Crystal Structure Prediction via Deep Learning.

We demonstrate the application of deep neural networks as a machine-learning tool for the analysis of a large collection of crystallographic data contained in the crystal structure repositories. Using input data in the form of multiperspective atomic fingerprints, which describe coordination topology around unique crystallographic sites, we show that the neural-network model can be trained to effectively distinguish chemical elements based on the topology of their crystallographic environment. The model also identifies structurally similar atomic sites in the entire data set of ∼50000 crystal structures, essentially uncovering trends that reflect the periodic table of elements. The trained model was used to analyze templates derived from the known crystal structures in order to predict the likelihood of forming new compounds that could be generated by placing elements into these structural templates in a combinatorial fashion. Statistical analysis of predictive performance of the neural-network model, which was applied to a test set of structures never seen by the model during training, indicates its ability to predict known elemental compositions with a high likelihood of success. In ∼30% of cases, the known compositions were found among the top 10 most likely candidates proposed by the model. These results suggest that the approach developed in this work can be used to effectively guide the synthetic efforts in the discovery of new materials, especially in the case of systems composed of three or more chemical elements.

• Publication year

  2018

• Venue

  Journal of the American Chemical Society

• Publication date

  2018-06-06

• Fields of study

  Chemistry, Medicine, Materials Science, Computer Science

• Identifiers
  DOI 10.1021/jacs.8b03913PMID 29874459
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Discovery of Intermetallic Compounds from Traditional to Machine-Learning Approaches.

  2018cited by this paper
• Parallels in Structural Chemistry between the Molecular and Metallic Realms Revealed by Complex Intermetallic Phases.

  2018cited by this paper
• Learning a Local-Variable Model of Aromatic and Conjugated Systems

  2018cited by this paper
• Inverse Band Structure Design via Materials Database Screening: Application to Square Planar Thermoelectrics

  2018cited by this paper
• XtalOpt version r11: An open-source evolutionary algorithm for crystal structure prediction

  2018cited by this paper
• Disentangling Structural Confusion through Machine Learning: Structure Prediction and Polymorphism of Equiatomic Ternary Phases ABC.

  2017cited by this paper
• Computer-aided design of metal chalcohalide semiconductors: from chemical composition to crystal structure

  2017cited by this paper
• Machine learning for the structure–energy–property landscapes of molecular crystals

  2017cited by this paper
• Prediction of Organic Reaction Outcomes Using Machine Learning

  2017cited by this paper
• Deep learning for computational chemistry

  2017cited by this paper
• Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks

  2017cited by this paper
• Predicting the Thermodynamic Stability of Solids Combining Density Functional Theory and Machine Learning

  2017cited by this paper
• Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn.

  2017cited by this paper
• Classification of crystal structure using a convolutional neural network

  2017cited by this paper
• Construction of crystal structure prototype database: methods and applications

  2017cited by this paper
• Neural Networks for the Prediction of Organic Chemistry Reactions

  2016cited by this paper
• Machine-learning-assisted materials discovery using failed experiments

  2016cited by this paper
• Quantum-chemical insights from deep tensor neural networks

  2016cited by this paper
• Functionality-Directed Screening of Pb-Free Hybrid Organic–Inorganic Perovskites with Desired Intrinsic Photovoltaic Functionalities

  2016cited by this paper
• Prediction of Host-Guest Na-Fe Intermetallics at High Pressures.

  2016cited by this paper
• The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies

  2015cited by this paper
• Decomposition Products of Phosphine Under Pressure: PH2 Stable and Superconducting?

  2015cited by this paper
• Theoretical predictions of novel superconducting phases of BaGe3 stable at atmospheric and high pressures.

  2015cited by this paper
• Deep Learning

  2015cited by this paper
• Design and discovery of a novel half-Heusler transparent hole conductor made of all-metallic heavy elements

  2014cited by this paper
• Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds.

  2014cited by this paper
• The Configurational Space of Rocksalt‐Type Oxides for High‐Capacity Lithium Battery Electrodes

  2014cited by this paper
• A stable compound of helium and sodium at high pressure.

  2013cited by this paper
• Theoretical prediction and experimental realization of new stable inorganic materials using the inverse design approach.

