arXiv subjects

Qi Ou

Publications and source records attributed to Qi Ou.

11 recordsLinked to original sources

arXiv2026

3D Molecular Representation Learning for Organic Mixtures: Viscosity and Density Prediction

The viscosity and density of organic mixtures are essential properties for designing lubricants, solvents, and heat transfer fluids. In engineering practice, formulating a functional fluid requires understanding how these properties change with composition and temperature. However, exhaustive experimental characterization across the full parameter space is impractical due to the vast number of possible species and combinations. Here we introduce a mixture-aware 3D molecular representation learning strategy, built upon a pre-trained molecular encoder, that jointly encodes component structures, mole fractions, and temperature to achieve accurate predictions for organic mixtures. Fine-tuning on publicly available datasets covering a wide range of binary organic mixtures yields test-set R2 values of 0.973 for dynamic viscosity and 0.996 for density, significantly outperforming traditional machine learning baselines. Beyond this overall accuracy, the model captures non-monotonic viscosity changes upon mixing, surpassing simple linear or logarithmic mixing rules. The architecture is extendable to ternary and multicomponent mixtures, as verified via preliminary experiments. Using this model, we quantitatively analyze how molecular structure-branching, cycloalkane, and aromatic rings-affects viscosity-temperature behavior, which benefits the design of lubricants with superior viscosity-temperature performance. Altogether, this work provides a practical, data-driven tool for mixture property prediction, accelerating the rational formulation of functional fluids in chemical engineering.

physics.chem-ph↗

arXiv2025

A Conformation-Centric Generative Foundation Model for Linear Polymer Modeling and Design

Linear polymers, macromolecules formed from monomers covalently bonded into continuous chains, underpin countless technologies and are indispensable to modern life. While deep learning is advancing polymer science, existing methods typically represent the whole linear polymer solely through monomer-level descriptors, overlooking the global structural information inherent in polymer conformations, which ultimately limits their practical performance. Moreover, this important field still lacks a dedicated foundation model that can effectively support diverse downstream tasks, thereby severely constraining progress. To address these challenges, we introduce PolyConFM, a foundation model tailored for modeling and designing linear polymers through conformation-centric generative pretraining. Recognizing that each linear polymer is essentially a continuous chain whose conformation can be naturally decomposed into a sequence of local conformations (i.e., those of its repeating units), we pretrain PolyConFM under the conditional generation paradigm, reconstructing these local conformations via masked autoregressive (MAR) modeling and further generating their orientation transformations to recover the corresponding polymer conformation. Meanwhile, we construct a linear polymer conformation dataset via molecular dynamics simulations to mitigate data sparsity, thereby enabling conformation-centric pretraining. Experiments demonstrate that PolyConFM consistently outperforms representative task-specific methods across diverse downstream tasks, thereby equipping polymer science with a powerful tool targeting linear polymers.

cs.LG↗

arXiv2025

PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models

Polymer conformation generation is a critical task that enables atomic-level studies of diverse polymer materials. While significant advances have been made in designing conformation generation methods for small molecules and proteins, these methods struggle to generate polymer conformations due to their unique structural characteristics. Meanwhile, the scarcity of polymer conformation datasets further limits the progress, making this important area largely unexplored. In this work, we propose PolyConf, a pioneering tailored polymer conformation generation method that leverages hierarchical generative models to unlock new possibilities. Specifically, we decompose the polymer conformation into a series of local conformations (i.e., the conformations of its repeating units), generating these local conformations through an autoregressive model, and then generating their orientation transformations via a diffusion model to assemble them into the complete polymer conformation. Moreover, we develop the first benchmark with a high-quality polymer conformation dataset derived from molecular dynamics simulations to boost related research in this area. The comprehensive evaluation demonstrates that PolyConf consistently outperforms existing conformation generation methods, thus facilitating advancements in polymer modeling and simulation.

cond-mat.soft↗

arXiv2025

Stochastic resolution of identity to CC2 for large systems: Oscillator strength and ground state gradient calculations

