Accelerated materials property predictions and design using motif-based fingerprints

Abstract

Data-driven approaches are particularly useful for computational materials discovery and design as they can be used for rapidly screening over a very large number of materials, thus suggesting lead candidates for further in-depth investigations. A central challenge of such approaches is to develop a numerical representation, often referred to as a fingerprint, of the materials. Inspired by recent developments in chem-informatics, we propose a class of hierarchical motif-based topological fingerprints for materials composed of elements such as C, O, H, N, F, etc., whose coordination preferences are well understood. We show that these fingerprints, when representing either molecules or crystals, may be effectively mapped onto a variety of properties using a similarity-based learning model and hence can be used to predict relevant properties of a material, given that its fingerprint can be defined. Two simple procedures are introduced to demonstrate that the learning model can be inverted to identify the desired fingerprints and then, to reconstruct molecules which possess a set of targeted properties.

References in corpus (9)

• A Higher-Accuracy van der Waals Density Functional
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Kernel methods in machine learning
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Predicting Crystal Structures with Data Mining of Quantum Calculations
• Crystal structure prediction using the Minima Hopping method
• Towards Direct-Gap Silicon Phases by the Inverse Band Structure Design Approach
• Inverse Quantum Chemistry: Concepts and Strategies for Rational Compound Design
• Comment on "Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning"

Cited by in corpus (28)

• Comparing molecules and solids across structural and alchemical space
• Machine learning prediction errors better than DFT accuracy
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics
• Polymer Informatics: Current Status and Critical Next Steps
• Predicting Electronic Structure Properties of Transition Metal Complexes with Neural Networks
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Polymer Informatics with Multi-Task Learning
• Polymer informatics at-scale with multitask graph neural networks
• Compositional optimization of hard-magnetic phases with machine-learning models
• Recognizing Local and Global Structural Motifs at the Atomic Scale
• Bioplastic Design using Multitask Deep Neural Networks
• Efficient implementation of atom-density representations
• Machine-learning approach for discovery of conventional superconductors
• Understanding Magnetic Properties of Actinide-Based Compounds from Machine Learning
• Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction
• Informatics-Driven Selection of Polymers for Fuel-Cell Applications
• Polymer Composites Informatics for Flammability, Thermal, Mechanical and Electrical Property Predictions
• Pressure-stabilized binary compounds of magnesium and silicon
• Multimodal machine learning with large language embedding model for polymer property prediction
• Screening of Therapeutic Agents for COVID-19 using Machine Learning and Ensemble Docking Simulations
• Adaptive Exploration and Optimization of Materials Crystal Structures
• Probabilistic deep learning approach for targeted hybrid organic-inorganic perovskites
• Shifting computational boundaries for complex organic materials
• Ollivier persistent Ricci curvature (OPRC) based molecular representation for drug design
• AI-Driven Design of poly(ethylene terephthalate)-replacement copolymers