125584 -

: Quinolones (QNs) and Sulfonamides (SAs) were flagged as high-priority risks due to their notable contribution to Antimicrobial Resistance (AMR) .

The study moves beyond traditional modeling by using "cross-modal attention." This AI technique allows the model to process different types of data—such as chemical structures and biological activity—simultaneously. By focusing on how these different "modes" relate to one another, the AI can pinpoint exactly which chemical groups contribute to high environmental and health risks. 125584

Insights for environmental, ecological, health, and AMR risks : Quinolones (QNs) and Sulfonamides (SAs) were flagged

One of the study's most startling revelations is that retain equal or even higher risks than their "parent" antibiotics. This suggests that even when an antibiotic technically "breaks down," its environmental footprint remains dangerously high. 3. Key Biological Indicators Key Biological Indicators While the world focuses on

While the world focuses on the primary impact of antibiotics, a "shadow" threat lingers in our waterways: . These are chemical offspring created when antibiotics break down in the environment. Traditionally, assessing their risks was a slow, expensive manual process. Research article 125584 changes this by introducing a cross-modal attention deep learning framework to predict the multi-dimensional life-cycle risks of these substances. 1. The Power of Cross-Modal Learning

: The AI identified specific molecular groups—such as N-groups, COOH (carboxyl), C=O (carbonyl), OH (hydroxyl), and halogens —as the primary mediators of high life-cycle risks. 4. Implications for Global Health