Naslov
New binary algorithm for the prediction of protein folding types

Autori
Štambuk, Nikola ; Konjevoda, Paško ; Gotovac, Nikola

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
Book of Abstracts MATH/CHEM/COMP 2004 / Graovac, Ante ; Pokrić, Biserka ; Smrečki, Vilko - Zagreb : Institut Ruđer Bošković, 2004, 78-78

Skup
MATH/CHEM/COMP 2004 - The 19th Dubrovnik International Course & Conference on the Interfaces among Mathematics, Chemistry and Computer Sciences

Mjesto i datum
Dubrovnik, Hrvatska, 21.06.2004. - 26.06.2004

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
amino acid; binary algorithm; classification trees; DNA; genetic code; machine learning; nucleotide; protein folding; RNA

Sažetak
New binary algorithm for the prediction of alpha and beta protein folding types from RNA, DNA and amino acid sequences is described. The algorithm was tested with machine learning SMO classifier for the support vector machines and classification trees, on a dataset of 140 dissimilar protein folds. Depending on the method of testing, the overall classification accuracy was > 90 and the tenfold cross validation result of the procedure was > 80%. The method enables quick, simple and accurate prediction of alpha and beta protein folds on a personal computer by means of few binary patterns of coded amino acid and nucleotide physicochemical properties. Genetic code randomisation analysis based on 100, 000 different codes tested for the protein fold prediction quality indicated that dipeptides represent basic protein units with respect to the genetic code defining of the secondary protein structure.

Izvorni jezik
Engleski

Znanstvena područja
Temeljne medicinske znanosti

POVEZANOST RADA