Deep Learning-Based Prediction of Contact Maps and Crystal Structures of Inorganic Materials.

Crystal structure prediction is one of the major unsolved problems in materials science. Traditionally, this problem is formulated as a global optimization problem for which global search algorithms are combined with first-principles free energy calculations to predict the ground-state crystal structure of a given material composition. These ab initio algorithms are currently too slow for predicting complex material structures. Inspired by the AlphaFold algorithm for protein structure prediction, herein, we propose AlphaCrystal, a crystal structure prediction algorithm that combines a deep residual neural network model for predicting the atomic contact map of a target material followed by three-dimensional (3D) structure reconstruction using genetic algorithms. Extensive experiments on 20 benchmark structures showed that our AlphaCrystal algorithm can predict structures close to the ground truth structures, which can significantly speed up the crystal structure prediction and handle relatively large systems.

Global Mapping of Structures and Properties of Crystal Materials.

Understanding materials' composition-structure-function relationships is of critical importance for the design and discovery of novel functional materials. While most such studies focus on individual materials, we conducted a global mapping study of all known materials deposited in the Materials Project database to investigate their distributions in the space of a set of seven compositional, structural, physical, and neural latent descriptors. These two-dimensional materials maps along with their density maps allow us to illustrate the distribution of the patterns and clusters of different shapes, which indicates the propensity of these materials and the tinkering history of existing materials. We then overlap the material properties such as composition prototypes and piezoelectric properties over the background material maps to study the relationships of how material compositions and structures affect their physical properties. We also use these maps to study the spatial distributions of properties of known inorganic materials, in particular those of local vicinities in structural space such as structural density and functional diversity. These maps provide a uniquely comprehensive overview of materials and space and thus reveal previously undescribed fundamental properties. Our methodology can be easily extended by other researchers to generate their own global material maps with different background maps and overlap properties for both distribution understanding and cluster-based new material discovery. The source code for feature generation and generated maps is available at https://github.com/usccolumbia/matglobalmapping.

DeepXRD, a Deep Learning Model for Predicting XRD spectrum from Material Composition.

One of the long-standing problems in materials science is how to predict a material's structure and then its properties given only its composition. Experimental characterization of crystal structures has been widely used for structure determination, which is, however, too expensive for high-throughput screening. At the same time, directly predicting crystal structures from compositions remains a challenging unsolved problem. Herein we propose a deep learning algorithm for predicting the XRD spectrum given only the composition of a material, which can then be used to infer key structural features for downstream structural analysis such as crystal system or space group classification or crystal lattice parameter determination or materials property prediction. Benchmark studies on two data sets show that our DeepXRD algorithm can achieve good performance for XRD prediction as evaluated over our test sets. It can thus be used in high-throughput screening in the huge materials composition space for materials discovery.

Scalable deeper graph neural networks for high-performance materials property prediction.

Machine-learning-based materials property prediction models have emerged as a promising approach for new materials discovery, among which the graph neural networks (GNNs) have shown the best performance due to their capability to learn high-level features from crystal structures. However, existing GNN models suffer from their lack of scalability, high hyperparameter tuning complexity, and constrained performance due to over-smoothing. We propose a scalable global graph attention neural network model DeeperGATGNN with differentiable group normalization (DGN) and skip connections for high-performance materials property prediction. Our systematic benchmark studies show that our model achieves the state-of-the-art prediction results on five out of six datasets, outperforming five existing GNN models by up to 10%. Our model is also the most scalable one in terms of graph convolution layers, which allows us to train very deep networks (e.g., >30 layers) without significant performance degradation. Our implementation is available at https://github.com/usccolumbia/deeperGATGNN.

TCSP: a Template-Based Crystal Structure Prediction Algorithm for Materials Discovery.

