Combining structure and sequence information allows automated prediction of substrate specificities within enzyme families

Abstract

An important aspect of the functional annotation of enzymes is not only the type of reaction catalysed by an enzyme, but also the substrate specificity, which can vary widely within the same family. In many cases, prediction of family membership and even substrate specificity is possible from enzyme sequence alone, using a nearest neighbour classification rule. However, the combination of structural information and sequence information can improve the interpretability and accuracy of predictive models. The method presented here, Active Site Classification (ASC), automatically extracts the residues lining the active site from one representative three-dimensional structure and the corresponding residues from sequences of other members of the family. From a set of representatives with known substrate specificity, a Support Vector Machine (SVM) can then learn a model of substrate specificity. Applied to a sequence of unknown specificity, the SVM can then predict the most likely substrate. The models can also be analysed to reveal the underlying structural reasons determining substrate specificities and thus yield valuable insights into mechanisms of enzyme specificity. We illustrate the high prediction accuracy achieved on two benchmark data sets and the structural insights gained from ASC by a detailed analysis of the family of decarboxylating dehydrogenases. The ASC web service is available at http://asc.informatik.uni-tuebingen.de/.

Figure 1. Graphical overview of the ASC method.

(A) In the first step training sequences are aligned using 3DCoffee to get an MSA. (B) In a second step residues lining the active site are extracted from the template structure. (C) The third step maps the extracted residues along the MSA to get a signature of the active site for each sequence. (D) These signatures are then encoded into feature vectors using the three descriptors . Alternatively, kernels may be used. (E) The final ASC model is trained using the generated feature vectors.

Figure 2. View on the superimposed active sites of IPMDH and ICDH.

The first chain of the homo-dimeric enzyme is represented by its solvent-excluded surface. The second chain is depicted in a backbone representation. The two substrates isocitrate (purple) and isopropylmalate (green) lie in the interface of the two chains. IPMDH sidechains are coloured green and sidechains from ICDH (PDB-Id: 1AI2, [40]) are coloured purple. This figure was created using BALLView .