LinkProt: a database collecting information about biological links

Abstract

Protein chains are known to fold into topologically complex shapes, such as knots, slipknots or complex lassos. This complex topology of the chain can be considered as an additional feature of a protein, separate from secondary and tertiary structures. Moreover, the complex topology can be defined also as one additional structural level. The LinkProt database (http://linkprot.cent.uw.edu.pl) collects and displays information about protein links - topologically non-trivial structures made by up to four chains and complexes of chains (e.g. in capsids). The database presents deterministic links (with loops closed, e.g. by two disulfide bonds), links formed probabilistically and macromolecular links. The structures are classified according to their topology and presented using the minimal surface area method. The database is also equipped with basic tools which allow users to analyze the topology of arbitrary (bio)polymers.

Figure 1.

The timeline of the number of new LinkProt entries. The total number (green curve), total number of sequentially non-redundant structures (orange curve) and non-redundant entries in each month (blue curve) are presented. In the top-left corner various realizations of the Hopf link topology are presented — the deterministic link (bottom-left), probabilistic (center) and macromolecular (top-right).

Figure 2.

Example page of a link data interpretation. Left, structure of proteins with minimal surfaces spanning the covalent loops. Right, pie chart presenting possible link types for the HIV-1 protease with PDB code 3IXO. All detected links whose probability is shown on the pie chart are displayed as icons.

Figure 3.

Top, the table of possible link types with the link probability and piercing residues. Middle, the colored sequence presenting the piercing residues. Bottom, the piercing histograms.

Figure 4.

Example of macromolecular links with their schematic representations: left panel flower link (5), right panel Hopf link.

Figure 5.

Presentation of the Search tab. The top of the page shows filters: sequence similarity, the probability cut-off (for probabilistic links) and disregard chirality (to distinguish subtypes in a given link type, depending on its chirality and chain orientation). Middle, left and right panels present icons of deterministic and probabilistic links. The search panel also contains macromolecular links and link types which are not shown here.