AI-enhanced computational chemistry
AI-accelerated nonadiabatic dynamics reduces the cost of the ab initio simulations of nonlinear time-resolved spectra. We have developed a robust protocol and demonstrated its feasibility for calculating stimulated emission contributions in transient absorption pump–probe and 2D electronic spectra of pyrazine. …
Check out our tutorial on how to run TS geometry optimizations and also analysis (freq and IRC) with MLatom@XACS.We demonstrate on an example of the Diels–Alder reaction how to use fast GFN2-xTB and AIQM1 methods providing reasonable TS geometries and …
Transition state search and analysis with MLatom@XACS Read more »
Single-point calculations can be performed with various models and methods in MLatom including: For more details on the models in MLatom, please check an overview. Here we will illustrate how to calculate isomerization energy of sugar in ISOL24 with different types of methods …
Tutorial on single-point calculations with MLatom@XACS Read more »
Pavlo O. Dral, Fuchun Ge, Yi-Fan Hou, Peikun Zheng, Yuxinxin Chen, Mario Barbatti, Olexandr Isayev, Cheng Wang, Bao-Xin Xue, Max Pinheiro Jr, Yuming Su, Yiheng Dai, Yangtao Chen, Lina Zhang, Shuang Zhang, Arif Ullah, Quanhao Zhang, Yanchi Ou. MLatom 3: A …
MLatom 3 for AI-enhanced computational chemistry: JCTC paper and online tutorial Read more »
We have released the version 3.1.1 of MLatom with improvements in the performance and bug fixes.
In this tutorial we show how to optimize molecular geometries with MLatom. Here, only the optimization of the minima is shown and the optimization of the transition states will be shown elsewhere (for now, please check out the manual). For the …
Tutorial on geometry optimizations with MLatom@XACS Read more »
Equivariant potentials are the (relatively) new kid on the block with promising high accuracy in published benchmarks. One of them is MACE which we now added to the zoo of machine learning potentials available through the interfaces in MLatom. See …
We have released the version 3.1.0 of MLatom with new interface to MACE, one of state-of-the-art machine learning potentials that feature equivariant message passing neural networks.
We have released the version 3.0.1 of MLatom with minor upgrades that improve the stability and user experience. In this update, we fixed some bugs in the previous version. Also, we included the docstrings in the code, which might be …
Location: Xiamen University, China Duration: 2 years (with possible 1-year extension) Xiamen University is offering a fully-funded 2-year postdoctoral research position in the field of machine learning-based simulations of condensed matter. This opportunity is available within the research group of Prof. Pavlo …