MLatom 3: 10-Year Anniversary Edition is on the way

Published Time:  2023-09-08 12:10:40

MLatom is a package for AI-enhanced computational chemistry, see MLatom.com for details.

We are happy to announce that on the occasion of its ten-year anniversary, we will release a brand new MLatom 3 with tons of new features including more simulation options, Python API for user-customized workflows, and its integration into XACS cloud computing with the online terminal. We will also hold two online broadcasts demonstrating new features: one in English on September 13, at 15:30 Beijing time/9:30 am CET and another in Chinese on September 14, at 10:00 Beijing time; both for ca. 15 min. In these broadcasts, you will be able to ask questions in real time and give suggestions. You can access the English broadcast on the XACS YouTube channel at https://youtube.com/live/eScQokNaDTw?feature=share and Chinese on the XACS WeChat channel at:


Old features stay the same

You will be able to still use MLatom for the same calculations as before - nothing changed for the users of the old features, although inside the hoods, we completely rewritten most of MLatom. For example, this input file for geometry optimization will work as before:


Tons of new simulation features

MLatom 3 comes with tons of new useful features such as:

  • molecular dynamics
  • IR spectra simulations from molecular dynamics
  • support of more quantum chemical methods ranging from DFT and ab initio via interfaces to PySCF, Gaussian, and Orca to semi-empirical via interfaces to mndo, Sparrow, and xtb.
  • ML-quantum dynamics via an interface to the MLQD package

It means that now, you will have a huge library of methods to choose from and, e.g., running MD will be possible via input file as


Python API

If you feel more comfortable working with Python and Jupyter, you will be able to use MLatom’s Python API to create your custom workflows by simply importing mlatom and exploiting its flexibility and a wide range of capabilities. For example, if you want to optimize hyperparameters of your model, your Python script might look like this:


Integration with new XACS cloud computing

In parallel with preparing the release of MLatom 3, we are also preparing the release of new XACS cloud computing, which will allow you to run MLatom 3 online, e.g., through online XACS terminal: