Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
CROSS-VALIDATION OF PROTEIN STRUCTURAL CLASS PREDICTION USING STATISTICAL CLUSTERING AND NEURAL NETWORKS
Autore:
METFESSEL BA; SAURUGGER PN; CONNELLY DP; RICH SS;
Indirizzi:
OPIN SYST,INT PLAZA,SUITE 635,7900 INT DR BLOOMINGTON MN 55425 UNIV MINNESOTA,DEPT LAB MED & PATHOL MINNEAPOLIS MN 55455 PIONEER HI BRED INT INC,DIV PLANT BREEDING,DEPT DATA MANAGEMENT JOHNSTON IA 50131
Titolo Testata:
Protein science
fascicolo: 7, volume: 2, anno: 1993,
pagine: 1171 - 1182
SICI:
0961-8368(1993)2:7<1171:COPSCP>2.0.ZU;2-0
Fonte:
ISI
Lingua:
ENG
Soggetto:
SECONDARY STRUCTURE PREDICTION; AMINO-ACID COMPOSITION; GLOBULAR-PROTEINS; SEQUENCE; HYDROPHOBICITY; DATABASE; PATTERNS;
Keywords:
BACKPROPAGATION NEURAL NETWORK; CROSS-VALIDATION; EUCLIDEAN DISTANCE; LEARNING VECTOR QUANTIZATION NEURAL NETWORK; MCNEMAR TEST; PROTEIN STRUCTURAL CLASS PREDICTION;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Science Citation Index Expanded
Citazioni:
31
Recensione:
Indirizzi per estratti:
Citazione:
B.A. Metfessel et al., "CROSS-VALIDATION OF PROTEIN STRUCTURAL CLASS PREDICTION USING STATISTICAL CLUSTERING AND NEURAL NETWORKS", Protein science, 2(7), 1993, pp. 1171-1182

Abstract

We present an approach to predicting protein structural class that uses amino acid composition and hydrophobic pattern frequency information as input to two types of neural networks: (1) a three-layer back-propagation network and (2) a learning vector quantization network. The results of these methods are compared to those obtained from a modifiedEuclidean statistical clustering algorithm. The protein sequence dataused to drive these algorithms consist of the normalized frequency ofup to 20 amino acid types and six hydrophobic amino acid patterns. From these frequency values the structural class predictions for each protein (all-alpha, all-beta, or alpha-beta classes) are derived. Examples consisting of 64 previously classified proteins were randomly divided into multiple training (56 proteins) and test (8 proteins) sets. The best performing algorithm on the test sets was the learning vector quantization network using 17 inputs, obtaining a prediction accuracy of 80.2%. The Matthews correlation coefficients are statistically significant for all algorithms and all structural classes. The differences between algorithms are in general not statistically significant. Theseresults show that information exists in protein primary sequences that is easily obtainable and useful for the prediction of protein structural class by neural networks as well as by standard statistical clustering algorithms.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/11/20 alle ore 15:01:19