Protein structure prediction has reached the single-structure frontier

Abstract

Dramatic advances in protein structure prediction have sparked debate as to whether the problem of predicting structure from sequence is solved or not. Here, I argue that AlphaFold2 and its peers are currently limited by the fact that they predict only a single structure, instead of a structural distribution, and that this realization is crucial for the next generation of structure prediction algorithms.

Fig. 1. AlphaFold2’s model of M^pro is on the frontier of the set of experimentally determined structures.

a, The M^pro functional unit, a dimer (gray surface), is shown with the backbone traces of 64 ligand-free structures deposited in the PDB (blue) aligned to AlphaFold2’s model (magenta). b, R.m.s. deviation between all pairs of M^pro PDB entries (blue) and from AlphaFold2’s model to each PDB entry (yellow). Top: filtered for M^pro structures without specific ligands bound (“ligands” excludes crystallization reagents, buffers, salts). Bottom: all M^pro PDB entries. RMSDs are computed for all non-hydrogen protein atoms modeled in all structures. PDB IDs included are those with 100% sequence identity match to PDB ID 7AR6; a list is included in the Supplementary Information.

Fig. 2. AlphaFold2’s prediction of hemoglobin lies between the R and T states.

Shown are experimental structures of O₂- or CO-bound (R, orange) and ligand-free (T, blue) hemoglobin, superimposed with the AlphaFold2 prediction (magenta). Right inset: detail of the structural superimposition. Left inset: principal component analysis of the dihedral angles shows the atomic coordinates in a space of reduced dimensionality. Plotted are the first two principal components (PC1 and PC2), which explain 45% of the total variance (Supplementary Fig. 3). Note: included T-state structure 1HGC is partially O₂ bound, with the two α-subunits ligand bound and the β-subunits ligand free. Structures selected from those highlighted in ref. .

Fig. 3. AlphaFold2 uncertainty correlates with structural variability in ABL kinase.

Left: for 25 ABL kinase structures, the local distance difference test (LDDT) computed across the experimental ensemble plotted against the AlphaFold2 model’s certainty metric, predicted LDDT (Spearman correlation coefficient 0.47). Color of markers shows position in sequence. The dynamic N terminus and activation loop exhibit notably low confidence. Right: structural superimposition of the same experimental structures from the PDB, colored by AlphaFold2’s confidence (predicted LDDT; AlphaFold2 model not shown). In regions of high variability between structures, such as the activation loop, the pLDDT reports lower confidence. PDB IDs listed in the Supplementary Information.