Naslov
Prediction of protein folding types from the primary nucleotide sequences

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

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

Izvornik
Book of Abstracts MATH/CHEM/COMP 2002 / Ante Graovac, Biserka Pokrić, Vilko Smrečki - Zagreb : Institut Ruđer Bošković, 2002

Skup
MATH/CHEM/COMP 2002 - The 17th Dubrovnik International Course & Conference on the Interfaces among Mathematics, Chemistry and Computer Sciences

Mjesto i datum
Dubrovnik, Hrvatska, 24.06.2002. - 29.06.2002

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
protein folding; machine leraning algorithm; nucleotide sequence; codon frequency

Sažetak
We present new method that enables simple prediction of alpha- and beta-protein folding types from the nucleotide and amino acid sequences. SMO machine learning algotithm for the support vector machines was used for the classification. Relative frequency patterns of particular codons proved to be sufficient for the accurate SMO based discrimination of alpha- and beta- protein folding types. The method is not dependent on the physicochemical parameter analysis of the nucleotide or amino acid sequences. Overall prediction results and procedure cross-validations indicated that this procedure enables simple, quick and accurate prediction of the protein folds on a PC. The mehod may be used for detecting the type of the protein folding from the newly sequenced exon regions.

Izvorni jezik
Engleski

Znanstvena područja
Temeljne medicinske znanosti

POVEZANOST RADA