Prediction of reversibly oxidized protein cysteine thiols using protein structure properties

Abstract

Protein cysteine thiols can be divided into four groups based on their reactivities: those that form permanent structural disulfide bonds, those that coordinate with metals, those that remain in the reduced state, and those that are susceptible to reversible oxidation. Physicochemical parameters of oxidation-susceptible protein thiols were organized into a database named the Balanced Oxidation Susceptible Cysteine Thiol Database (BALOSCTdb). BALOSCTdb contains 161 cysteine thiols that undergo reversible oxidation and 161 cysteine thiols that are not susceptible to oxidation. Each cysteine was represented by a set of 12 parameters, one of which was a label (1/0) to indicate whether its thiol moiety is susceptible to oxidation. A computer program (the C4.5 decision tree classifier re-implemented as the J48 classifier) segregated cysteines into oxidation-susceptible and oxidation-non-susceptible classes. The classifier selected three parameters critical for prediction of thiol oxidation susceptibility: (1) distance to the nearest cysteine sulfur atom, (2) solvent accessibility, and (3) pKa. The classifier was optimized to correctly predict 136 of the 161 cysteine thiols susceptible to oxidation. Leave-one-out cross-validation analysis showed that the percent of correctly classified cysteines was 80.1% and that 16.1% of the oxidation-susceptible cysteine thiols were incorrectly classified. The algorithm developed from these parameters, named the Cysteine Oxidation Prediction Algorithm (COPA), is presented here. COPA prediction of oxidation-susceptible sites can be utilized to locate protein cysteines susceptible to redox-mediated regulation and identify possible enzyme catalytic sites with reactive cysteine thiols.

Figure 1.

Backbone structure of PTEN tumor suppressor with cysteine residues in space-filling format. All eight cysteines are shown, two of which are susceptible to intramolecular disulfide bond formation (Cys71 and Cys124). The remaining six cysteines remain in the reduced form (Cys83, Cys105, Cys136, Cys211, Cys218, Cys250). Data is from PDB record 1D5R viewed by WebLab Viewer (Accelrys)

Figure 2.

Dependence of percent of correctly classified reactive cysteine thiols and decision tree size on M value. The M value of the J48 classifier was varied from 2 to 70 and allowed to segregate the reactive cysteine thiols into oxidation-susceptible and oxidation-non-susceptible classes. Percent correctly classified cysteine thiols were generated by leave-one-out cross-validation (filled squares). The tree size generated at each M value was plotted (filled circles).

Figure 3.

ROC curves generated by leave-one-out analysis of J48-mediated segregated data in BALOSCTdb. Each curve was generated from a different M value setting. M values ranged from 2 to 70, and data were segregated into oxidation-susceptible and oxidation-non-susceptible classes. The true positive and false positive data were obtained by comparing the predicted oxidation-susceptible cysteines to the known oxidation-susceptible cysteines. Large filled orange circle denotes one point on the curve generated by M49–M52 constrained J48 classifier output. Diagonal line was placed in the plot for reference.

Figure 4.

Cysteine Oxidation Prediction Algorithm created from the decision tree produced by the J48 classifier from data in BALOSCTdb.