An implementation of stochastic resolution of identity (sRI) approximation to CC2 oscillator strengths as well as ground state analytical gradients is presented. The essential 4-index electron repulsion integrals (ERIs) are contracted with a set of stochastic orbitals on the basis of the RI technique and the orbital energy differences in the denominators are decoupled with the Laplace transform. These lead to a significant scaling reduction from O(N^5) to O(N^3) for oscillator strengths and gradients with the size of the basis set, N. The gradients need a large number of stochastic orbitals with O(N^3), so we provide an additional O(N^4) version with better accuracy and smaller prefactor by adopting sRI partially. Such steep computational acceleration of nearly two or one order of magnitude is very attractive for large systems. This work is an extension to our previous implementations of sRI-CC2 ground and excited state energies and shows the feasibility of introducing sRI to CC2 properties beyond energies.

physics.chem-ph↗

arXiv2025

High-Accuracy Physical Property Prediction for Organics via Molecular Representation Learning: Bridging Data to Discovery

The ongoing energy crisis has underscored the urgent need for energy-efficient materials with high energy utilization efficiency, prompting a surge in research into organic compounds due to their environmental compatibility, cost-effective processing, and versatile modifiability. To address the high experimental costs and time-consuming nature of traditional trial-and-error methods in the discovery of highly functional organic compounds, we apply the 3D transformer-based molecular representation learning algorithm to construct a pre-trained model using 60 million semi-empirically optimized structures of small organic molecules, namely, Org-Mol, which is then fine-tuned with public experimental data to obtain prediction models for various physical properties. Despite the pre-training process relying solely on single molecular coordinates, the fine-tuned models achieves high accuracy (with $R^2$ values for the test set exceeding 0.95). These fine-tuned models are applied in a high-throughput screening process to identify novel immersion coolants among millions of automatically constructed ester molecules, resulting in the experimental validation of two promising candidates. This work not only demonstrates the potential of Org-Mol in predicting bulk properties for organic compounds but also paves the way for the rational and efficient development of ideal candidates for energy-saving materials.

physics.chem-ph↗

arXiv2025

ABACUS: An Electronic Structure Analysis Package for the AI Era

ABACUS (Atomic-orbital Based Ab-initio Computation at USTC) is an open-source software for first-principles electronic structure calculations and molecular dynamics simulations. It mainly features density functional theory (DFT) and molecular dynamics functions and is compatible with both plane-wave basis sets and numerical atomic orbital basis sets. ABACUS serves as a platform that facilitates the integration of various electronic structure methods, such as Kohn-Sham DFT, stochastic DFT, orbital-free DFT, and real-time time-dependent DFT, etc. In addition, with the aid of high-performance computing, ABACUS is designed to perform efficiently and provide massive amounts of first-principles data for generating general-purpose machine learning potentials, such as DPA models. Furthermore, ABACUS serves as an electronic structure platform that interfaces with several AI-assisted algorithms and packages, such as DeePKS-kit, DeePMD, DP-GEN, DeepH, DeePTB, HamGNN, etc.

cond-mat.mtrl-sci↗

arXiv2023

Stochastic resolution of identity to CC2 for large systems: excited state properties

We apply a stochastic resolution of identity approximation (sRI) to the CC2 method for excitation energy calculations. A set of stochastic orbitals are employed to decouple the crucial 4-index electron repulsion integrals and optimize the contraction steps in CC2 response theory. The CC2 response for excitations builds upon sRI-CC2 ground-state calculations, which scales as O(N^3), where N is a measure for the system size. Overall, the current algorithm for excited states also allows a sharp scaling reduction from original O(N^5) to O(N^3). We test the sRI-CC2 for different molecular systems and basis sets, and we show our sRI-CC2 method can accurately reproduce the results of deterministic CC2 approach. Our sRI-CC2 exhibits an experimental scaling of O(N^2.88) for a hydrogen dimer chain, allowing us to calculate systems with nearly thousands of electrons.

