Impact of protein conformational diversity on AlphaFold predictions

Abstract

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 under this ensemble paradigm. Using a curated collection of apo-holo conformations, we found that AlphaFold2 predicts the holo form of a protein in 70% of the cases, being unable to reproduce the observed conformational diversity with an equivalent error than in the estimation of a single conformation. 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 plDDT, indicating that plDDT values in a single 3D model could be used to infer local conformational changes linked to ligand binding transitions.

Sampling alternative conformational states of transporters and receptors with AlphaFold2

“…The correlation demonstrates that predicted flexibility by AF2 is related to the protein’s dynamics inferred from the experimental structures. In contrast with a recent preprint ( Saldaño et al, 2021 ), the predicted flexibility values failed to correlate with their pLDDT values, which reflect the confidence of the AF2 prediction of each residue’s local environment ( Mariani et al, 2013 ).…”

“…The correlation demonstrates that predicted flexibility by AF2 is related to the protein's dynamics inferred from the experimental structures. In contrast with a recent preprint 35 , the predicted flexibility values failed to correlate with their pLDDT values, which reflect the confidence of the AF2 prediction of each residue's local environment 36 . Distributions of predicted models relative to the experimental structures Visual examination suggested that many of the predicted models fall "in between" the two experimentally determined conformations (example shown in Figure 3A).…”

“…While these results reinforce the notion that AF2 can provide models to guide biophysical studies of conformationally heterogeneous membrane proteins, they represent a methodological ‘hack’, rather than an explicit objective built into the algorithm’s architecture. Several preprints have provided evidence that AF2, despite its accuracy, likely does not learn the energy landscapes underpinning protein folding and function ( Saldaño et al, 2021 ; Pak et al, 2021 ; Akdel et al, 2021 ). Moreover, AF2 does not directly account for the lipid environment, which has been experimentally shown to bias the conformational equilibria of membrane proteins ( Martens et al, 2018 ; Muller et al, 2019 ; Immadisetty et al, 2019 ).…”

Sampling the conformational landscapes of transporters and receptors with AlphaFold2

“…The correlation demonstrates that predicted flexibility by AF2 is related to the protein's dynamics inferred from the experimental structures. In contrast with a recent preprint 35 , the predicted flexibility values failed to correlate with their pLDDT values, which reflect the confidence of the AF2 prediction of each residue’s local environment 36 .…”

Modeling Alternate Conformations with Alphafold2 via Modification of the Multiple Sequence Alignment

“…A recent report examining a curated subset of apo and ligand bound structures suggested that pLDDT values infer local conformational changes. 31 The results presented here do not suggest that these regions of low confidence are incorrect in their two- or three-dimensional structure, but appear to be regions where there are contacts in the MSA that are not considered in the given structure (Fig. 2, Supp.…”