We present an update of the DScribe package, a Python library for atomistic descriptors. The update extends DScribe's descriptor selection with the Valle-Oganov materials fingerprint and provides descriptor derivatives to enable more advanced machine learning tasks, such as force prediction and structure optimization. For all descriptors, numeric derivatives are now available in DScribe. For the many-body tensor representation (MBTR) and the Smooth Overlap of Atomic Positions (SOAP), we have also implemented analytic derivatives. We demonstrate the effectiveness of the descriptor derivatives for machine learning models of Cu clusters and perovskite alloys.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1063/5.0151031 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Deep sequencing-derived Metagenome Assembled Genomes from the gut microbiome of liver transplant patients.
Sci Data
January 2025
Department of Food Science and Human Nutrition, University of Illinois at Urbana-Champaign, Urbana, IL, 61801, USA.
Recurrence of metabolic dysfunction-associated steatotic liver disease (MASLD) after liver transplantation (LT) is a continuing concern. The role of gut microbiome dysbiosis in MASLD initiation and progression has been well established. However, there is a lack of comprehensive gut microbiome shotgun sequence data for patients experiencing MASLD recurrence after LT.
View Article and Find Full Text PDFQuotient Complex (QC)-Based Machine Learning for 2D Hybrid Perovskite Design.
J Chem Inf Model
January 2025
Division of Physics & Applied Physics, School of Physical and Mathematical Sciences, Nanyang Technological University, 21 Nanyang Link, Singapore 637371, Singapore.
With remarkable stability and exceptional optoelectronic properties, two-dimensional (2D) halide layered perovskites hold immense promise for revolutionizing photovoltaic technology. Effective data representations are key to the success of all learning models. Currently, the lack of comprehensive and accurate material representations has hindered AI-based design and discovery of 2D perovskites, limiting their potential for advanced photovoltaic applications.
View Article and Find Full Text PDFA Comparison of the Electronic Properties of Selected Antioxidants Vitamin C, Uric Acid, NAC and Melatonin with Guanosine Derivatives: A Theoretical Study.
Molecules
December 2024
DNA Damage Laboratory of the Food Science Department, Faculty of Pharmacy, Medical University of Lodz, ul. Muszynskiego 1, 90-151 Lodz, Poland.
Each cell in the human body is continually exposed to harmful external and internal factors. During evolution, cells have developed various defence systems, divided into enzymatic and non-enzymatic types, to which low-weight molecule antioxidants belong. In this article, the ionisation potential and electron affinity, as well as global reactivity descriptors of Vitamin C, Melatonin, Uric Acids, and N-acetyl-L-cysteine, were theoretically investigated at the MP-2/aug-cc-pVTZ level of theory in the condensed (aqueous) phase.
View Article and Find Full Text PDFCurvilinear regression analysis and ranking of migraine treatment drugs using degree-based topological indices and the WASPAS method.
Comput Biol Med
January 2025
Department of Mathematics, COMSATS University Islamabad, Vehari Campus, 61100, Vehari, Pakistan. Electronic address:
Topological indices, derived from molecular graphs, provide valuable numerical descriptors for the comprehensive analysis of pharmaceuticals. These indices are pivotal in the physicochemical characterization and predictive assessment of various drugs. In this study, we calculate several degree-based topological indices for a range of migraine treatment medications, including aspirin, caffeine, eletriptan, ergotamine, sumatriptan, rizatriptan, verapamil, diclofenac, frovatriptan, and droperidol.
View Article and Find Full Text PDFThermally Activated Delayed Fluorescence in B,N-Substituted Tetracene Derivatives: A Theoretical Pathway to Enhanced OLED Materials.
J Phys Chem A
January 2025
Departamento de Química, Instituto Tecnológico de Aeronáutica, São José dos Campos, 12228-900 São Paulo, Brazil.
Polycyclic aromatic hydrocarbons (PAHs) exhibit intriguing characteristics that position them as promising candidates for advancements in organic semiconductor technologies. Notably, tetracene finds substantial utility in Electronics due to its application in organic light-emitting diodes (OLEDs) and organic field-effect transistors (OFETs). The strategic introduction of an isoelectronic boron-nitrogen (B,N) pair to replace a carbon-carbon pair in acenes introduces changes in the electronic structure, allowing for the controlled modulation of diradical characteristics.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!