Closed-loop optimization of fast-charging protocols for batteries with machine learning.

Simultaneously optimizing many design parameters in time-consuming experiments causes bottlenecks in a broad range of scientific and engineering disciplines1,2. One such example is process and control optimization for lithium-ion batteries during materials selection, cell manufacturing and operation. A typical objective is to maximize battery lifetime; however, conducting even a single experiment to evaluate lifetime can take months to years3-5. Furthermore, both large parameter spaces and high sampling variability3,6,7 necessitate a large number of experiments. Hence, the key challenge is to reduce both the number and the duration of the experiments required. Here we develop and demonstrate a machine learning methodology  to efficiently optimize a parameter space specifying the current and voltage profiles of six-step, ten-minute fast-charging protocols for maximizing battery cycle life, which can alleviate range anxiety for electric-vehicle users8,9. We combine two key elements to reduce the optimization cost: an early-prediction model5, which reduces the time per experiment by predicting the final cycle life using data from the first few cycles, and a Bayesian optimization algorithm10,11, which reduces the number of experiments by balancing exploration and exploitation to efficiently probe the parameter space of charging protocols. Using this methodology, we rapidly identify high-cycle-life charging protocols among 224 candidates in 16 days (compared with over 500 days using exhaustive search without early prediction), and subsequently validate the accuracy and efficiency of our optimization approach. Our closed-loop methodology automatically incorporates feedback from past experiments to inform future decisions and can be generalized to other applications in battery design and, more broadly, other scientific domains that involve time-intensive experiments and multi-dimensional design spaces.

Membrane palmitoylated proteins regulate trafficking and processing of nectins.

Nectins are cell-cell adhesion molecules involved in the formation of various intercellular junctions and the establishment of apical-basal polarity at cell-cell adhesion sites. To have a better understanding of the roles of nectins in the formation of cell-cell junctions, we searched for new cytoplasmic binding partners for nectin. We report that nectin-1α associates with membrane palmitoylated protein 3 (MPP3), one of the human homologues of a Drosophila tumor suppressor gene, Disc large. Two major forms of MPP3 at 66 and 98 kDa were detected, in conjunction with nectin-1α, suggesting that an association between the two may occur in various cell types. Nectin-1α recruits MPP3 to cell-cell contact sites, mediated by a PDZ-binding motif at the carboxyl terminus of nectin-1α. Association with MPP3 increases cell surface expression of nectin-1α and enhances nectin-1α ectodomain shedding, indicating that MPP3 regulates trafficking and processing of nectin-1α. Further study showed that MPP3 interacts with nectin-3α, but not with nectin-2α, showing that the association of nectins with MPP3 is isoform-specific. MPP5, another MPP family member, interacts with nectins with varying affinity and facilitates surface expression of nectin-1α, nectin-2α, and nectin-3α. These data suggest that wide interactions between nectins and MPP family members may occur in various cell-cell junctions and that these associations may regulate trafficking and processing of nectins.