Automated selection of positions determining functional specificity of proteins by comparative analysis of orthologous groups in protein families

Abstract

The increasing volume of genomic data opens new possibilities for analysis of protein function. We introduce a method for automated selection of residues that determine the functional specificity of proteins with a common general function (the specificity-determining positions [SDP] prediction method). Such residues are assumed to be conserved within groups of orthologs (that may be assumed to have the same specificity) and to vary between paralogs. Thus, considering a multiple sequence alignment of a protein family divided into orthologous groups, one can select positions where the distribution of amino acids correlates with this division. Unlike previously published techniques, the introduced method directly takes into account nonuniformity of amino acid substitution frequencies. In addition, it does not require setting arbitrary thresholds. Instead, a formal procedure for threshold selection using the Bernoulli estimator is implemented. We tested the SDP prediction method on the LacI family of bacterial transcription factors and a sample of bacterial water and glycerol transporters belonging to the major intrinsic protein (MIP) family. In both cases, the comparison with available experimental and structural data strongly supported our predictions.

Figure 1.

The phylogenetic tree of the analyzed proteins from the MIP family. Proteins of the AQP and the GLP training sets are in bold. Eukaryotic members of the MIP family are in bold and underlined.

Figure 2.

Candidate SDP for the LacI (A) and TreR (B) repressors. Effector molecules are shown by space filling and colored yellow; SDP are shown by space filling and colored by function: red, residues in close contact with DNA; green, residues in close contact with effectors; blue, residues in close contact with the other subunit; white, residues near the DNA-binding or effector-binding region but not satisfying the contact criteria (see the legend to Table 1); gray, overprediction (residues with no obvious function).

Figure 3.

Residues making close contacts with the effector (minimal distance <5 Å) in PurR, LacI, and TreR repressors (numbering as in PurR from E. coli).

Figure 4.

The Bernoulli estimator for the training set (17 bacterial MIP proteins). Horizontal axis: k, the number of accepted positions. Vertical axis: probability that there are at least k Z-scores Z ≥ Z_k.

Figure 5.

Candidate SDP for GlpF from E. coli and for bovine AQP1. (A) Structure of GlpF from E. coli with three glycerol molecules (top). (B) Structure of bovine AQP1 with several water molecules in the channel (top). Substrate molecules are shown by space filling and colored green. Candidate SDP are shown by space filling and colored yellow if they form the channel and red if they may establish subunit interactions (see the text for discussion).

Figure 6.

The phylogenetic tree of the proteins from MIP family (after the realignment, both training and test sets are included). The branch colors indicate orthology relationships: blue, bidirectional best hits (BETs) of AqpZ E. coli AQPZ_ECOLI); green, true GlpF orthologs, that is, BETs of GlpF from E. coli for gram-negative bacteria and BETs of GlpF from Bacillus subtilis for gram-positive bacteria if their genes lie in operons related to the glycerol metabolism; light green, recent GlpF paralogs whose genes lie in operons involved in the glycerol metabolism; purple, proteins homologous to PduF from Salmonella typhimurium whose genes are located in the gene cluster related to the propanediol degradation; brown, glyceroaquaporins, that is, BETs of GLA from Lactococcus lactis; magenta, true paralogs, that is, GlpF homologs whose genes lie in operons with functions other than glycerol metabolism; orange, proteins with unresolved orthology relationships. The colors of the protein names indicate the protein specificity assigned by SDP profiles: blue, proteins selected by the AQP SDP profile (W_AQP3); green, proteins selected by the GLP SDP profile (W_GLP3). The names of the proteins from the training sets for AQP and GLP groups are in bold. Bold red, eukaryotic MIP proteins.

Figure 7.

The protein function predicted by the SDP profile score. (A) Average identity of the test proteins to the proteins from the AQP and GLP training sets. (B) Scores of the proteins from the test set computed using the AQP and GLP profiles. For the interpretation of colors, see the legend to Figure 6 ▶.