physics.chem-ph↗

arXiv2023

DeePKS Model for Halide Perovskites with the Accuracy of Hybrid Functional

Accurate prediction for the electronic structure properties of halide perovskites plays a significant role in the design of highly efficient and stable solar cells. While density functional theory (DFT) within the generalized gradient approximation (GGA) offers reliable prediction in terms of lattice constants and potential energy surface for halide perovskites, it severely underestimates the band gap due to the lack of non-local exact exchange term, which exists in computationally expensive hybrid functionals. In this work, a universal Deep Kohn-Sham (DeePKS) model based on neural network is trained so as to enable electronic structure calculations with the accuracy of hybrid functional HSE06 and the efficiency comparable to GGA functional, for a plethora of halide perovskites, i.e., ABX$_3$ (A=FA, MA, Cs; B=Sn, Pb; X=Cl, Br, I). Forces, band gaps, and density of states (DOS) predicted by our DeePKS model for all aforementioned perovskites are in good agreement with the HSE06 results, with significantly improved efficiency. In addition, even though the spin-orbit coupling (SOC) effect has not been taken into consideration during the training process, DeePKS+SOC offers highly consistent band gap and DOS as compared to HSE06+SOC for Pb-containing systems. We believe such DeePKS model can be readily applied for an accurate yet efficient prediction of various properties for the family of halide perovskites.

physics.chem-ph↗

arXiv2022

DeePKS+ABACUS as a Bridge between Expensive Quantum Mechanical Models and Machine Learning Potentials

Recently, the development of machine learning (ML) potentials has made it possible to perform large-scale and long-time molecular simulations with the accuracy of quantum mechanical (QM) models. However, for high-level QM methods, such as density functional theory (DFT) at the meta-GGA level and/or with exact exchange, quantum Monte Carlo, etc., generating a sufficient amount of data for training a ML potential has remained computationally challenging due to their high cost. In this work, we demonstrate that this issue can be largely alleviated with Deep Kohn-Sham (DeePKS), a ML-based DFT model. DeePKS employs a computationally efficient neural network-based functional model to construct a correction term added upon a cheap DFT model. Upon training, DeePKS offers closely-matched energies and forces compared with high-level QM method, but the number of training data required is orders of magnitude less than that required for training a reliable ML potential. As such, DeePKS can serve as a bridge between expensive QM models and ML potentials: one can generate a decent amount of high-accuracy QM data to train a DeePKS model, and then use the DeePKS model to label a much larger amount of configurations to train a ML potential. This scheme for periodic systems is implemented in a DFT package ABACUS, which is open-source and ready for use in various applications.

physics.chem-ph↗

arXiv2022

INAQS, a generic interface for non-adiabatic QM/MM dynamics: Design, implementation, and validation for GROMACS/Q-CHEM simulations

The accurate description of large molecular systems in complex environments remains an ongoing challenge for the field of computational chemistry. This problem is even more pronounced for photo-induced processes, as multiple excited electronic states and their corresponding non-adiabatic couplings must be taken into account. Multiscale approaches such as hybrid quantum mechanics/molecular mechanics (QM/MM) offer a balanced compromise between accuracy and computational burden. Here, we introduce an open-source software package (INAQS) for non-adiabatic QM/MM simulations that bridges the sampling capabilities of the GROMACS MD package and the excited-state infrastructure of the Q-CHEM electronic structure software. The interface is simple and can be adapted easily to other MD codes. The code supports a variety of different trajectory based molecular dynamics, ranging from Born-Oppenheimer to surface hopping dynamics. To illustrate the power of this combination, we simulate electronic absorption spectra, free energy surfaces along a reaction coordinate, and the excited state dynamics of 1,3-cyclohexadiene in solution.

physics.chem-ph↗

arXiv2021

Quantum-Electrodynamical Time-Dependent Density Functional Theory. I. A Gaussian Atomic Basis Implementation

Inspired by the formulation of quantum-electrodynamical time-dependent density functional theory (QED-TDDFT) by Rubio and coworkers, we propose an implementation that uses dimensionless amplitudes for describing the photonic contributions to QED-TDDFT electron-photon eigenstates. The leads to a symmetric QED-TDDFT coupling matrix, which is expected to facilitate the future development of analytic derivatives. Through a Gaussian atomic basis implementation of the QED-TDDFT method, we examined the effect of dipole self-energy, rotating wave approximation, and the Tamm-Dancoff approximation on the QED-TDDFT eigenstates of model compounds (ethene, formaldehyde, and benzaldehyde) in an optical cavity. We highlight, in the strong coupling regime, the role of higher-energy and off-resonance excited states with large transition dipole moments in the direction of the photonic field, which are automatically accounted for in our QED-TDDFT calculations and might substantially affect the energy and composition of polaritons associated with lower-energy electronic states.

cond-mat.mtrl-sci↗