You can now use MLatom to perform TDDFT and TDA calculations with MLatom and parse Gaussian output files.This can be useful for UV/vis spectra simulations via single-point convolution and nuclear-ensemble approach (NEA).We also welcome a new contributor to MLatom: Vignesh Kumar …

TDDFT and TDA calculations + parsing of Gaussian output files Read more »

The explosion of quantum chemical datasets (see our overview of them) satisfies the appetite of those data-hungry machine learning potentials while raising another critical question: how to learn data in different fidelities? Here, we propose the all-in-one (AIO) ANI model, …

All-in-one: Learning across quantum chemical levels. Better than transfer learning! Read more »

Recently, we published a paper in JOC about the surprising dynamics phenomena in the Diels–Alder reaction of fullerene C60. The AI-accelerated molecular dynamics uncovers that in a small fraction (10%) of reactive trajectories, the diene molecule (2,3-dimethyl-1,3-butadiene) is roaming around …

JOC: Surprising dynamics phenomena in the Diels–Alder reaction of C60 uncovered with AI Read more »

AIQM2 is the long-awaited successor of the highly successful AIQM1 (see Nat. Commun. paper). It has overall improved accuracy and much better performance for transition states, where it produces high-quality geometries and barrier heights: it is better than B3LYP/6-31G* but orders of …

AIQM2 is out: better and faster than B3LYP for reaction simulations! Read more »

Recently, we published a paper in JCTC about the end-to-end physics-informed active learning with data-efficient construction of machine learning potentials. It shortens molecular simulation time to a couple of days which could have taken weeks of pure quantum chemical calculations. The active …

JCTC: Physics-informed active learning for accelerating quantum chemical simulations Read more »

We have held online broadcast on April 24, at 15:30 Beijing time/9:30 am CET on the XACS Youtube channel at https://www.youtube.com/watch?v=TOVmwgId-eA. In the broadcast, we have demonstrated how MLatom@XACS can be used for accelerating expensive quantum chemical simulations via efficient building …

View online broadcast: Active learning for building your data and machine learning potentials Read more »

A machine learning potential with low error in the potential energies does not guarantee good performance for the simulations. One of the reasons is that it is hard to train machine learning potentials with balanced descriptions of different PES regions, …

JPCL | Tell Machine Learning Potentials What They Are Needed For: Simulation-Oriented Training Read more »