Researchers at Arc Institute developed MULTI-evolve, an AI-guided framework that compresses protein engineering from months of iterative experimentation into weeks using as few as 200 strategic lab measurements. By training neural networks on pairwise combinations of beneficial mutations, the approach learns the rules of how mutations interact and accurately predicts complex multi-mutant proteins, achieving up to 256-fold activity improvements in a single experimental round. Published in Science, the framework and open-source tools are applicable to enzymes, genome editors, and therapeutic proteins.

Harvard researchers have developed OpenMetabolics, an open-source, smartphone-based activity monitor that uses machine learning and leg motion to estimate calories burned.

Harvard researchers report a new way to make ultra-smooth, microscopic mirrors that form high-performance optical resonators, or cavities.

Harvard engineers have developed a new 3D printing method for building soft robots that bend and change shape in predictable ways when inflated. The technique employs rotational multimaterial 3D printing, in which a dual-material nozzle prints filaments with a flexible outer shell and removable inner gel.