Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling. Building on iBonD, the largest experimental pKa database established, we and other researchers have developed several methods including machine-learning-based empirical prediction and high-accuracy energy calculations. Despite this foundation, the rapid augmentation of high-quality pKa data remains fundamentally constrained. As part of this work, we performed large-scale regression-based pKa prediction on unlabeled molecular datasets using a collection of extensively optimized machine-learning models. The results indicate that, since the feature distributions of unlabeled molecular datasets, the pKa data distribution approximates normality, with extreme scarcity of tail-region samples. Although such augmentation is highly valuable for improving overall data availability and predictive modeling, it remains insufficient for efficiently discovering molecules with broad-spectrum pKa properties. To address this, we explore the targeted generation of molecules with sparse pKa properties from the vast chemical space. Given that traditional continuous latent space VAE-RNN methods for molecular generation suffer from insufficient stability and fail to demonstrate clear advantages in complementing sparse data, we design and implement a quantum-assisted sparse-pKa molecular generation. Feasibility is validated on a simulated quantum annealer, and superior extreme-value sampling is further achieved on physical coherent Ising machines (CIMs). (to be continued)
Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling. Building on iBonD, the largest experimental pKa database established, we and other researchers have developed several methods including machine-learning-based empirical prediction and high-accuracy energy calculations. Despite this foundation, the rapid augmentation of high-quality pKa data remains fundamentally constrained. As part of this work, we performed large-scale regression-based pKa prediction on unlabeled molecular datasets using a collection of extensively optimized machine-learning models. The results indicate that, since the feature distributions of unlabeled molecular datasets, the pKa data distribution approximates normality, with extreme scarcity of tail-region samples. Although such augmentation is highly valuable for improving overall data availability and predictive modeling, it remains insufficient for efficiently discovering molecules with broad-spectrum pKa properties. To address this, we explore the targeted generation of molecules with sparse pKa properties from the vast chemical space. Given that traditional continuous latent space VAE-RNN methods for molecular generation suffer from insufficient stability and fail to demonstrate clear advantages in complementing sparse data, we design and implement a quantum-assisted sparse-pKa molecular generation. Feasibility is validated on a simulated quantum annealer, and superior extreme-value sampling is further achieved on physical coherent Ising machines (CIMs). (to be continued)
Abstract Computer-aided design of novel molecules and compounds is a challenging task that can be addressed with quantum computing (QC) owing to its notable advances in optimization and machine learning. Here, we use QC-assisted learning and optimization techniques implemented with near-term QC devices for molecular property prediction and generation tasks. The proposed probabilistic energy-based deep learning model trained in a generative manner facilitated by QC yields robust latent representations of molecules, while the proposed data-driven QC-based optimization framework performs guided navigation of the target chemical space by exploiting the structure–property relationships captured by the energy-based model. We demonstrate the viability of the proposed molecular design approach by generating several molecular candidates that satisfy specific property target requirements. The proposed QC-based methods exhibit an improved predictive performance while efficiently generating novel molecules that accurately fulfill target conditions and exemplify the potential of QC for automated molecular design, thus accentuating its utility.
Materials discovery is a computationally intensive process that requires exploring vast chemical spaces to identify promising candidates with desirable properties. In this work, we propose using quantum-enhanced machine learning algorithms following the extremal learning framework to predict novel heteroacene structures with low hole reorganization energy λ, a key property for organic semiconductors. We leverage chemical data generated in a previous large-scale virtual screening to construct three initial training datasets containing 54, 99 and 119 molecules encoded using N=7,16 and 22 bits, respectively. Furthermore, a sequential learning process is employed to augment the initial training data with compounds predicted by the algorithms through iterative retraining. Both algorithms are able to successfully extrapolate to heteroacene structures with lower λ than in the initial dataset, demonstrating good generalization capabilities even when the amount of initial data is limited. We observe an improvement in the quality of the predicted compounds as the number of encoding bits N increases, which offers an exciting prospect for applying the algorithms to richer chemical spaces that require larger values of N and hence, in perspective, larger quantum circuits to deploy the proposed quantum-enhanced protocols.
