… Next we show how the MPNNs can be trained on multiple conformers or on a single 'effective
conformer' that represents the ensemble. The former uses the deep learning concept of …

… In this work, we introduce Conformator as a new conformer ensemble generator that is free
… Conformator is a knowledge-based conformer ensemble generator that builds on concepts …

… of a molecule’s 3D conformer ensemble from the molecular … lack of modeling important
molecular geometry elements (eg, … metrics to compare two conformer ensembles, generated by …

… the first MoleculAR Conformer Ensemble Learning (… molecules, for which conformer ensemble
learning may be relevant to capture their properties. Hence, we only retain molecules with …

… completeness of conformer ensembles from three different algorithms for conformer generation
in comparison with ensembles derived from extensive molecular dynamics simulations …

… In this study, we have demonstrated how to learn ensemble properties from molecular
simulations and provide easily interpretable metrics of important features with prominent ML …

… While RMSD gives a geometric way to evaluate ensemble quality, we also consider the
chemical similarity between generated and ground truth ensembles. For a random 100-molecule …

… challenge of predicting the 3D conformation of a protein given its amino acid sequence 9 . …
trained on molecular mechanics simulation data. We apply it here to model the ensembles of …

… For almost all molecules, multiple geometrically distinct conformers exist. Understanding
and predicting thermodynamically accessible ensembles of molecular conformers is a key task …

… Then, we calculate ensemble properties including average energy E, lowest energy Emin,
average HOMO-LUMO gap ∆ϵ, minimum gap ∆ϵmin, and maximum gap ∆ϵmax based on …