Predicted local distance difference test (pLDDT)

The predicted local distance difference test (pLDDT) is a per-residue measure of local confidence. It is scaled from 0 to 100, with higher scores indicating higher confidence

For every prediction you will get the average pLDDT and the per-residue plot.

Default Per-residue pLDDT Plot

You can also ask Aura to generate a customized plot for you. e.g

Ask Aura

Plot the pLDDT only from residue 85 to 100.

Aura genrated plot for the PLDDT

pLDDT measures confidence in the local structure, estimating how well the prediction would agree with an experimental structure. It is based on the local distance difference test Cα (lDDT-Cα), which is a score that does not rely on superposition but assesses the correctness of the local distances (Mariani et al., 2013).

On this basis, a pLDDT above 90 would be taken as the highest accuracy category, in which both the backbone and side chains are typically predicted with high accuracy. In contrast, a pLDDT above 70 usually corresponds to a correct backbone prediction with misplacement of some side chains.

The structure will be colored using this palette

You can inspect the pLDDT using the visualizer on each residue. The color will indicate the value range.

Visulization of the pLDDT

The pLDDT score can vary significantly along a protein chain. This means models can be very confident in the structure of some parts of the protein, but less confident in other regions. This gives users an indication of which parts of the predicted structure may be reliable and which are unlikely to be (Guo et al., 2022).

Sample pLDDT (predicted Local Distance Difference Test) for a predicted protein structure. Different colours indicate the model’s level of confidence in its prediction (see key).

Source: https://www.ebi.ac.uk/training/online/courses/alphafold/inputs-and-outputs/evaluating-alphafolds-predicted-structures-using-confidence-scores/plddt-understanding-local-confidence/

Last updated

Was this helpful?