Extended Data Fig. 6: Analysis and examples for modified proteins and nucleic acids.
From: Accurate structure prediction of biomolecular interactions with AlphaFold 3
a, Accuracy on structures. containing common phosphorylation residues (SEP, TPO, PTR, NEP, HIP) from the recent PDB evaluation set. Comparison between AlphaFold 3 with phosphorylation modelled, and AlphaFold 3 without modelling phosphorylation (N = 76 clusters, paired two-sided Wilcoxon signed-rank test, p = 1.6 * 10−4). Note, to predict a structure without modelling phosphorylation, we predict the parent (standard) residue in place of the modification. AlphaFold 3 generally achieves better backbone accuracy when modelling phosphorylation. Error bars indicate exact binomial distribution 95% confidence intervals. b, SPOC domain of human SHARP in complex with phosphorylated RNA polymerase II C-terminal domain (PDB ID 7Z1K), predictions coloured by pLDDT (orange: 0–50, yellow: 50–70, cyan 70–90, and blue 90–100). Left: Phosphorylation modelled (mean pocket-aligned RMSDCα 2.104 Å). Right: Without modelling phosphorylation (mean pocketaligned RMSDCα 10.261 Å). When excluding phosphorylation, AlphaFold 3 provides lower pLDDT confidence on the phosphopeptide. c, Structure of parkin bound to two phospho-ubiquitin molecules (PDB ID 7US1), predictions similarly coloured by pLDDT. Left: Phosphorylation modelled (mean pocket-aligned RMSDCα 0.424 Å). Right: Without modelling phosphorylation (mean pocket-aligned RMSDCα 9.706 Å). When excluding phosphorylation, AlphaFold 3 provides lower pLDDT confidence on the interface residues of the incorrectly predicted ubiquitin. d, Example structures with modified nucleic acids. Left: Guanosine monophosphate in RNA (PDB ID 7TNZ, mean pocket-aligned modified residue RMSD 0.840 Å). Right: Methylated DNA cytosines (PDB ID 7SDW, mean pocket-aligned modified residue RMSD 0.502 Å). Welabel residues of the predicted structure for reference. Ground truth structure in grey; predicted protein in blue, predicted RNA in purple, predicted DNA in magenta, predicted ions in orange, with predicted modifications highlighted via spheres.
