AI uncovers hidden rules of some of nature’s toughest protein bonds
Peer-Reviewed Publication
Updates every hour. Last Updated: 15-Dec-2025 10:11 ET (15-Dec-2025 15:11 GMT/UTC)
Scientists from Auburn University and Colorado State University have shown how artificial intelligence can reveal the hidden rules of one of biology’s strangest phenomena: catch-bonds – molecular interactions that get stronger when pulled. Their findings shed light on how bacteria cling to surfaces, how tissues resist tearing, and how new biomaterials might be designed to harness force instead of breaking under it.
The accuracy of machine learning algorithms for predicting suicidal behavior is too low to be useful for screening or for prioritizing high-risk individuals for interventions, according to a new study published Sept. 11 in the open-access journal PLOS Medicine by Matthew Spittal of the University of Melbourne, Australia, and colleagues.
From pollinating flowers to enabling decomposition and supporting nutrient cycles, insects’ abundance and biodiversity are critical for maintaining healthy ecosystems. However, recent studies showing population declines have raised alarm about how insects are coping with the modern world. Understanding whether recent observations are part of longer timescale trends can help inform global conservation efforts, and identify the reasons behind the so-called “Insect Apocalypse”.
Published in Science, researchers from the Okinawa Institute of Science and Technology (OIST) used a community genomics approach to explore ant populations in the Fijian archipelago as a model system to understand insect biodiversity trends. By studying the genomics of museum collections, they were able to trace the ants’ evolutionary relationships to explore their arrival to the islands and reconstruct the population history of the species.
Understanding the strategies and unmet needs of caregivers managing medications for people with Alzheimer’s disease or related dementias may improve the lives of both caregivers and patients. A recent study describes the strategies and the unmet needs of caregivers managing medications for people with Alzheimer’s disease or related dementias. The researchers identified three distinct caregiver personas: “Checklist Cheryl,” “Social Sam,” and “Responsive Rhonda.” Each persona embodies a different approach to medication management, varying in organization, technology use, collaboration and response to challenges. These nuanced personas can guide the design of customized caregiver support and digital health tools.