Search for: All records

Architected materials design across orders of magnitude length scale intrigues exceptional mechanical responses nonexistent in their natural bulk state. However, the so‐termed mechanical metamaterials, when scaling bottom down to the atomistic or microparticle level, remain largely unexplored and conventionally fall out of their coarse‐resolution, ordered‐pattern design space. Here, combining high‐throughput molecular dynamics (MD) simulations and machine learning (ML) strategies, some intriguing atomistic families of disordered mechanical metamaterials are discovered, as fabricated by melt quenching and exemplified herein by lightweight‐yet‐stiff cellular materials featuring a theoretical limit of linear stiffness–density scaling, whose structural disorder—rather than order—is key to reduce the scaling exponent and is simply controlled by the bonding interactions and their directionality that enable flexible tunability experimentally. Importantly, a systematic navigation in the forcefield landscape reveals that, in‐between directional and non‐directional bonding such as covalent and ionic bonds, modest bond directionality is most likely to promotes disordered packing of polyhedral, stretching‐dominated structures responsible for the formation of metamaterials. This work pioneers a bottom‐down atomistic scheme to design mechanical metamaterials formatted disorderly, unlocking a largely untapped field in leveraging structural disorder in devising metamaterials atomistically and, potentially, generic to conventional upscaled designs.

 

Numerical simulations have revolutionized material design. However, although simulations excel at mapping an input material to its output property, their direct application to inverse design has traditionally been limited by their high computing cost and lack of differentiability. Here, taking the example of the inverse design of a porous matrix featuring targeted sorption isotherm, we introduce a computational inverse design framework that addresses these challenges, by programming differentiable simulation on TensorFlow platform that leverages automated end-to-end differentiation. Thanks to its differentiability, the simulation is used to directly train a deep generative model, which outputs an optimal porous matrix based on an arbitrary input sorption isotherm curve. Importantly, this inverse design pipeline leverages the power of tensor processing units (TPU)—an emerging family of dedicated chips, which, although they are specialized in deep learning, are flexible enough for intensive scientific simulations. This approach holds promise to accelerate inverse materials design. 

Computational drug repurposing is a cost- and time-efficient approach that aims to identify new therapeutic targets or diseases (indications) of existing drugs/compounds. It is especially critical for emerging and/or orphan diseases due to its cheaper investment and shorter research cycle compared with traditional wet-lab drug discovery approaches. However, the underlying mechanisms of action (MOAs) between repurposed drugs and their target diseases remain largely unknown, which is still a main obstacle for computational drug repurposing methods to be widely adopted in clinical settings.

In this work, we propose KGML-xDTD: a Knowledge Graph–based Machine Learning framework for explainably predicting Drugs Treating Diseases. It is a 2-module framework that not only predicts the treatment probabilities between drugs/compounds and diseases but also biologically explains them via knowledge graph (KG) path-based, testable MOAs. We leverage knowledge-and-publication–based information to extract biologically meaningful “demonstration paths” as the intermediate guidance in the Graph-based Reinforcement Learning (GRL) path-finding process. Comprehensive experiments and case study analyses show that the proposed framework can achieve state-of-the-art performance in both predictions of drug repurposing and recapitulation of human-curated drug MOA paths.

KGML-xDTD is the first model framework that can offer KG path explanations for drug repurposing predictions by leveraging the combination of prediction outcomes and existing biological knowledge and publications. We believe it can effectively reduce “black-box” concerns and increase prediction confidence for drug repurposing based on predicted path-based explanations and further accelerate the process of drug discovery for emerging diseases.

 

A graph-based machine learning model is built to predict atom dynamics from their static structure, which, in turn, unveils the predictive power of static structure in dynamical evolution of disordered phases. 

