A new method lets users ask, in plain language, for a new molecule with certain properties, and receive a detailed description of how to synthesize it.

Enhancing activity of a specific component of neurons’ “NMDA” receptors normalized protein synthesis, neural activity, and seizure susceptibility in the hippocampus of fragile X lab mice.

Starting with a single frame in a simulation, a new system uses generative AI to emulate the dynamics of molecules, connecting static molecular structures and developing blurry pictures into videos.

Using this model, researchers may be able to identify antibody drugs that can target a variety of infectious diseases.

Large multi-ring-containing molecules known as oligocyclotryptamines have never been produced in the lab until now.

Most antibiotics target metabolically active bacteria, but with artificial intelligence, researchers can efficiently screen compounds that are lethal to dormant microbes.

These compounds can kill methicillin-resistant Staphylococcus aureus (MRSA), a bacterium that causes deadly infections.

MIT researchers find that in mice and human cell cultures, lipid nanoparticles can deliver a potential therapy for inflammation in the brain, a prominent symptom in Alzheimer’s.

A potential new Alzheimer’s drug represses the harmful inflammatory response of the brain’s immune cells, reducing disease pathology, preserving neurons, and improving cognition in preclinical tests.

This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.