PDBsum additions

Abstract

PDBsum, http://www.ebi.ac.uk/pdbsum, is a website providing numerous pictorial analyses of each entry in the Protein Data Bank. It portrays the structural features of all proteins, DNA and ligands in the entry, as well as depicting the interactions between them. The latest features, described here, include annotation of human protein sequences with their naturally occurring amino acid variants, dynamic graphs showing the relationships between related protein domain architectures, analyses of ligand binding clusters across different experimental determinations of the same protein, analyses of tunnels in proteins and new search options.

Figure 1.

Natural human variants for human coagulation factor Xa mapped onto the 3D structure of the protein in PDB entry 2p16. (a) The protein’s ‘wiring diagram’ is annotated with small lightning bolt images to show residues that, according to the 1000 Genomes data, have natural variants (R71 and R150 in this case). The colouring of the protein’s sequence represents the two structural domains, whereas the purple lines, helices and arrows depict the secondary structures: coil, α-helix and β-strand, respectively. The UniProtKB, Pfam and the Ensembl gene identifier references are given above the diagram and the full set of variants listed to the left (not shown). In (b) are shown two LigPlot diagrams of the interactions of the wild-type and the mutated residue with the surrounding protein residues. The left diagram shows the interactions made by the wild-type residue, Arg71, and the right diagram shows those of the variant, Gln71. The residue of interest is drawn with purple bonds, the interacting residues being drawn in orange. Hydrogen bonds are represented by green dotted lines and residues interacting via non-bonded contact are shown as red eyelashes.

Figure 2.

An ArchSchema domain architecture network for coagulation factor Xa from Homo sapiens, PDB entry 2p16. (a) The initial network shows 622 domain architectures (i.e. sequences of Pfam domains), each represented by a different node on the graph. There are over 5500 domain architecture with one of more domains in common with that of coagulation factor Xa, but the graph is automatically trimmed to show only the closest relatives. (b) The same graph, but trimmed via the ArchSchema controls to remove the more distant nodes. (c) A blow-up of the central section of the trimmed graph. Here one can see the sequences of individual Pfam domains, as depicted by the coloured boxes inside each node—taller boxes corresponding to Pfam-A domains and smaller ones to Pfam-B. The node representing coagulation factor Xa is the slightly larger box with a grey background at the top of the inset. Red lines underneath domains indicate there is at least one entry containing the domain in the PDB. (Clicking on the node and then on the proteins marked with a green tick takes you to the structures). Satellite nodes can be added to the plots by selecting the type required: UniProtKB sequence identifiers, PDB identifiers or enzyme classes.

Figure 3.

The target summary provided by DrugPort for the drug apixaban, showing its protein target, coagulation factor Xa. The table shows the UniProt identifier and a schematic diagram of the protein’s Pfam domains (as coloured cylinders). The PDB entries of the protein are represented by the purple schematic diagrams of their secondary structure (the spring-like regions representing α-helices and the arrows corresponding to β-strands). These give an idea of the structural coverage given by the PDB entry and, in this case, one can clearly see that only the trypsin domain has been solved. The red border round the thumbnail for Target 1 indicates that the PDB structures are of the drug molecule bound to that target. The schematic diagrams indicate the residue positions in the protein where the drug molecule binds. Various links are given by the little row of icons in the table headers, including a link to an ArchSchema network (Figure 2) and a ligand cluster analysis (the blue and green superposed molecules) described in the main text.

Figure 4.

The tunnels calculated for PDB entry 2p16, excluding ligands. The tunnels are the coloured shapes embedded in the grey secondary structure representation of the protein. The table on the right shows various properties for each tunnel, the colours of the balls in the table corresponding to the colours in the image.