Reproduction of a life-size oil painting of an adult male woolly mammoth navigating a mountain pass in Arctic Alaska. Little is known about the movement patterns of these extinct giants. Isotopic records from a 17 100-year-old mammoth tusk reveal that the animal covered an extensive geographic range during its lifetime. However, as the ice age ended and the Arctic environment began to change, maintaining this level of mobility would have been increasingly difficult.
New deep learning software can predict protein structures in minutes by simultaneously considering one-, two-, and three-dimensional information (sequence, distance, and coordinates, respectively), allowing the network to collectively reason about the relationship between a protein's amino acid sequence and its folded structure. The software can also be used to build models of complex biological assemblies from the sequences of interacting partners in a fraction of the time previously required.
An artificial intelligence algorithm selects an RNA molecule's three-dimensional shape out of a sea of incorrect shapes. Computational prediction of the structures into which RNAs fold is particularly important - and particularly difficult - because so few structures are known. The success of machine learning despite this lack of data opens doors to understanding and designing diverse molecules, including medicines.
Snow blankets the ground in Dallas, Texas, on 18 February 2021. The cold wave of February 2021 was one of the costliest weather disasters in the United States, especially for Texas, owing to the intersection of energy regulation decisions and exceptionally severe winter weather. New research combines machine learning analysis of observations with numerical modeling to demonstrate that Arctic climate change has modified polar vortex behavior to increase the likelihood of such extreme events.