Learning the language of molecules to predict their properties
This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.
This AI system only needs a small amount of data to predict molecular properties, which could speed up drug discovery and material development.
BioAutoMATED, an open-source, automated machine-learning platform, aims to help democratize artificial intelligence for research labs.
A new approach for identifying significant differences in gene use between closely-related species provides insights into human evolution.
The images shed light on how electrons form superconducting pairs that glide through materials without friction.
A new technique produces perovskite nanocrystals right where they’re needed, so the exceedingly delicate materials can be integrated into nanoscale devices.
A new computational method facilitates the dense placement of objects inside a rigid container.
The foundry gives the wider research community access to Lincoln Laboratory’s expertise in fabricating quantum circuits.
The new strategy may enable engineered T cells to eradicate solid tumors such as glioblastoma.
The disorganized arrangement of the proteins in light-harvesting complexes is the key to their extreme efficiency.
Training artificial neural networks with data from real brains can make computer vision more robust.
A new dataset can help scientists develop automatic systems that generate richer, more descriptive captions for online charts.
MAGE merges the two key tasks of image generation and recognition, typically trained separately, into a single system.
The first RNA-guided DNA-cutting enzyme found in eukaryotes, Fanzor could one day be harnessed to edit DNA more precisely than CRISPR/Cas systems.
The system analyzes the likelihood that an attacker could thwart a certain security scheme to steal secret information.
Work could lead to heady applications in novel electronics and more.