arXiv subjects

Anguang Hu

Publications and source records attributed to Anguang Hu.

3 recordsLinked to original sources

arXiv2024

Computationally Efficient Molecular Integrals of Solid Harmonic Gaussian Orbitals Using Quantum Entanglement of Angular Momentum

Evaluating multi-center molecular integrals with Cartesian Gaussian-type basis sets has been a long-standing bottleneck in electronic structure theory calculation for solids and molecules. We have developed a vector-coupling and vector-uncoupling scheme to solve molecular Coulomb integrals with solid harmonics basis functions(SHGO). Solid harmonics are eigenstates of angular momentum, making it possible to factorize molecular integrals. By combining solid harmonic addition, differential and product rules, the computationally costly multi-center four-center integrals can be factored into an angular part and a radial component dependent on the atomic positions. The potential speed-up ratio in evaluating molecular nuclear Coulomb integrals in our method can reach up to four orders of magnitude for atomic orbitals with high angular momentum quantum numbers. The foundation underpinning the mathematical efficiency is the quantum angular momentum theory, where both vector-coupling and vector-uncoupling schemes correspond to unitary Clebsch-Gordan transformations that act on quantum angular momentum states, influencing their degree of entanglement. By incorporating quantum angular momentum through these transformations, the entanglement of the states can be reduced, and the less entanglement there is for a quantum system, the easier it is to simulate. The highly efficient method unveiled here opens new avenues for accelerated material and molecule design and discovery.

quant-ph↗

arXiv2023

Machine learning for the prediction of safe and biologically active organophosphorus molecules

Drug discovery is a complex process with a large molecular space to be considered. By constraining the search space, the fragment-based drug design is an approach that can effectively sample the chemical space of interest. Here we propose a framework of Recurrent Neural Networks (RNN) with an attention model to sample the chemical space of organophosphorus molecules using the fragment-based approach. The framework is trained with a ZINC dataset that is screened for high druglikeness scores. The goal is to predict molecules with similar biological action modes as organophosphorus pesticides or chemical warfare agents yet less toxic to humans. The generated molecules contain a starting fragment of PO2F but have a bulky hydrocarbon side chain limiting its binding effectiveness to the targeted protein.

cs.LG↗

arXiv2023

CHA2: CHemistry Aware Convex Hull Autoencoder Towards Inverse Molecular Design

Optimizing molecular design and discovering novel chemical structures to meet certain objectives, such as quantitative estimates of the drug-likeness score (QEDs), is NP-hard due to the vast combinatorial design space of discrete molecular structures, which makes it near impossible to explore the entire search space comprehensively to exploit de novo structures with properties of interest. To address this challenge, reducing the intractable search space into a lower-dimensional latent volume helps examine molecular candidates more feasibly via inverse design. Autoencoders are suitable deep learning techniques, equipped with an encoder that reduces the discrete molecular structure into a latent space and a decoder that inverts the search space back to the molecular design. The continuous property of the latent space, which characterizes the discrete chemical structures, provides a flexible representation for inverse design in order to discover novel molecules. However, exploring this latent space requires certain insights to generate new structures. We propose using a convex hall surrounding the top molecules in terms of high QEDs to ensnare a tight subspace in the latent representation as an efficient way to reveal novel molecules with high QEDs. We demonstrate the effectiveness of our suggested method by using the QM9 as a training dataset along with the Self- Referencing Embedded Strings (SELFIES) representation to calibrate the autoencoder in order to carry out the Inverse molecular design that leads to unfold novel chemical structure.

cs.LG↗