scholarly journals How to represent crystal structures for machine learning: Towards fast prediction of electronic properties

2014 ◽  
Vol 89 (20) ◽  
Author(s):  
K. T. Schütt ◽  
H. Glawe ◽  
F. Brockherde ◽  
A. Sanna ◽  
K. R. Müller ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electronic Properties ◽  
Crystal Structures ◽  
Fast Prediction

scholarly journals Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using Complementary DFT and Machine Learning Approaches

2018 ◽  
Vol 2 (1) ◽  
pp. 1800128 ◽  
Author(s):  
Sherif Abdulkader Tawfik ◽  
Olexandr Isayev ◽  
Catherine Stampfl ◽  
Joe Shapter ◽  
David A. Winkler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electronic Properties ◽  
2D Materials ◽  
Learning Approaches ◽  
Structural And Electronic Properties ◽  
Efficient Prediction

scholarly journals Electronic properties and crystal structures of double-perovskites, Ba2BiIIIBiVO6,Ba2PrBiO6, and Ba2PrSbO6: First-principles study

2020 ◽  
Vol 7 (6) ◽  
pp. 065505
Author(s):  
Kazume Nishidate ◽  
Achy Adiko ◽  
Michiaki Matsukawa ◽  
Haruka Taniguchi ◽  
Arisa Sato ◽  
...  
Keyword(s):  
Electronic Properties ◽  
Crystal Structures ◽  
First Principles ◽  
Double Perovskites ◽  
First Principles Study

scholarly journals Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained On Docked Poses

2021 ◽  
Author(s):  
Fergus Boyles ◽  
Charlotte M Deane ◽  
Garrett Morris
Keyword(s):  
Machine Learning ◽  
Ligand Binding ◽  
Crystal Structures ◽  
Binding Affinity ◽  
Scoring Function ◽  
Scoring Functions ◽  
Data Set ◽  
Core Sets ◽  
Strong Performance

Machine learning scoring functions for protein-ligand binding affinity have been found to consistently outperform classical scoring functions when trained and tested on crystal structures of bound protein-ligand complexes. However, it is less clear how these methods perform when applied to docked poses of complexes.<br><br>We explore how the use of docked, rather than crystallographic, poses for both training and testing affects the performance of machine learning scoring functions. Using the PDBbind Core Sets as benchmarks, we show that the performance of a structure-based machine learning scoring function trained and tested on docked poses is lower than that of the same scoring function trained and tested on crystallographic poses. We construct a hybrid scoring function by combining both structure-based and ligand-based features, and show that its ability to predict binding affinity using docked poses is comparable to that of purely structure-based scoring functions trained and tested on crystal poses. Despite strong performance on docked poses of the PDBbind Core Sets, we find that our hybrid scoring function fails to generalise to anew data set, demonstrating the need for improved scoring functions and additional validation benchmarks. <br><br>Code and data to reproduce our results are available from https://github.com/oxpig/learning-from-docked-poses.

A new, layered monoclinic phase of Co3O4 at high pressure

2015 ◽  
Vol 17 (30) ◽  
pp. 19957-19961 ◽  
Author(s):  
Thanayut Kaewmaraya ◽  
Wei Luo ◽  
Xiao Yang ◽  
Puspamitra Panigrahi ◽  
Rajeev Ahuja
Keyword(s):  
High Pressure ◽  
Electronic Properties ◽  
Crystal Structures ◽  
Monoclinic Phase

We present the crystal structures and electronic properties of a Co3O4 spinel under high pressure.

Topotactic Intercalation of a Metallic Dense Host Matrix Chalcogenide with Large Electron−Phonon Coupling:  Crystal Structures and Electronic Properties of LixMo2SbS2(0 ≤x< 0.7)

2007 ◽  
Vol 19 (1) ◽  
pp. 69-78 ◽  
Author(s):  
Alexandros Lappas ◽  
Christopher J. Nuttall ◽  
Zacharias G. Fthenakis ◽  
Vladimir Yu. Pomjakushin ◽  
Mark A. Roberts
Keyword(s):  
Electronic Properties ◽  
Crystal Structures ◽  
Phonon Coupling ◽  
Host Matrix ◽  
Electron Phonon Coupling

Anion substitution and influence of sulfur on the crystal structures, phase transitions, and electronic properties of mixed TiO2/TiS2 compounds

2021 ◽  
Vol 77 (5) ◽  
pp. 833-847
Author(s):  
Dušica Jovanović ◽  
Dejan Zagorac ◽  
Branko Matović ◽  
Aleksandra Zarubica ◽  
Jelena Zagorac
Keyword(s):  
Phase Transitions ◽  
Electronic Properties ◽  
Crystal Structures ◽  
Crystal Form ◽  
Structure Type ◽  
Structure Property ◽  
Anion Substitution ◽  
Metastable Structures ◽  
Semiconducting Properties ◽  
Structure Property Relationship

Recent studies of TiO2/TiS2 nanostructures with various morphologies have been reported, usually showing improved properties with applications from electronics and catalysis to solar cells and medicine. However, there is a limited number of studies on the crystal structures of TiO2/TiS2 compounds with corresponding properties. In this research, relevant crystal structures of TiO1–x S x (x = 0, 0.25, 0.5, 0.75 and 1) solid solutions were investigated using an ab initio method. For each composition, crystal structures adopting anatase, rutile and CdI2 structure type were calculated on LDA-PZ and GGA-PBE levels of theory. Novel phase transitions and predicted structures are presented, and apart from several interesting metastable structures, a very interesting pressure-induced phase transition is found in the TiOS compound. Furthermore, electronic properties were studied through the dependence of semiconducting properties on dopant concentration. The first description of the electronic properties of the mixed TiO1–x S x compounds in crystal form has been presented, followed by a detailed study of the structure–property relationship, which will possibly have numerous industrial and technological applications.

scholarly journals Database of Two-Dimensional Hybrid Perovskite Materials: Open-Access Collection of Crystal Structures, Band Gaps, and Atomic Partial Charges Predicted by Machine Learning

2020 ◽  
Vol 32 (17) ◽  
pp. 7383-7388 ◽  
Author(s):  
Ekaterina I. Marchenko ◽  
Sergey A. Fateev ◽  
Andrey A. Petrov ◽  
Vadim V. Korolev ◽  
Artem Mitrofanov ◽  
...  
Keyword(s):  
Machine Learning ◽  
Open Access ◽  
Crystal Structures ◽  
Band Gaps ◽  
Two Dimensional ◽  
Perovskite Materials ◽  
Hybrid Perovskite ◽  
Partial Charges
Sign in / Sign up

Export Citation Format

Share Document