Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computer

2026-02-17

AI Summary

This work addresses the challenge that existing molecular generation models struggle to efficiently produce highly drug-like compounds and are constrained by the distribution of training data. The authors propose a novel approach that, for the first time, integrates D-Wave quantum annealing with deep generative modeling through a neural hash function (NHF) endowed with both regularization and binarization capabilities. This NHF enables efficient conversion between continuous and discrete representations and is embedded directly into the objective function to guide optimization. Notably, the method transcends the limitations of training data without requiring explicit constraints, yielding molecules that significantly outperform those generated by fully classical models in both drug-likeness and validity, thereby advancing the quality of unconstrained molecular design.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Mixed Discrete/Continuous Search
• Natural Language Processing: Generation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• molecular generative models
• drug-likeness
• quantum annealing
• deep generative modeling
• small molecule design

Innovation

• Quantum Annealing
• Generative AI
• Neural Hash Function
• Drug-like Molecules
• Molecular Design