Dijous 11 de juny, el Dipòsit Digital no estarà operatiu de 15:00 a 17:00 h per tasques de manteniment. Disculpeu les molèsties.
El jueves 11 de Junio, el Dipòsit Digital no estará operativo de 15:00 a 17:00 h debido a tareas de mantenimiento. Disculpen las molestias.
Thursday, Jun 11th, the Digital Repository will be unavailable due to a system update.

Files

882531.pdf (3.13 MB)

Document type

Article

Version

Published version

Publication date

2024-01-17

Publication license

cc-by-nc (c) Santiago, Raul, 2024
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/228405

Unlocking the predictive power of quantum-inspired representations for intermolecular properties in machine learning

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

https://doi.org/10.1039/d3dd00187c

Abstract

The quest for accurate and efficient Machine Learning (ML) models to predict complex molecular properties has driven the development of new quantum-inspired representations (QIR). This study introduces MODA (Molecular Orbital Decomposition and Aggregation), a novel QIR-class descriptor with enhanced predictive capabilities. By incorporating wave-function information, MODA is able to capture electronic structure intricacies, providing deeper chemical insight and improving performance in unsupervised and supervised learning tasks. Specially designed to be separable, the multi-moiety regularization technique unlocks the predictive power of MODA for both intra- and intermolecular properties, making it the first QIR-class descriptor capable of such distinction. We demonstrate that MODA shows the best performance for intermolecular magnetic exchange coupling (JAB) predictions among the descriptors tested herein. By offering a versatile solution to address both intra- and intermolecular properties, MODA showcases the potential of quantum-inspired descriptors to improve the predictive capabilities of ML- based methods in computational chemistry and materials discovery.

Subject

QSPR (Relacions estructura-propietat quantitatives), Aprenentatge automàtic, Aprenentatge profund

Subject (English)

QSPR (Quantitative Structure-Property Relationships), Machine learning, Deep learning (Machine learning)

Citation

Collections

Articles publicats en revistes (Ciència dels Materials i Química Física)
Articles publicats en revistes (Institut de Química Teòrica i Computacional (IQTCUB))

Citation

SANTIAGO, Raul, et al. Unlocking the predictive power of quantum-inspired representations for intermolecular properties in machine learning. Digital Discovery. 2024. Vol. 3, num. 1, pags. 99-112. ISSN 2635-098X. [consulted: 11 of June of 2026]. Available at: https://hdl.handle.net/2445/228405

Export metadata

JSON - METS

Share record