Fast and accurate crystal structure prediction (CSP) algorithms and web servers are highly desirable for the exploration and discovery of new materials out of the infinite chemical design space. However, currently, the computationally expensive first-principles calculation-based CSP algorithms are applicable to relatively small systems and are out of reach of most materials researchers. Several teams have used an element substitution approach for generating or predicting new structures, but usually in an ad hoc way. Here we develop a template-based crystal structure prediction (TCSP) algorithm and its companion web server, which makes this tool accessible to all materials researchers. Our algorithm uses elemental/chemical similarity and oxidation states to guide the selection of template structures and then rank them based on the substitution compatibility and can return multiple predictions with ranking scores in a few minutes. A benchmark study on the 98290 formulas of the Materials Project database using leave-one-out evaluation shows that our algorithm can achieve high accuracy (for 13145 target structures, TCSP predicted their structures with root-mean-square deviation < 0.1) for a large portion of the formulas. We have also used TCSP to discover new materials of the Ga-B-N system, showing its potential for high-throughput materials discovery. Our user-friendly web app TCSP can be accessed freely at www.materialsatlas.org/crystalstructure on our MaterialsAtlas.org web app platform.

Crystal structure prediction of materials with high symmetry using differential evolution.

Crystal structure determines properties of materials. With the crystal structure of a chemical substance, many physical and chemical properties can be predicted by first-principles calculations or machine learning models. Since it is relatively easy to generate a hypothetical chemically valid formula, crystal structure prediction becomes an important method for discovering new materials. In our previous work, we proposed a contact map-based crystal structure prediction method, which uses global optimization algorithms such as genetic algorithms to maximize the match between the contact map of the predicted structure and the contact map of the real crystal structure to search for the coordinates at the Wyckoff positions (WP), demonstrating that known geometric constraints (such as the contact map of the crystal structure) help the crystal structure reconstruction. However, when predicting the crystal structure with high symmetry, we found that the global optimization algorithm has difficulty to find an effective combination of WP that satisfies the chemical formula, which is mainly caused by the inconsistency between the dimensionality of the contact map of the predicted crystal structure and the dimensionality of the contact map of the target crystal structure. This makes it challenging to predict the crystal structures of high-symmetry crystals. In order to solve this problem, here we propose to use PyXtal to generate and filter random crystal structures with given symmetry constraints based on the information such as chemical formulas and space groups. With contact map as the optimization goal, we use differential evolution algorithms to search for non-special coordinates at the WP to realize the structure prediction of high-symmetry crystal materials. Our experimental results show that our proposed algorithm CMCrystalHS can effectively solve the problem of inconsistent contact map dimensions and predict the crystal structures with high symmetry.

Mlatticeabc: Generic Lattice Constant Prediction of Crystal Materials Using Machine Learning.

Lattice constants such as unit cell edge lengths and plane angles are important parameters of the periodic structures of crystal materials. Predicting crystal lattice constants has wide applications in crystal structure prediction and materials property prediction. Previous work has used machine learning models such as neural networks and support vector machines combined with composition features for lattice constant prediction and has achieved a maximum performance for cubic structures with an average coefficient of determination (R 2) of 0.82. Other models tailored for special materials family of a fixed form such as ABX3 perovskites can achieve much higher performance due to the homogeneity of the structures. However, these models trained with small data sets are usually not applicable to generic lattice parameter prediction of materials with diverse compositions. Herein, we report MLatticeABC, a random forest machine learning model with a new descriptor set for lattice unit cell edge length (a, b, c) prediction which achieves an R 2 score of 0.973 for lattice parameter a of cubic crystals with an average R 2 score of 0.80 for a prediction of all crystal systems. The R 2 scores are between 0.498 and 0.757 over lattice b and c prediction performance of the model, which could be used by just inputting the molecular formula of the crystal material to get the lattice constants. Our results also show significant performance improvement for lattice angle predictions. Source code and trained models can be freely accessed at https://github.com/usccolumbia/MLatticeABC.

