AI uncovers hidden rules of some of nature’s toughest protein bonds
Peer-Reviewed Publication
This month, we’re focusing on artificial intelligence (AI), a topic that continues to capture attention everywhere. Here, you’ll find the latest research news, insights, and discoveries shaping how AI is being developed and used across the world.
Updates every hour. Last Updated: 21-Nov-2025 19:11 ET (22-Nov-2025 00:11 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.
A research team in Taiwan’s Academia Sinica led by Dr. James C. Liao has recently designed an artificial carbon fixation cycle using synthetic biology. The team engineered this cycle into Arabidopsis, creating a type of “C2 plant”. In so doing, the research team have achieved a 50% increase in carbon fixation efficiency, along with accelerated plant growth and significantly higher lipid production. The finding offers a new strategy to address climate change, promote sustainable energy, and enhance food security. The research was published in the journal Science in September 2025.
A new study by University of Kansas scholars argues that traditional educational research has reached a breaking point in the era of AI. Despite massive publication output, the field has had limited impact due to entrenched problems. The study calls for an epistemological rebirth through methodological pluralism, ethical vigilance, and future-oriented approaches that embrace human–AI collaboration.