AI-enhanced computational chemistry
Have an idea for a new model and are looking for the right tool? Try MLatom. Because MLatom is easy to use to create new models, it has an impressive collection of rapidly growing number of models. And your model can …
Lego-bricks and infrastructure for your own computational chemistry model Read more »
Two-photon absorption is a fascinating property: some molecules can simultaneously absorb two photons and then emit a photon of higher energy than absorbed ones. This has found numerous uses: As a result, it is very important to find materials with stronger …
Our active learning protocol for accelerating surface hopping dynamics with machine learning is now available in MLatom 3.10! It is efficient and robust: often, you can do surface-hopping dynamics from start to finish within a couple of days on a …
Data is cornerstone of MLatom as it is a data-driven package. To truly unlock the potential of MLatom, you need to master handling of data with its Python API. In our online tutorial, we give a primer into MLatom’s data …
Not sure which DFT functional to choose for your calculations? Choose them all! (Or at least as many as you can)…To be precise, use the ensembles of the DFT functionals as we recently suggested. These ensembles combine predictions from multiple …
Not sure which DFT functional to choose? Choose them all! Read more »
We have been asked countless times when MLatom can support the periodic boundary conditions (PBC). Finally, we have released the new version of MLatom supporting the calculations with periodic boundary conditions! To get it, you can either use MLatom on …
Molecular Raman spectra can now be calculated online with MLatom on the XACS cloud computing platform* using a simple input file: *As of 24 July 2024, only for GFN2-xTB and UAIQM with GFN2-xTB baseline. You can find the frequencies and …
Molecules are always in motion.This motion can be simulated with molecular dynamics approach but it needs many steps to evaluate and is very slow. Just to demonstrate the pain of propagating MD let’s do it by hand for a couple …
Chemistry students learn early that a reaction proceeds from reactants to products via a transition state connecting them. This simple picture does not always hold though. The reactions never pass exactly through the transition state and we must propagate molecular dynamics trajectories …
If you want to use machine learning for potential energy surfaces, one of the biggest obstacles is getting the data to train machine learning potential. We have recently developed the physics-informed active learning protocol for efficient data sampling and training …
Active learning for building data-efficient machine learning potentials Read more »