Search for: All records

This article describes a machine learning guided framework for screening the potential toxicity impact of amine chemistries used in the synthesis of hybrid organic–inorganic perovskites. Using a combination of a probabilistic molecular fingerprint technique that encodes bond connectivity (MinHash) coupled to non‐linear data dimensionality reduction methods (Uniform Manifold Approximation and Projection), we develop an “Amine Atlas.” We show how the Amine Atlas can be used to rapidly screen the relative toxicity levels of amine molecules used in the synthesis of 2D and 3D perovskites and help identify safer alternatives. Our work also serves as a framework for rapidly identifying molecular similarity guided, structure–function relationships for safer materials chemistries that also incorporate sustainability/toxicity concerns.

 

This paper describes a database framework that enables one to rapidly explore systematics in structure-function relationships associated with new and emerging PFAS chemistries. The data framework maps high dimensional information associated with the SMILES approach of encoding molecular structure with functionality data including bioactivity and physicochemical property. This ‘PFAS-Map’ is a 3-dimensional unsupervised visualization tool that can automatically classify new PFAS chemistries based on current PFAS classification criteria. We provide examples on how the PFAS-Map can be utilized, including the prediction and estimation of yet unmeasured fundamental physical properties of PFAS chemistries, uncovering hierarchical characteristics in existing classification schemes, and the fusion of data from diverse sources.

 

In this study, we describe a method to construct a correlation map that captures the evolution of species‐specific dynamic information through the spatial correlation of high‐dimensional time‐series molecular dynamics (MD) simulation dataset for a series of borosilicate glasses. The correlation is based on ‘displacement’ between a pair of atomic configurations determined by the root mean square distance (RMSD) metric. We implement the correlation map as a quantitative visualization tool that provides a compressed representation of a high‐dimensional molecular dynamics dataset to inspect various physical aspects and capture distinct atomic dynamics—from large fluctuations to small local oscillations—for high‐temperature melt, linear cooling, and low‐temperature equilibration processes during molecular dynamics simulation of glasses. We capture species‐specific dynamics using this method that show different cooling dynamics for different glass formers and modifiers, especially the onset of slow dynamics and the variation of atomic dynamics at high temperatures. Furthermore, we show that the species‐specific atomic dynamics have structural origins that depend on the composition of the simulated borosilicate glasses. The correlation map serves as a visualization tool to rapidly survey changes in atomic configurations during different simulation conditions.

 

The use of machine learning techniques to expedite the discovery and development of new materials is an essential step towards the acceleration of a new generation of domain-specific highly functional material systems. In this paper, we use the test case of bulk metallic glasses to highlight the key issues in the field of high throughput predictions and propose a new probabilistic analysis of rules for glass forming ability using rough set theory. This approach has been applied to a broad range of binary alloy compositions in order to predict new metallic glass compositions. Our data driven approach takes into account not only a broad variety of thermodynamic, structural and kinetic based criteria, but also incorporates qualitative and descriptive attributes associated with eutectic points in phase diagrams. For the latter, we demonstrate the use of automated machine learning methods that go far beyond text recognition approaches by also being able to interpret phase diagrams. When combined with structural descriptors, this approach provides the foundations to develop a hierarchical probabilistic predication tool that can rank the feasibility of glass formation.

 

ChemMLis an open machine learning (ML) and informatics program suite that is designed to support and advance the data‐driven research paradigm that is currently emerging in the chemical and materials domain.ChemMLallows its users to perform various data science tasks and execute ML workflows that are adapted specifically for the chemical and materials context. Key features are automation, general‐purpose utility, versatility, and user‐friendliness in order to make the application of modern data science a viable and widely accessible proposition in the broader chemistry and materials community.ChemMLis also designed to facilitate methodological innovation, and it is one of the cornerstones of the software ecosystem for data‐driven in silico research.

This article is categorized under:

Software > Simulation Methods

Computer and Information Science > Chemoinformatics

Structure and Mechanism > Computational Materials Science

Software > Molecular Modeling

 

Abstract This paper introduces the use of topological data analysis (TDA) as an unsupervised machine learning tool to uncover classification criteria in complex inorganic crystal chemistries. Using the apatite chemistry as a template, we track through the use of persistent homology the topological connectivity of input crystal chemistry descriptors on defining similarity between different stoichiometries of apatites. It is shown that TDA automatically identifies a hierarchical classification scheme within apatites based on the commonality of the number of discrete coordination polyhedra that constitute the structural building units common among the compounds. This information is presented in the form of a visualization scheme of a barcode of homology classifications, where the persistence of similarity between compounds is tracked. Unlike traditional perspectives of structure maps, this new “Materials Barcode” schema serves as an automated exploratory machine learning tool that can uncover structural associations from crystal chemistry databases, as well as to achieve a more nuanced insight into what defines similarity among homologous compounds. 

Abstract The convergence of proton conduction and multiferroics is generating a compelling opportunity to achieve strong magnetoelectric coupling and magneto-ionics, offering a versatile platform to realize molecular magnetoelectrics. Here we describe machine learning coupled with additive manufacturing to accelerate the design strategy for hydrogen-bonded multiferroic macromolecules accompanied by strong proton dependence of magnetic properties. The proton switching magnetoelectricity occurs in three-dimensional molecular heterogeneous solids. It consists of a molecular magnet network as proton reservoir to modulate ferroelectric polarization, while molecular ferroelectrics charging proton transfer to reversibly manipulate magnetism. The magnetoelectric coupling induces a reversible 29% magnetization control at ferroelectric phase transition with a broad thermal hysteresis width of 160 K (192 K to 352 K), while a room-temperature reversible magnetic modulation is realized at a low electric field stimulus of 1 kV cm −1 . The findings of electrostatic proton transfer provide a pathway of proton mediated magnetization control in hierarchical molecular multiferroics. 

This paper presents a new approach for predicting thermodynamic properties of perovskites that harnesses deep learning and crystal structure fingerprinting based on Hirshfeld surface analysis. It is demonstrated that convolutional neural network methods capture critical features embedded in two-dimensional Hirshfeld surface fingerprints that enable a quantitative assessment of the formation energy of perovskites. Building on our recent work on lattice parameter prediction from Hirshfeld surface calculations, we show how transfer learning can be used to speed up the training of the neural network, allowing multiple properties to be trained using the same feature extraction layers. We also predict formation energies for various perovskite polymorphs, and our predictions are found to give generally improved performance over a well-established graph network method, but with the methods better suited to different types of datasets. Analysis of the structure types within the dataset reveals the Hirshfeld surface-based method to excel for the less symmetric and similar structures, while the graph network performs better for very symmetric and similar structures.