<i>CryoRL</i>: reinforcement learning enables efficient cryo-EM data collection

Single-particle cryo-electron microscopy (cryo-EM) has become one of the mainstream structural biology techniques because its ability to determine high-resolution structures dynamic bio-molecules. However, cryo-EM data acquisition remains expensive and labor-intensive, requiring substantial expertise. Structural biologists need a more efficient objective method collect best in limited time frame. We formulate collection task as an optimization problem this work. The goal is maximize total number good images taken within specified period. show that reinforcement learning offers effective way plan collection, successfully navigating heterogenous grids. approach we developed, cryoRL, demonstrates better performance than average users for under similar settings.