatment decisions and improve survival outcomes for NPC patients.
A new study in Nature shows that delivering a single injection of gene therapy at birth may offer years-long protection against HIV, tapping into a critical window in early life that could reshape the fight against pediatric infections in high-risk regions.
Liver cancer cells thrive on fat, posing a serious risk of cancer diagnosis for millions of people living with fatty liver disease. But researchers at McMaster University in collaboration with Espervita Therapeutics have developed a promising new treatment that helps the immune system attack and destroy these tumours.
This review elucidates the specific roles of the above mechanisms in the development of obesity-associated cancers at different sites, and outline intervention strategies to prevent obesity-associated cancers.
Researchers review controversial effects of fecal microbiota transplantation (FMT) on immune checkpoint inhibitor therapy. While some studies show improved cancer outcomes, others reveal no benefit or adverse effects, highlighting the complex relationship between gut bacteria and cancer treatment success.
Researchers discovered immune checkpoint inhibitors (ICIs)—revolutionary cancer drugs—significantly increase the risk of cholestasis, a rare bile buildup that damages the liver. Younger patients (<65) and those receiving anti-PD-1 drugs face higher risk. Women develop symptoms earlier than men. Rigorous liver monitoring is urged.
This review systematically analyzes computational frameworks that integrate multi-omics data (genomics, transcriptomics, proteomics) to transform antagonistic drug interactions into synergistic combinations. By evaluating AI-driven models like AuDNNsynergy and DrugComboRanker, it demonstrates how these tools optimize cancer therapies, overcoming drug resistance and improving efficacy while reducing experimental screening burdens.