Algorithmic case-based decision support provides examples to help human make sense of predicted labels and aid human in decision-making tasks. Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models consider as similar examples can be perceived as distinct by humans. As a result, they have limited effectiveness in case-based decision support. In this work, we incorporate ideas from metric learning with supervised learning to examine the importance of alignment for effective decision support. In addition to instance-level labels, we use human-provided triplet judgments to learn human-compatible decision-focused representations. Using both synthetic data and human subject experiments in multiple classification tasks, we demonstrate that such representation is better aligned with human perception than representation solely optimized for classification. Human-compatible representations identify nearest neighbors that are perceived as more similar by humans and allow humans to make more accurate predictions, leading to substantial improvements in human decision accuracies (17.8% in butterfly vs. moth classification and 13.2% in pneumonia classification). 

Designing and printing metamaterials with customizable architectures enables the realization of unprecedented mechanical behaviors that transcend those of their constituent materials. These behaviors are recorded in the form of response curves, with stress-strain curves describing their quasi-static footprint. However, existing inverse design approaches are yet matured to capture the full desired behaviors due to challenges stemmed from multiple design objectives, nonlinear behavior, and process-dependent manufacturing errors. Here, we report a rapid inverse design methodology, leveraging generative machine learning and desktop additive manufacturing, which enables the creation of nearly all possible uniaxial compressive stress‒strain curve cases while accounting for process-dependent errors from printing. Results show that mechanical behavior with full tailorability can be achieved with nearly 90% fidelity between target and experimentally measured results. Our approach represents a starting point to inverse design materials that meet prescribed yet complex behaviors and potentially bypasses iterative design-manufacturing cycles.

 

Motivated by numerous lower atmosphere climate model hindcast simulations, we performed simulations of the Earth's atmosphere from the surface up through the thermosphere‐ionosphere to reveal for the first time the century scale changes in the upper atmosphere from the 1920s through the 2010s using the Whole Atmosphere Community Climate Model—eXtended (WACCM‐X v. 2.1). We impose solar minimum conditions to get a clear indication of the effects of the long‐term forcing from greenhouse gas increases and changes of the Earth's magnetic field and to avoid the requirement for careful removal of the 11‐year solar cycle as in some previous studies using observations and models. These previous studies have shown greenhouse gas effects in the upper atmosphere but what has been missing is the time evolution with actual greenhouse gas increases throughout the last century, including the period of less than 5% increase prior to the space age and the transition to the over 25% increase in the latter half of the 20th century. Neutral temperature, density, and ionosphere changes are close to those reported in previous studies. Also, we find high correlation between the continuous carbon dioxide rate of change over this past century and that of temperature in the thermosphere and the ionosphere, attributed to the shorter adjustment time of the upper atmosphere to greenhouse gas changes relative to the longer time in the lower atmosphere. Consequently, WACCM‐X future scenario projections can provide valuable insight in the entire atmosphere of future greenhouse gas effects and mitigation efforts.

 

Fatigue-induced cracking in steel components and other brittle materials of civil structures is one of the primary mechanisms of degrading structural integrity and can lead to sudden failures. However, these cracks are often difficult to detect during visual inspections, and off-the-shelf sensing technologies can generally only be used to monitor already identified cracks because of their spatial localization. A solution is to leverage advances in large area electronics to cover large surfaces with skin-type sensors. Here, the authors propose an elastic and stretchable multifunctional skin sensor that combines optical and capacitive sensing properties. The multifunctional sensor consists of a soft stretchable structural color film sandwiched between transparent carbon nanotube electrodes to form a parallel plate capacitor. The resulting device exhibits a reversible and repeatable structural color change from light blue to deep blue with an angle-independent property, as well as a measurable change in capacitance, under external mechanical strain. The optical function is passive and engineered to visually assist in localizing fatigue cracks, and the electrical function is added to send timely warnings to infrastructure operators. The performance of the device is characterized in a free-standing configuration and further extended to a fatigue crack monitoring application. A correlation coefficient-based image processing method is developed to quantify the strain measured by the optical color response. Results show that the sensor performs well in detecting and quantifying fatigue cracks using both the color and capacitive signals. In particular, the color signal can be measured with inexpensive cameras, and the electrical signal yields good linearity, resolution, and accuracy. Tests conducted on two steel specimens demonstrate a minimum detectable crack length of 0.84 mm.