Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
PREDICTING PROTEIN STRUCTURAL CLASSES FROM AMINO-ACID-COMPOSITION - APPLICATION OF FUZZY CLUSTERING
Autore:
ZHANG CT; CHOU KC; MAGGIORA GM;
Indirizzi:
UPJOHN CO,COMP AIDED DRUG DISCOVERY KALAMAZOO MI 49007 UPJOHN CO,COMP AIDED DRUG DISCOVERY KALAMAZOO MI 49007 TIANJIN UNIV,DEPT PHYS TIANJIN 300072 PEOPLES R CHINA
Titolo Testata:
Protein engineering
fascicolo: 5, volume: 8, anno: 1995,
pagine: 425 - 435
SICI:
0269-2139(1995)8:5<425:PPSCFA>2.0.ZU;2-I
Fonte:
ISI
Lingua:
ENG
Keywords:
ALL ALPHA; ALL BETA; ALPHA+BETA; ALPHA; BETA; FUZZY CLUSTERING; FUZZY SETS; PROTEIN STRUCTURAL CLASS;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Science Citation Index Expanded
Citazioni:
20
Recensione:
Indirizzi per estratti:
Citazione:
C.T. Zhang et al., "PREDICTING PROTEIN STRUCTURAL CLASSES FROM AMINO-ACID-COMPOSITION - APPLICATION OF FUZZY CLUSTERING", Protein engineering, 8(5), 1995, pp. 425-435

Abstract

Most globular proteins can be classified into one of four structural classes-all-alpha, all-beta, alpha+beta and alpha/beta-depending upon the type, amount and arrangement of secondary structures present, In this work a new method, based upon fuzzy clustering, is proposed for predicting the structural class of a protein from its amino acid composition, Here, each of the structural classes is described by a fuzzy cluster and each protein is characterized by its membership degree, a number between zero and one in each of the four clusters, with the constraint that the sum of the membership degrees equals unity, A given protein is then classified as belonging to that structural class corresponding to the fuzzy cluster with maximum membership degree, Calculation of membership degrees is carried out using the fuzzy c-means algorithmon a training set of 64 proteins, Results obtained for the training set show that the fuzzy clustering approach produces results comparablewith or better than those obtained by other methods. A test set of 27proteins also produced comparable results to those obtained with the training set, The success of the present preliminary work on protein structure class prediction suggests that further refinements of method mag lead to improved predictions and this is currently being investigated.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/11/20 alle ore 15:48:50