Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kunugi, Hayato, Rahmani, Mohsen, Iyama, Yosuke, Hirono, Yutaro, Suma, Akira, Woolway, Matthew, Vargas-Calderón, Vladimir, Kim, William, Chern, Kevin, Amin, Mohammad, Tateno, Masaru
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.15451
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914556244131840
author Kunugi, Hayato
Rahmani, Mohsen
Iyama, Yosuke
Hirono, Yutaro
Suma, Akira
Woolway, Matthew
Vargas-Calderón, Vladimir
Kim, William
Chern, Kevin
Amin, Mohammad
Tateno, Masaru
author_facet Kunugi, Hayato
Rahmani, Mohsen
Iyama, Yosuke
Hirono, Yutaro
Suma, Akira
Woolway, Matthew
Vargas-Calderón, Vladimir
Kim, William
Chern, Kevin
Amin, Mohammad
Tateno, Masaru
contents Deep generative modeling to stochastically design small molecules is an emerging technology for accelerating drug discovery and development. However, one major issue in molecular generative models is their lower frequency of drug-like compounds. To resolve this problem, we developed a novel framework for optimization of deep generative models integrated with a D-Wave quantum annealing computer, where our Neural Hash Function (NHF) presented herein is used both as the regularization and binarization schemes simultaneously, of which the latter is for transformation between continuous and discrete signals of the classical and quantum neural networks, respectively, in the error evaluation (i.e., objective) function. The compounds generated via the quantum-annealing generative models exhibited higher quality in both validity and drug-likeness than those generated via the fully-classical models, and was further indicated to exceed even the training data in terms of drug-likeness features, without any restraints and conditions to deliberately induce such an optimization. These results indicated an advantage of quantum annealing to aim at a stochastic generator integrated with our novel neural network architectures, for the extended performance of feature space sampling and extraction of characteristic features in drug design.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15451
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer
Kunugi, Hayato
Rahmani, Mohsen
Iyama, Yosuke
Hirono, Yutaro
Suma, Akira
Woolway, Matthew
Vargas-Calderón, Vladimir
Kim, William
Chern, Kevin
Amin, Mohammad
Tateno, Masaru
Quantitative Methods
Artificial Intelligence
Machine Learning
Quantum Physics
Deep generative modeling to stochastically design small molecules is an emerging technology for accelerating drug discovery and development. However, one major issue in molecular generative models is their lower frequency of drug-like compounds. To resolve this problem, we developed a novel framework for optimization of deep generative models integrated with a D-Wave quantum annealing computer, where our Neural Hash Function (NHF) presented herein is used both as the regularization and binarization schemes simultaneously, of which the latter is for transformation between continuous and discrete signals of the classical and quantum neural networks, respectively, in the error evaluation (i.e., objective) function. The compounds generated via the quantum-annealing generative models exhibited higher quality in both validity and drug-likeness than those generated via the fully-classical models, and was further indicated to exceed even the training data in terms of drug-likeness features, without any restraints and conditions to deliberately induce such an optimization. These results indicated an advantage of quantum annealing to aim at a stochastic generator integrated with our novel neural network architectures, for the extended performance of feature space sampling and extraction of characteristic features in drug design.
title Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer
topic Quantitative Methods
Artificial Intelligence
Machine Learning
Quantum Physics
url https://arxiv.org/abs/2602.15451