Prediction of ligand-dependent conformational sampling of ABC transporters by AlphaFold3 and correlation to experimental structures and energetics
AlphaFold3 architecture represented an important leap relative to Alphafold2 by enabling the inclusion of protein ligands in the prediction network. Ligand-dependent structural rearrangements are inherently difficult to predict computationally as they imply transitions between states separated by large energy differences. Here we apply AlphaFold3 to predict nucleotide-dependent changes in the conformational cycle of representative ABC transporters that have been extensively investigated by experimental structural biology techniques. We show that under similar conditions, AlphaFold3 predictions sample experimentally observed conformations. Moreover, the heterogeneity of these predictions correlates with experimental measures of dynamics obtained from multiple techniques. For couple of the tested transporters, the implied relative energetics of the conformations mirror their experimental counterpart. Remarkably, AlphaFold3 predicts previously unobserved conformations that have been implied to be sampled by ABC transporters. Finally, we report preliminary results showing that postulated sequence determinants of conformational changes modify the predictions of AlphaFold3. Although hundreds of ABC transporter structures have been determined and were included in the training data of AF3, we propose that aspects of its predictions reflect extrapolation of principles learned from these structures.