Novel inorganic crystal structures predicted using autonomous simulation agents.

We report a dataset of 96640 crystal structures discovered and computed using our previously published autonomous, density functional theory (DFT) based, active-learning workflow named CAMD (Computational Autonomy for Materials Discovery). Of these, 894 are within 1 meV/atom of the convex hull and 26826 are within 200 meV/atom of the convex hull. The dataset contains DFT-optimized pymatgen crystal structure objects, DFT-computed formation energies and phase stability calculations from the convex hull. It contains a variety of spacegroups and symmetries derived from crystal prototypes derived from known experimental compounds, and was generated from active learning campaigns of various chemical systems. This dataset can be used to benchmark future active-learning or generative efforts for structure prediction, to seed new efforts of experimental crystal structure discovery, or to construct new models of structure-property relationships.

Learning properties of ordered and disordered materials from multi-fidelity data.

Predicting the properties of a material from the arrangement of its atoms is a fundamental goal in materials science. While machine learning has emerged in recent years as a new paradigm to provide rapid predictions of materials properties, their practical utility is limited by the scarcity of high-fidelity data. Here, we develop multi-fidelity graph networks as a universal approach to achieve accurate predictions of materials properties with small data sizes. As a proof of concept, we show that the inclusion of low-fidelity Perdew-Burke-Ernzerhof band gaps greatly enhances the resolution of latent structural features in materials graphs, leading to a 22-45% decrease in the mean absolute errors of experimental band gap predictions. We further demonstrate that learned elemental embeddings in materials graph networks provide a natural approach to model disorder in materials, addressing a fundamental gap in the computational prediction of materials properties.

Deep neural networks for accurate predictions of crystal stability.

Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations remain comparatively expensive and scale poorly with system size. Here we show that deep neural networks utilizing just two descriptors-the Pauling electronegativity and ionic radii-can predict the DFT formation energies of C3A2D3O12 garnets and ABO3 perovskites with low mean absolute errors (MAEs) of 7-10 meV atom-1 and 20-34 meV atom-1, respectively, well within the limits of DFT accuracy. Further extension to mixed garnets and perovskites with little loss in accuracy can be achieved using a binary encoding scheme, addressing a critical gap in the extension of machine-learning models from fixed stoichiometry crystals to infinite universe of mixed-species crystals. Finally, we demonstrate the potential of these models to rapidly transverse vast chemical spaces to accurately identify stable compositions, accelerating the discovery of novel materials with potentially superior properties.

Functional Reactive Polymer Electrospun Matrix.

Synthetic multifunctional electrospun composites are a new class of hybrid materials with many potential applications. However, the lack of an efficient, reactive large-area substrate has been one of the major limitations in the development of these materials as advanced functional platforms. Herein, we demonstrate the utility of electrospun poly(glycidyl methacrylate) films as a highly versatile platform for the development of functional nanostructured materials anchored to a surface. The utility of this platform as a reactive substrate is demonstrated by grafting poly(N-isopropylacrylamide) to incorporate stimuli-responsive properties. Additionally, we demonstrate that functional nanocomposites can be fabricated using this platform with properties for sensing, fluorescence imaging, and magneto-responsiveness.

Versatile microfluidic droplets array for bioanalysis.

We propose a novel method to obtain versatile droplets arrays on a regional hydrophilic chip that is fabricated by PDMS soft lithography and regional plasma treatment. It enables rapid liquid dispensation and droplets array formation just making the chip surface in contact with solution. By combining this chip with a special Christmas Tree structure, the droplets array with concentrations in gradient is generated. It possesses the greatly improved performance of convenience and versatility in bioscreening and biosensing. For example, high throughput condition screening of toxic tests of CdSe quantum dots on HL-60 cells are conducted and cell death rates are successfully counted quickly and efficiently. Furthermore, a rapid biosensing approach for cancer biomarkers carcinoma embryonic antigen (CEA) is developed via magnetic beads (MBs)-based sandwich immunoassay methods.