Easy-to-use universal AI models for modern computational chemistry

MLatom supports a wide range of universal machine learning (ML)-based models including ML potentials and hybrid ML-enhanced quantum mechanical (QM) methods. They can be used out-of-box without training.

In short, we have there several new universal (no training needed) ML models: DM21 (from Science paper by DeepMind), ANI-1xnr (good for reactions, from Nature Chemistry paper) and AIMnet2 (have support of more elements and charged species).

You can check out the video below for a short introduction. Also, see the online tutorial for more information.