Pregled bibliografske jedinice broj: 1111103
An evolution based classifier for prediction of protein interfaces without using protein structures
An evolution based classifier for prediction of protein interfaces without using protein structures // Bioinformatics, 21 (2005), 10; 2496-2501 doi:10.1093/bioinformatics/bti340 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1111103 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
An evolution based classifier for prediction of protein interfaces without using protein structures
Autori
Res, I. ; Mihalek, I. ; Lichtarge, O.
Izvornik
Bioinformatics (1367-4803) 21
(2005), 10;
2496-2501
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
machine learning, protein interactions
Sažetak
Motivation: The number of available protein structures still lags far behind the number of known protein sequences. This makes it important to predict which residues participate in protein–protein interactions using only sequence information. Few studies have tackled this problem until now. Results: We applied support vector machines to sequences in order to generate a classification of all protein residues into those that are part of a protein interface and those that are not. For the first time evolutionary information was used as one of the attributes and this inclusion of evolutionary importance rankings improves the classification. Leave-one-out cross-validation experiments show that prediction accuracy reaches 64%.
Izvorni jezik
Engleski
Znanstvena područja
Biologija, Računarstvo, Biotehnologija, Interdisciplinarne biotehničke znanosti, Biotehnologija u biomedicini (prirodno područje, biomedicina i zdravstvo, biotehničko područje)
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus
- MEDLINE
