Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: Improving the accuracy of high-throughput protein-protein affinity prediction may require better training data

Fig. 4

Database errors may interfere with affinity prediction accuracy. We predicted the binding affinities of mutant D121A intracellular inhibitor NuiA (NuiA; yellow) and wild-type NuiA (purple) in complex with Nuclease A (nucA; gray) using the trained statistical affinity-prediction model. The wild-type NuiA structure was inferred by homology modeling, using the mutant structure as a template. We plot the structure of each complex and report predicted and experimentally-determined binding affinities (pKds). Inset displays a close-up of the D121A mutation, showing an inferred hydrogen bond between D121 and E24 of NucA (dashed line)

Back to article page