MLatom 3 is a program package designed to leverage the power of ML to enhance typical computational chemistry simulations and to create complex workflows.

This open-source package provides plenty of choice to the users who can run simulations with the command-line options, input files, or with scripts using MLatom as a Python package, both on their computers and on the online XACS cloud computing service at XACScloud.com.

Computational chemists can calculate energies and thermochemical properties, optimize geometries, run molecular and quantum dynamics, and simulate (ro)vibrational, one-photon UV/vis absorption, and two-photon absorption spectra with ML, quantum mechanical, and combined models. The users can choose from an extensive library of methods containing pretrained ML models and quantum mechanical approximations such as AIQM1 approaching coupled-cluster accuracy. The developers can build their own models using various ML algorithms. The great flexibility of MLatom is largely due to the extensive use of the interfaces to many state-of-the-art software packages and libraries.

A brief overview of the capabilities of MLatom 3 is given in the video:

Text and figures of this overview are adapted from the paper on MLatom 3 in J. Chem. Theory Comput. 2024, DOI: 10.1021/acs.jctc.3c01203 (published under the CC-BY 4.0 license; see the original paper for more references and theory). More information about MLatom and its developers is on MLatom.com.

You can see an overview of MLatom 3 for more information.