  2013cited by this paper
• Representation Learning: A Review and New Perspectives

  2012cited by this paper
• Revisiting the Zintl-Klemm concept: alkali metal trielides.

  2011cited by this paper
• Connecting the chemical and physical viewpoints of what determines structure: from 1-D chains to γ-brasses.

  2011cited by this paper
• Selection of convolution kernel in non-uniform fast Fourier transform for Fourier domain optical coherence tomography.

  2011cited by this paper
• Crystal fingerprint space--a novel paradigm for studying crystal-structure sets.

  2010cited by this paper
• Ionic high-pressure form of elemental boron

  2009cited by this paper
• Interpenetrating polar and nonpolar sublattices in intermetallics: the NaCd(2) structure.

  2007cited by this paper
• USPEX - Evolutionary crystal structure prediction

  2006cited by this paper
• Predicting crystal structure by merging data mining with quantum mechanics

  2006cited by this paper
• Data Mining in and around Crystal Structure Databases

  2006cited by this paper
• Crystal structure prediction using ab initio evolutionary techniques: principles and applications.

  2006cited by this paper
• High-throughput ab initio analysis of the Bi–In, Bi–Mg, Bi–Sb, In–Mg, In–Sb, and Mg–Sb systems

  2005cited by this paper
• The Nowotny chimney ladder phases: whence the 14 electron rule?

  2004cited by this paper
• Predicting crystal structures with data mining of quantum calculations.

  2003cited by this paper
• Bonding and structure of intermetallics: a new bond order potential

  1991cited by this paper
• Structure maps for. Pseudobinary and ternary phases

  1988cited by this paper
• The factors influencing solid state structure — A modern Mendeleyevian answer

  1981cited by this paper
• The theoretical prediction of the physical properties of many electron atoms and ions. Mole refraction, diamagnetic susceptibility, and extension in space

  1927cited by this paper
• Crystal structure and chemical constitution

  year unknowncited by this paper
• Über den Bau der Atome und Moleküle im Licht der Dispersionstheorie

  year unknowncited by this paper

• Deep learning generative model for conditional crystal structure prediction of sodium amide

  2026cites this paper
• The Characterization of Curved Grain Boundary in Nickel-Based Superalloy Formed During Heat Treatment

  2026cites this paper
• Soft Computing Approaches toward Density-Based Analysis of Many-Electron Systems

  2026cites this paper
• Data-driven sustainability assessment of advanced manufacturing processes

  2026cites this paper
• Organic–Inorganic Metal Halide Perovskites: Toward Stability, Chirality, and AI-Guided Discovery

  2026cites this paper
• High-throughput screening of thermodynamically stable molecular crystal forms using crystal structure prediction method based on deep graph neural network

  2026cites this paper
• From density functional theory to machine learning: Emerging paradigms in energy materials discovery

  2026cites this paper
• Bridging text and crystal structures: literature-driven contrastive learning for materials science

  2025cites this paper
• Conditional Generative Modeling for Amorphous Multi-Element Materials

  2025cites this paper
• Utilizing Machine Learning to Advance Battery Materials Design: Challenges and Prospects

  2025cites this paper
• Programmable friction control in 3D printed patterned multi-materials: a flexible design strategy

  2025cites this paper
• Machine learning boosted first principles model predictions of DSC decomposition energies for early‐stage material screening

  2025cites this paper
• Disentangling autoencoders and spherical harmonics for efficient shape classification in crystal growth simulations

  2025cites this paper
• Crystal Structure Prediction Using a Self-Attention Neural Network and Semantic Segmentation

  2025cites this paper
• Bridging Theory and Experiment in Materials Discovery: Machine-Learning-Assisted Prediction of Synthesizable Structures

  2025cites this paper
• Data-driven approach to the performance of SnSe-based thermoelectric materials

  2025cites this paper
• From Algorithms to Applications: A Comprehensive Review of Machine Learning in Computational Materials Science

  2025cites this paper
• Hierarchical incremental learning deciphers molecular arrangements in multi-component materials

  2025cites this paper
• A perspective on design principle of solid electrolytes

  2025cites this paper
• Cocrystal Technology in the Screening of Pharmaceutical Solid Forms and Chiral Resolution of Drugs: a Review

  2025cites this paper
• Environmentally friendly PAEs alternatives with desired synthesizability by machine learning methods

  2025cites this paper
• Recent progress in the design and application of machine learning for the hydrogen evolution reaction in electrocatalysis and photocatalysis

  2025cites this paper
• Efficient Molecular Crystal Structure Prediction and Stability Assessment with AIMNet2 Neural Network Potentials

  2025cites this paper
• Machine learning-assisted fabrication for CoCrNi-TiCx composite coatings: process parameters, microstructure and properties

  2025cites this paper
• Deep potential-driven structure exploration of ice polymorphs

  2025cites this paper
• Does Hessian Data Improve the Performance of Machine Learning Potentials?

  2025cites this paper
• Advances in Deep Learning-Driven Metasurface Design and Application in Holographic Imaging

  2025cites this paper
• Design of the amorphous/crystalline TiO2 nanocomposites via machine learning for photocatalytic applications

  2025cites this paper
• Advances in high-pressure materials discovery enabled by machine learning

  2025cites this paper
• Energy Loss Functions for Physical Systems

  2025cites this paper
• Quality by Computational Design: Harnessing AI to Advance Rational Drug Development.

  2025cites this paper
• Deciphering the complexities of crystalline state(s) with molecular simulations

  2025cites this paper
• Target-property-guided material generation: towards on-demand inverse design of materials

  2025cites this paper
• Progress of AI-Driven Drug–Target Interaction Prediction and Lead Optimization

  2025cites this paper
• High-density superhard carbon stabilized by strain induced phase-transition and light absorption enhancement of its low-dimensional graphyne under high-pressure

  2025cites this paper
• Advancing the Proton Exchange Membrane Water Electrolysis: Perspective on the Affordable Hydrogen Production Cost

  2025cites this paper
• Machine learning for 2D material–based devices

  2025cites this paper
• Harnessing the leading edge: machine learning ventures in chemistry and materials science.

  2025cites this paper
• Advanced Deep Learning Approaches in Metasurface Modeling and Design: A Review

  2025cites this paper
• A Representation of Crystal Systems and Space Groups based on the Variance of Atomic Positions (VAP): Case of 2D materials

  2025cites this paper
• Machine Learning in nanoarchitectonics.

  2025cites this paper
• Machine Learning-Driven Molecular Dynamics Investigation of the Physical and Heat Transfer Properties of Magnesium

  2025cites this paper
• Data science of the in silico crystallization

  2025cites this paper
• Predicting thermodynamic stability of inorganic compounds using ensemble machine learning based on electron configuration

  2025cites this paper
• Robust image descriptor for machine learning based data reduction in serial crystallography

  2024cites this paper
• Cocrystal Prediction Based on Deep Forest Model—A Case Study of Febuxostat

  2024cites this paper
• Multi-Objective Quality-Diversity for Crystal Structure Prediction

  2024cites this paper
• Polymorph Identification for Flexible Molecules: Linear Regression Analysis of Experimental and Calculated Solution- and Solid-State NMR Data

  2024cites this paper
• A Data-Driven Approach for the Fast Prediction of Macrosegregation

  2024cites this paper
• Spatiotemporal prediction and characterization of microstructure evolution during in-situ heat treatment using a deep learning algorithm

  2024cites this paper
• The prediction of single-molecule magnet properties via deep learning

  2024cites this paper
• Advances in materials informatics: a review

  2024cites this paper
• Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis

  2024cites this paper
• AlphaCrystal-II: Distance matrix based crystal structure prediction using deep learning

  2024cites this paper
• Machine-learning accelerated structure search for ligand-protected clusters.

  2024cites this paper
• Advancing Efficiency in Mineral Construction Materials Recycling: A Comprehensive Approach Integrating Machine Learning and X-ray Diffraction Analysis

  2024cites this paper
• Artificial intelligence for personalized nanomedicine; from material selection to patient outcomes

  2024cites this paper
• Data-Quality-Navigated Machine Learning Strategy with Chemical Intuition to Improve Generalization.

  2024cites this paper
• Insights into Thermal Conductivity of Pnictogen Chalcogenides: Machine Learning Stereochemically Active Lone Pairs and Hybridization

  2024cites this paper
• Rethinking Gradient-Based Methods: Multi-Property Materials Design Beyond Differentiable Targets

  2024cites this paper
• Enhanced Powder Characteristics of Succinic Acid through Crystallization Techniques for Food Industry Application

  2024cites this paper
• Data-Driven Machine Learning Strategy for Designing Metal-Ion-Doped γ-Bi2MoO6 Photocatalysts to Enhance Degradation Performance.

