Accession Number : ADA326666

Title :   Protein Structure Prediction by Memory-Base Reasoning,

Corporate Author : THINKING MACHINES CORP CAMBRIDGE MA

Personal Author(s) : Zhang, Xiru ; Waltz, David ; Mesirov, Jill

PDF Url : ADA326666

Report Date : 14 DEC 1988

Pagination or Media Count : 20

Abstract : Memory-based reasoning (MBR) is a technique that makes intensive use of memory to recall some specific episodes from the past for problem solving. It is used in this research to predict protein structures based on 112 known structures selected from the Brookhaven Protein Databank. The phi and psi, angles of each amino acid in a protein are used to represent its 3-D structure. For this particular problem, we extend MBR to include a recursive procedure to refine its initial prediction and a varying 'window' size to take into account the interaction between amino acids apart from different distances along the amino acid sequence. The system implemented, PHI-PSI, has been tested with all the available data. It does better than distribution-based guesses for most of the phi and psi; angle values.

Descriptors :   *MEMORY(PSYCHOLOGY), *PROBLEM SOLVING, *AMINO ACIDS, ANGLES, SIZES(DIMENSIONS), PREDICTIONS, PROTEINS, STRUCTURES, SEQUENCES, MEMORY DEVICES, RECURSIVE FUNCTIONS, WINDOWS, VALUE.

Subject Categories : Psychology
      Biochemistry

Distribution Statement : APPROVED FOR PUBLIC RELEASE