29 August 2024 in Scientific Data
Due to rapid advancements in deep learning techniques, the demand for large-volume high-quality datasets grows significantly in chemical research. We developed a quantum-chemistry database that includes 443,106 small organic molecules with sizes up to 10 heavy atoms including C, N, O, and F. Ground-state geometry optimizations and frequency calculations of all compounds were performed at the B3LYP/6-31G* level with the BJD3 dispersion correction, while the excited-state single-point calculations were conducted at the ωB97X-D/6-31G* level. Totally twenty-seven molecular properties, such as geometric, thermodynamic, electronic and energetic properties, were gathered from these calculations. Meanwhile, we also established a comprehensive protocol for the construction of a high-volume quantum-chemistry dataset. Our QCDGE (Quantum Chemistry Dataset with Ground- and Excited-State Properties) dataset contains a substantial volume of data, exhibits high chemical diversity, and most importantly includes excited-state information. This dataset, along with its construction protocol, is expected to have a significant impact on the broad applications of machine learning studies across different fields of chemistry, especially in the area of excited-state research.
14 September 2022 in Physical Chemistry Chemical Physics
We proposed a “hierarchical” protocol based on the unsupervised machine learning algorithms (principal component analysis and clustering approaches) to automatically analyze the ring deformation in the nonadiabatic molecular dynamics.
27 May 2025 in The Journal of Chemical Physics
We have constructed an ab initio protocol for the simulation of transient-absorption (TA) pump–probe (PP) signals of realistic polyatomic systems. The protocol is based on interfacing the doorway-window representation of spectroscopic signals with the on-the-fly mapping Hamiltonian dynamics approach at the symmetrical quasi-classical/Meyer–Miller level. The methodology is applied to the simulation of TA PP signals of two molecular systems, azobenzene and cis-hepta-3,5,7-trieniminium cation. For both molecules, the TA PP spectra were demonstrated to give a direct fingerprint of the excited state wavepacket dynamics and internal conversion, which permits the monitoring of the isomerization pathways en route to the final photoproducts.
11 September 2026 in JACS Au
Analyzing nonadiabatic molecular dynamics trajectories traditionally heavily relies on expert intuition and visual pattern recognition, a process that is difficult to formalize. We present VisU, a vision-driven framework that leverages the complementary strengths of two state-of-the-art large language models (Doubao-Seed-1.6-Vision and DeepSeek-V3.2) to establish a “virtual research cooperation”. This operates through a “Mentor–Engineer–Student” paradigm that mimics the collaborative intelligence of a professional chemistry laboratory. Within this ecosystem, the Mentor provides physical intuition through visual reasoning, while the Engineer adaptively constructs analysis scripts, and the Student executes the pipeline and manages the data and results. VisU autonomously orchestrates a four-stage workflow comprising Preprocessing, Recursive Channel Discovery, Important-Motion Identification, and Validation/Summary. This systematic approach identifies reaction channels and key nuclear motions while generating a professional academic report at the end. By bridging visual insight with chemical expertise, VisU establishes a new framework for human–AI collaboration in the analysis of excited-state dynamics simulation results, significantly reducing dependence on manual interpretation and enabling more intuitive, scalable mechanistic discovery in nonadiabatic dynamics simulations.