Machine Learning-Based Prediction of Crystal Systems and Space Groups from Inorganic Materials Compositions.

Structural information of materials such as the crystal systems and space groups are highly useful for analyzing their physical properties. However, the enormous composition space of materials makes experimental X-ray diffraction (XRD) or first-principle-based structure determination methods infeasible for large-scale material screening in the composition space. Herein, we propose and evaluate machine-learning algorithms for determining the structure type of materials, given only their compositions. We couple random forest (RF) and multiple layer perceptron (MLP) neural network models with three types of features: Magpie, atom vector, and one-hot encoding (atom frequency) for the crystal system and space group prediction of materials. Four types of models for predicting crystal systems and space groups are proposed, trained, and evaluated including one-versus-all binary classifiers, multiclass classifiers, polymorphism predictors, and multilabel classifiers. The synthetic minority over-sampling technique (SMOTE) is conducted to mitigate the effects of imbalanced data sets. Our results demonstrate that RF with Magpie features generally outperforms other algorithms for binary and multiclass prediction of crystal systems and space groups, while MLP with atom frequency features is the best one for structural polymorphism prediction. For multilabel prediction, MLP with atom frequency and binary relevance with Magpie models are the best for predicting crystal systems and space groups, respectively. Our analysis of the related descriptors identifies a few key contributing features for structural-type prediction such as electronegativity, covalent radius, and Mendeleev number. Our work thus paves a way for fast composition-based structural screening of inorganic materials via predicted material structural properties.

Effect of repeated Kangaroo Mother Care on repeated procedural pain in preterm infants: A randomized controlled trial.

BACKGROUND: Preterm infants' repeated exposure to painful procedures may lead to negative consequences. Thus, non-pharmacological pain management is essential due to medication side effects. Kangaroo Mother Care, which aims at offering human care to neonates, has been established for the treatment of a single painful procedure, but the effectiveness of Kangaroo Mother Care across repeated painful procedures is unknown. OBJECTIVE: To test the effectiveness of repeated Kangaroo Mother Care on repeated heel-stick pain in preterm neonates. DESIGN: Randomized controlled trial. SETTING: Level III Neonatal Intensive Care Unit at a large teaching hospital in northeast China. METHOD: Preterm infants (gestational age less than 37 weeks) (n=80) were recruited and randomly assigned using a random table format to either an incubator group (n=40) or Kangaroo Mother Care group (n=40). Pain assessments were carried out during four routine heel stick procedures. For the first heel stick, preterm infants in each group received no intervention (routinely stayed in incubator). During the next three heel sticks, the infants in Kangaroo Mother Care group received heel sticks during Kangaroo Mother Care, while infants in the incubator group received heel sticks in incubator. The procedure of each heel stick included 3 phases: baseline, blood collection and recovery. Crying, grimacing and heart rate in response to pain were evaluated at each phase across four heel sticks by three trained independent observers who were blinded to the purpose of the study. Data were analyzed by analysis of variance (ANOVA), with repeated measures at different evaluation phases of heel stick. RESULTS: 75 preterm infants completed the protocol. Between-group comparison revealed that preterm infants' heart rate was significantly lower, and the duration of crying and facial grimacing were both significantly shorter in the Kangaroo Mother Care group (n=38) than the incubator group (n=37) from the blood collection phase to recovery phase during repeated heel sticks. No significant within-group difference was found in heart rate between the baseline phase and recovery phase through repeated heel sticks for Kangaroo Mother Care group. In contrast, the incubator group experienced significant within group differences in heart rate between baseline and recovery through repeated heel sticks. CONCLUSION: The effect of repeated Kangaroo Mother Care analgesia remains stable in preterm infants over repeated painful procedures. Given the many invasive procedures that are part of clinical care in preterm infants and most mothers preferred to provide comfort for their infants during painful procedures, Kangaroo Mother Care may be a safe analgesic alternative in preterm infants in whom it is feasible.