Search

CO2fixation is commonly limited by inefficiency of the CO2-fixing enzyme Rubisco. Eukaryotic algae concentrate and fix CO2in phase-separated condensates called pyrenoids, which complete up to one-third of global CO2fixation. Condensation of Rubisco in pyrenoids is dependent on interaction with disordered linker proteins that show little conservation between species. We developed a sequence-independent bioinformatic pipeline to identify linker proteins in green algae. We report the linker from Chlorellaand demonstrate that it binds a conserved site on the Rubisco large subunit. We show that the Chlorellalinker phase separates ChlamydomonasRubisco and that despite their separation by ~800 million years of evolution, the Chlorellalinker can support the formation of a functional pyrenoid in Chlamydomonas. This cross-species reactivity extends to plants, with the Chlorellalinker able to drive condensation of some native plant Rubiscos in vitro and in planta. Our results represent an exciting frontier for pyrenoid engineering in plants, which is modelled to increase crop yields.

There are two broad modeling paradigms in scientific applications: forward and inverse. While forward modeling estimates the observations based on known causes, inverse modeling attempts to infer the causes given the observations. Inverse problems are usually more critical as well as difficult in scientific applications as they seek to explore the causes that cannot be directly observed. Inverse problems are used extensively in various scientific fields, such as geophysics, health care and materials science. Exploring the relationships from properties to microstructures is one of the inverse problems in material science. It is challenging to solve the microstructure discovery inverse problem, because it usually needs to learn a one-to-many nonlinear mapping. Given a target property, there are multiple different microstructures that exhibit the target property, and their discovery also requires significant computing time. Further, microstructure discovery becomes even more difficult because the dimension of properties (input) is much lower than that of microstructures (output). In this work, we propose a framework consisting of generative adversarial networks and mixture density networks for inverse modeling of structure–property linkages in materials, i.e., microstructure discovery for a given property. The results demonstrate that compared to baseline methods, the proposed framework can overcome the above-mentioned challenges and discover multiple promising solutions in an efficient manner.

Functional materials and devices are usually morphologically complex and chemically heterogeneous. Their structures are often designed to be hierarchical because of the desired functionalities, which usually require many different components to work together in a coherent manner. The lithium ion battery, as an energy storage device, is a very typical example of this kind of structure. In a lithium ion battery, the cathode, anode, and separator are soaked in a liquid electrolyte, facilitating the back and forward shuttling of the lithium ions for energy storage and release. The desired performance of a lithium ion battery has many different aspects that need to be engineered and balanced depending on the targeted applications. In most cases, the cathode material has become the limiting factor for further improvements and, thus, has attracted intense attention from the research community.

The applications of artificial intelligence, machine learning, and deep learning techniques in the field of materials science are becoming increasingly common due to their promising abilities to extract and utilize data-driven information from available data and accelerate materials discovery and design for future applications. In an attempt to assist with this process, we deploy predictive models for multiple material properties, given the composition of the material. The deep learning models described here are built using a cross-property deep transfer learning technique, which leverages source models trained on large data sets to build target models on small data sets with different properties. We deploy these models in an online software tool that takes a number of material compositions as input, performs preprocessing to generate composition-based attributes for each material, and feeds them into the predictive models to obtain up to 41 different material property values. The material property predictor is available online at http://ai.eecs.northwestern.edu/MPpredictor.