Fold Recognition Using Sequence Fingerprints of Protein Local Substructures

Conference · 04 June 2003

DOI:https://doi.org/10.1109/CSB.2003.1227393· OSTI ID:15004201

Kryshtafovych, A A; Hvidsten, T; Komorowski, J; Fidelis, K

A protein local substructure (descriptor) is a set of several short non-overlapping fragments of the polypeptide chain. Each descriptor describes local environment of a particular residue and includes only those segments that are located in the proximity of this residue. Similar descriptors from the representative set of proteins were analyzed to reveal links between the substructures and sequences of their segments. Using detected sequence-based fingerprints specific geometrical conformations are assigned to new sequences. The ability of the approach to recognize correct SCOP folds was tested on 273 sequences from the 49 most popular folds. Good predictions were obtained in 85% of cases. No performance drop was observed with decreasing sequence similarity between target sequences and sequences from the training set of proteins.

• Research Organization: Lawrence Livermore National Laboratory (LLNL), Livermore, CA
• Sponsoring Organization: USDOE
• DOE Contract Number: W-7405-ENG-48
• OSTI ID: 15004201
• Report Number(s): UCRL-JC-153905
• Country of Publication: United States
• Language: English

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
COMPUTERS
PERFORMANCE
POLYPEPTIDES
PROTEINS
RESIDUES
TARGETS
TRAINING