Interpretable AI in materials discovery: Uncovering how models make predictions

A method to interpret artificial intelligence (AI) models used in materials discovery by analyzing their learned features has ...
Nature

Resolving chemical-motif similarity with enhanced atomic structure representations for accurately predicting descriptors at metallic interfaces

Accurately predicting catalytic descriptors with machine learning (ML) methods is significant to achieving accelerated catalyst design, where a unique representation of the atomic structure of each ...
BBC

Models of the atom - AQA

In ancient Greece, most people thought that matter was made up of combinations of four elements: earth, air, fire and water. There were a small number of Greeks who had a different idea. They believed ...
Nature

Accurate structure prediction of biomolecular interactions with AlphaFold 3

AF3 can predict structures from input polymer sequences, residue modifications and ligand SMILES (simplified molecular-input line-entry system). In Fig. 3 we show a selection of examples highlighting ...