Neural scaling laws are driving the machine learning community toward training ever-larger foundation models across domains, assuring high accuracy and transferable representations for extrapolative tasks. We test this promise in quantum chemistry by scaling model capacity and training data from quantum chemical calculations. As a generalization task, we evaluate the resulting models' predictions of the bond dissociation energy of neutral H2, the simplest possible molecule. We find that, regardless of dataset size or model capacity, models trained only on stable structures fail dramatically to even qualitatively reproduce the H2 energy curve. Only when compressed and stretched geometries are explicitly included in training do the predictions roughly resemble the correct shape. Nonetheless, the largest foundation models trained on the largest and most diverse datasets containing dissociating diatomics exhibit serious failures on simple diatomic molecules. Most strikingly, they cannot reproduce the trivial repulsive energy curve of two bare protons, revealing their failure to learn the basic Coulomb's law involved in electronic structure theory. These results suggest that scaling alone is insufficient for building reliable quantum chemical models.
Predicting molecular properties is a cornerstone of drug discovery, materials science, and quantum chemistry, where accuracy and speed are critical. Classical machine learning mod- els offer rapid predictions but often fail to capture the intricate quantum interactions governing molecular behavior. Our team investigated quantum kernel methods to predict properties of the QM9 dataset, a widely recognized benchmark containing134,000organic molecules with diverse chemical structures. By encoding molecular features into quantum circuits, we mapped classical data into highdimensional Hilbert spaces to enhance prediction accuracy. Our pipeline encompasses data preprocessing, quantum circuit design, model training with support vector regression, and evaluation of ten key molecular properties. The quantum kernel approach delivered promising results, achieving mean absolute errors of 0.13 Debye for dipole moment and 0.08 eV for HOMOLUMO gap, even when executed on noisy quantum devices. This work provides a comprehensive, reproducible pipeline, benchmarks quantum and classical models, and discusses practical challenges, contributing significantly to the field of quantumenhanced computational chemistry.
The generation of chemical molecular structures is crucial for advancements in drug design, materials science, and related fields. With the rise of artificial intelligence, numerous generative models have been developed to propose promising molecular structures to specific challenges. However, exploring the vast chemical space using classical generative models demands extensive chemical structure data, considerable computational resources, and a large number of model parameters, which hinders their efficiency. Quantum computing presents a promising alternative by exploiting quantum parallelism and entanglement, potentially reducing the computational overhead required for such tasks. In this study, we designed a quantum-based molecular generator (QMG) specifically tailored to generate small molecules containing carbon, nitrogen, and oxygen atoms. This model imposes strict constraints on the quantum circuit's output quantum states, significantly eliminating mathematically invalid connection graphs and enabling more efficient sampling of valid molecular structures. Remarkably, our quantum circuit, utilizing only 134 parameters, is capable of enumerating all molecular structures comprising up to nine heavy atoms, showcasing the parameter efficiency achievable through quantum superposition and entanglement. Our experimental results show that the output generated by this circuit exhibits a high degree of validity and uniqueness after Bayesian optimization, showing comparable performance to classical deep generative models. Furthermore, by fixing specific parameters in the quantum circuits, the quantum generator can constrain the chemical space and exclusively generate chemical molecules containing specified functional groups. This feature underscores its potential value for targeted applications in specific domains, especially in drug discovery. Overall, this compact design not only reduces parameter demands but also enables efficient exploration of a nontrivial portion of chemical space, demonstrating a key advantage of quantum-based generative models over larger classical counterparts.
Machine learning has made significant contributions to the fields of chemistry and materials science, enabling the exploration of vast chemical space through large-scale quantum chemical calculations. These models provide fast and accurate predictions of atomistic chemical properties, but they have limitations when it comes to capturing the electronic degrees of freedom of a molecule. This restricts their application in reactive chemistry and chemical analysis. To address this limitation, we introduce a deep learning framework that predicts the quantum mechanical wavefunction of a molecule in a local basis of atomic orbitals. The wavefunction serves as a foundational representation from which all other ground-state properties can be derived. Our approach maintains complete access to the electronic structure through the wavefunction, while achieving computational efficiency comparable to force-field methods. Moreover, the framework captures quantum mechanics in a form that can be analytically differentiated, allowing for efficient optimization and exploration of chemical systems. We demonstrate the potential of our approach through several examples. By leveraging the predicted wavefunction, we showcase the ability to perform inverse design of molecular structures to target specific electronic property optimizations. This opens exciting avenues for tailoring molecular structures to achieve desired electronic characteristics. Additionally, our framework paves the way for enhanced synergy between machine learning and quantum chemistry, enabling more comprehensive investigations into complex chemical systems.