  2024cites this paper
• Material Visions: Advancing Crystal Structure Prediction with Powerful Text Generation Models

  2024cites this paper
• Discovery of Bimetallic Hexagonal MBene Mo2ErB3T2.5 (T = O, F, and Cl).

  2024cites this paper
• Deep learning for symmetry classification using sparse 3D electron density data for inorganic compounds

  2024cites this paper
• Integrating Active Learning and DFT for Fast-Tracking Single-Atom Alloy Catalysts in CO2-to-Fuel Conversion.

  2024cites this paper
• Boosting-Crystal Graph Convolutional Neural Network for Predicting Highly Imbalanced Data: A Case Study for Metal-Insulator Transition Materials.

  2024cites this paper
• Machine Learning-Based Investigation of Atomic Packing Effects: Chemical Pressures at the Extremes of Intermetallic Complexity.

  2024cites this paper
• On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fields

  2024cites this paper
• Different applications of machine learning approaches in materials science and engineering: Comprehensive review

  2024cites this paper
• Proton Conducting Neuromorphic Materials and Devices.

  2024cites this paper
• Recent Advances in the Application of Machine Learning to Crystal Behavior and Crystallization Process Control

  2024cites this paper
• AI-Assisted Insole Sensing System for Multifunctional Plantar-Healthcare Applications.

  2024cites this paper
• Quantifying near-symmetric molecular distortion using symmetry-coordinate structural decomposition

  2024cites this paper
• Navigating challenges and opportunities of machine learning in hydrogen catalysis and production processes: beyond algorithm development

  2024cites this paper
• Multi-scale computational study of high-temperature corrosion and the design of corrosion-resistant alloys

  2024cites this paper
• Artificial Intelligence Assisted Pharmaceutical Crystallization

  2024cites this paper
• Machine learning recognition of hybrid lead halide perovskites and perovskite-related structures from X-ray diffraction patterns.

  2024cites this paper
• Cascading symmetry constraint during machine learning-enabled structural search for sulfur-induced Cu(111)-(43×43) surface reconstruction.

  2024cites this paper
• Energy landscapes-Past, present, and future: A perspective.

  2024cites this paper
• Synthesizability of materials stoichiometry using semi-supervised learning

  2024cites this paper
• Predicting Crystalline Material Properties with AI: Bridging Molecular to Particle Scales

  2024cites this paper
• HyStor: An experimental database of hydrogen storage properties for various metal alloy classes

  2024cites this paper
• CGWGAN: crystal generative framework based on Wyckoff generative adversarial network

  2024cites this paper
• Enhancing crystal structure prediction by combining computational and experimental data via graph networks

  2023cites this paper
• Machine Learning-Accelerated Discovery of A2BC2 Ternary Electrides with Diverse Anionic Electron Densities.

  2023cites this paper
• Deep learning in alloy material microstructures： Application and prospects

  2023cites this paper
• A machine learning framework for predicting physical properties in configuration space of gate alloys

  2023cites this paper
• Recent Progress on Phase Engineering of Nanomaterials.

  2023cites this paper
• Lightweight Extendable Stacking Framework for Structure Classification in Atomistic Simulations.

  2023cites this paper
• Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction

  2023cites this paper
• Machine learning meets quantum mechanics in catalysis

  2023cites this paper
• Machine Learning Accelerated Study of Defect Energy Levels in Perovskites

  2023cites this paper
• Exploring energy landscapes for solid-state systems with variable cells at the extended tight-binding level.

  2023cites this paper
• Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm

  2023cites this paper
• High-Throughput Screening of Promising Redox-Active Molecules with MolGAT

  2023cites this paper
• Simplicial Message Passing for Chemical Property Prediction

  2023cites this paper
• Materials cartography: A forward-looking perspective on materials representation and devising better maps

  2023cites this paper
• A Deep Learning Approach to Powder X‐Ray Diffraction Pattern Analysis: Addressing Generalizability and Perturbation Issues Simultaneously

  2023cites this paper
• Explainable machine learning for diffraction patterns

  2023cites this paper