Researchers have reported initial findings from a public-private partnership between the ECOG-ACRIN Cancer Research Group and Caris Life Sciences to improve recurrence risk assessment in early-stage breast cancer using artificial intelligence (AI). They are pairing ECOG-ACRIN’s extensive clinical trial expertise and biorepository resources with Caris’ comprehensive MI Cancer Seek® whole exome and whole transcriptome profiling, whole slide imaging, and advanced machine learning platforms. New multimodal–multitask deep learning algorithms were trained on histopathologic imaging, clinical data, and molecular profiling data from over 4,000 patient cases in the biorepository of the groundbreaking TAILORx cancer clinical trial, one of the world’s largest such resources. Analyses of these AI-driven models demonstrated they were more effective than existing methods for assessing recurrence risk. This research highlights the potential of AI to support more personalized treatment decisions in early-stage breast cancer. Such a level of multimodal integration is unprecedented at this scale in the prognostication of early breast cancer. 

An international team of researchers led by The University of New Mexico set out to understand how these mature faults break during massive seismic events, focusing on a long-debated phenomenon known as the “shallow slip deficit.” In many earthquakes, the surface shifts far less than the rocks deep underground, leaving scientists to question whether the missing energy is absorbed by surrounding rock or simply unmeasured. By analyzing the 2025 Myanmar earthquake, the team aimed to determine how a simple, ancient fault system releases energy, and whether that energy reaches the surface.

New psychoactive substances, originally developed as potential analgesics but abandoned due to adverse side effects, may still have pharmaceutical value if researchers could nail down the causes of those side effects. A new study from the University of Illinois Urbana-Champaign used deep learning and large-scale computer simulations to identify structural differences in synthetic cannabinoid molecules that cause them to bind to human brain receptors differently from classical cannabinoids.