Heather R Brodkin, Nicholas A DeLateur, Srinivas Somarowthu, Caitlyn L Mills, Walter R Novak, Penny J Beuning, Dagmar Ringe, Mary Jo Ondrechen

A scoring method for the prediction of catalytically important residues in enzyme structures is presented and used to examine the participation of distal residues in enzyme catalysis. Scores are based on the Partial Order Optimum Likelihood (POOL) machine learning method, using computed electrostatic properties, surface geometric features, and information obtained from the phylogenetic tree as input features. Predictions of distal residue participation in catalysis are compared with experimental kinetics data from the literature on variants of the featured enzymes; some additional kinetics measurements are reported for variants of Pseudomonas putida nitrile hydratase (ppNH) and for E. coli alkaline phosphatase (AP). The multi-layer active sites of Pseudomonas putida nitrile hydratase and of human phosphoglucose isomerase are predicted by the POOL logZP scores, as is the single-layer active site of Pseudomonas putida ketosteroid isomerase. The logZP score cutoff utilized here results in over-prediction of distal residue involvement in E. coli alkaline phosphatase. While fewer experimental data points are available for Pseudomonas putida mandelate racemase and for human carbonic anhydrase II, the POOL logZP scores properly predict the previously reported participation of distal residues. This article is protected by copyright. All rights reserved.