Impact of protein conformational diversity on AlphaFold predictions

Motivation: After the outstanding breakthrough of AlphaFold in predicting protein 3D models, new questions appeared and remain unanswered. The ensemble nature of proteins, for example, challenges the structural prediction methods because the models should represent a set of conformers instead of single structures. The evolutionary and structural features captured by effective deep learning techniques may unveil the information to generate several diverse conformations from a single sequence. Here, we address the performance of AlphaFold2 predictions obtained through ColabFold under this ensemble paradigm. Results: Using a curated collection of apo-holo pairs of conformers, we found that AlphaFold2 predicts the holo form of a protein in similar to 70% of the cases, being unable to reproduce the observed conformational diversity with the same error for both conformers. More importantly, we found that AlphaFold2's performance worsens with the increasing conformational diversity of the studied protein. This impairment is related to the heterogeneity in the degree of conformational diversity found between different members of the homologous family of the protein under study. Finally, we found that main-chain flexibility associated with apo-holo pairs of conformers negatively correlates with the predicted local model quality score pIDDT, indicating that pIDDT values in a single 3D model could be used to infer local conformational changes linked to ligand binding transitions.

Automated summary

By studying the performance of AlphaFold2 under the ensemble paradigm, it was found that AlphaFold2 performs well in predicting the holo form of proteins, but its performance deteriorates with increasing conformational diversity. There is a negative correlation between the main-chain flexibility associated with apo-holo pairs of conformers and the predicted local model quality score.