A new study in Science Bulletin presents DVSTP, a deep learning system that integrates pathology images with spatial transcriptomics and proteomics to map intra-tumor heterogeneity. DVSTP predicts molecular profiles from routine pathology slides, making spatial multi-omics more accessible. Whole–tumor 3D reconstruction reveals that SRSF6 drives immune exclusion and is associated with poor clinical outcomes.

Large language models and autonomous agents have advanced rapidly, showing broad promise in medical imaging analysis, clinical diagnosis, and treatment planning. However, most existing medical AI systems still rely primarily on pre-trained knowledge and fixed workflows, making it difficult to learn continuously from long-term clinical feedback, patient outcomes, and prior treatment experience. This "static AI" architecture limits their value in complex real-world clinical settings.

To address this bottleneck, a team led by Dr. Lian Zhang from the First Hospital of Hebei Medical University, in collaboration with domestic and international research partners, has proposed VIBEMed, which is a self-evolving multi-agent framework for clinical decision support designed to enable dynamic learning and safe, traceable system evolution.

Researchers have developed a facile water-based synthetic route for constructing fused azole–pyrimidine energetic materials, producing compounds with high thermal stability, strong detonation performance, and low mechanical sensitivity. The study demonstrates how eco-friendly aqueous synthesis can simultaneously improve safety, thermal resistance, and energetic performance in next-generation heat-resistant explosives.

Scientists from Nanyang Technological University, Singapore (NTU Singapore) have developed a new method to recycle mixed plastic packaging without using harmful chemical solvents – an approach that could make one of the world's most difficult waste streams significantly easier to handle.

This study demonstrates the gram-scale synthesis of water-stable M-Gallate (M = Mg, Ni, Co) metal-organic frameworks from inexpensive raw materials, and their application in harvesting water vapour from ultra-low humidity air. The optimal Mg-Gallate MOF achieves a record-high atmospheric water capture capacity of 170.0 mg/g at 0.2% relative humidity (RH) and 25 °C, surpassing all previously reported porous adsorbents under equivalent conditions.

Researchers have developed tough, conductive RBA hydrogels using a hyperbranched multi-arm crosslinking strategy. The hydrogels form a dense, stable network that enables wearable sensors to monitor full-body motion and support Morse-code-based human–machine interaction.

Birgitta Schultze-Bernhardt and her team at the Institute of Experimental Physics at Graz University of Technology (TU Graz) have developed a new type of UV dual-comb spectrometer that detects gaseous air pollutants with unrivalled accuracy and sensitivity. Using ultraviolet double laser light, the device measures the concentration of harmful gases such as formaldehyde within half a second. Thanks to its compact design and a measuring range of up to two and a half kilometres, the spectrometer is not only suitable for laboratory analyses, but also for mobile measurements in cities, industrial areas and agricultural regions.