SBSPKS: structure based sequence analysis of polyketide synthases

Abstract

Polyketide synthases (PKSs) catalyze biosynthesis of a diverse family of pharmaceutically important secondary metabolites. Bioinformatics analysis of sequence and structural features of PKS proteins plays a crucial role in discovery of new natural products by genome mining, as well as in design of novel secondary metabolites by biosynthetic engineering. The availability of the crystal structures of various PKS catalytic and docking domains, and mammalian fatty acid synthase module prompted us to develop SBSPKS software which consists of three major components. Model_3D_PKS can be used for modeling, visualization and analysis of 3D structure of individual PKS catalytic domains, dimeric structures for complete PKS modules and prediction of substrate specificity. Dock_Dom_Anal identifies the key interacting residue pairs in inter-subunit interfaces based on alignment of inter-polypeptide linker sequences to the docking domain structure. In case of modular PKS with multiple open reading frames (ORFs), it can predict the cognate order of substrate channeling based on combinatorial evaluation of all possible interface contacts. NRPS-PKS provides user friendly tools for identifying various catalytic domains in the sequence of a Type I PKS protein and comparing them with experimentally characterized PKS/NRPS clusters cataloged in the backend databases of SBSPKS. SBSPKS is available at http://www.nii.ac.in/sbspks.html.

Figure 1.

Schematic diagram depicting differences in domain annotations on a typical PKS module by sequence and structure based approach. Various catalytic domains annotated by sequence based programs like NRPS–PKS are shown as circles and the lines connecting the circles represent inter-domain linker stretches. For the same PKS module, the rectangular boxes depict the stretches aligning with various crystal structures of Type I PKS proteins. As can be seen boundaries of some catalytic domains have significantly altered and several amino acid stretches depicted as linkers by NRPS–PKS have compact structures and constitute structural domains of PKS. The figure also shows the crystal structures (PDB IDs 2HG4, 3EL6, 1IZ0, 2FR0 for KS-AT, DH, ER and KR, respectively) of various structural and catalytic domains in the same color as depicted in rectangular boxes.

Figure 2.

The figure depicts usage of NRPS–PKS for depicting various catalytic domains present in the query sequence. Clicking on each domain leads to a page which provides the details of its alignment with its structural homologs present in PDB as well as with other homologous domains in different experimentally characterized PKS clusters. The screenshot also depicts the prediction of substrate specificity of AT domain based on comparison of its putative active site pocket residues with AT domains having known substrates.

Figure 3.

Screen shots showing various options available in Model_3D_PKS and their usage for modeling 3D structures of various structural and catalytic domains present in a PKS module as well as structure of the complete module. The figure also shows usage of the software for depicting SDRs of KR domain on its structure and predicting stereo-specificity of the KR domain based on these residues.

Figure 4.

The figure depicts various options available in Dock_Dom_Anal for prediction of the order of substrate channeling between multiple ORFs in a modular PKS cluster based on docking domain interactions. As can be seen the program can quickly evaluate the total number of favorable, unfavorable and neutral inter-subunit contacts for various combinatorial orders of six ORFs present in a modular PKS cluster.