A novel Graph Neural Network approach captures relationships between sensor readings across different timestamps, helping researchers interpret data from machines and wearable devices.

An eight-week human trial reveals how diets based on fortified plant-based meat alternatives hold up nutritionally against animal meats.

A secure data analytics platform enables cross-institutional studies of patient health records without pooling raw data or compromising privacy.

A*STAR researchers developed an algorithm that enables more accurate assembly of genomic sequences to help us better understand the molecular variations underlying health and disease.

Researchers chart how polymers could be engineered into lightweight and long-lasting shields that can handle radiation-intensive environments.

By reasoning and accessing knowledge in an alternative language, large language models can produce more reliable answers in the user’s original language.

Air-trapping proteins from snap pea pods possess natural foaming properties, offering a plant-based alternative for making whipped cream and other fluffy foods.

A 4D printing approach produces shape-changing materials from common thermoplastics by turning heat-induced shrinkage into controlled movement.

A novel electricity-driven process produces valuable nitriles without the toxic cyanide reagents or high energy demands of conventional manufacturing.

A*STAR researchers develop a deep learning tool to overcome the lack of matched healthy DNA samples when identifying cancer-linked mutations in tumour sequencing data.