Enhanced Protein Classification Using Geometric Similarity

Summary: High accuracy classification of proteins based on the geometric similarity of their molecules.

Reference Code: 0105

The chemical properties and general function of given molecule are determined mainly by its structure in 3D space. All information required for a protein to be folded in its natural 3D structure is coded in its amino acid sequence. Therefore, the 3D representation of a residue sequence and the way this sequence folds in the 3D space are very important in order to be able to understand the “logic” in which a function or biological action of a protein is based on. With the technology innovation and the rapid development of X-Ray crystallography methods and NMR spectrum analysis techniques, a high number of new 3D structures of protein molecules is already available. Since the number of known protein structures increases very rapidly, a need for a classification of proteins is obvious, which may result in a better understanding of these complicated structures, their functions, and the deeper evolutionary procedures that led to their creation.

Distinctive aspects of the research

Fast and accurate classification of proteins based only on the geometric similarity of the protein’s 3D structure.

Potential applications

Useful tool for biologists and biochemists who are studying protein folding and protein classification providing fast filtering and suggesting a limited set of potential categories that the new protein may belong to. In this way, the time consuming experimental validation can be performed on a small set of potential categories.

Partnership sought

The tool has been already tested on benchmark datasets achieving high classification accuracy. Experimental testing can be also performed in real cases but this should be done in collaboration with biologists and biochemists for experimental validation of the produced results. Further research focuses on improving the geometric similarity search algorithms in order to decrease the computation time. The research effort for that is estimated to 1 year.

Resources and information



Under an open call launched this week, EXPERIMEDIA is making available over €500k to fund new experiments in the area of Future Media Internet (FMI).

Whether you're a service provider, technology/ application developer, broadcaster, content provider, network provider or researcher EXPERIMEDIA are looking for novel FMI experiments that help to understand and deliver new forms of social interaction and experience to communities online and in the real world.

The emphasis is on technology R&D for large-scale live events linking people to each other and to locations in ways that capture popular imagination.

Project participants will gain access to real-world Testbed Ecosystems at Schladming Ski Resort, the Multi-Sport High Performance Centre of Catalonia and the Foundation for the Hellenic World.

The Schladming testbed venue

EXPERIMEDIA seek experiments in the areas of:

● personalised entertainment supporting interaction, non-linear storytelling and immersive experiences;

● social communities using 3D environments to communicate and interact;

● capture and reproduction of the real world in 3D;

● perceptual congruity between real and virtual worlds.

All experiments must deliver significant impact to users and businesses within the testbed venues.

EXPERIMEDIA will be running a series of teleconferences on 4th July to provide information about the facilities and venues. In addition to the technical team, key people from each venue will be available to answer questions about the live events being targeted. Email info@experimedia.eu to register.

The open call closes on Wednesday 1st August 2012. For further details, visit the EXPERIMEDIA website. (See also the EXPERIMEDIA Project Overview (65)).