Napredna pretraga

Pregled bibliografske jedinice broj: 308354

Prediction of protein-protein hetero interaction sites from local sequence information using Random Forest


Šikić, Mile; Jeren, Branko; Vlahoviček, Kristian
Prediction of protein-protein hetero interaction sites from local sequence information using Random Forest // Book of abstracts, The 2nd Opatija Meeting on Computational Solutions in the Life Sciences / Babić, Darko ; Došlić, Nađa ; Smith, David ; Tomić, Sanja, Vlahoviček, Kristian (ur.).
Opatija: Centre for Computational Solutions in the Life Sciences, IRB, 2007. str. 87-87 (poster, međunarodna recenzija, sažetak, znanstveni)


Naslov
Prediction of protein-protein hetero interaction sites from local sequence information using Random Forest

Autori
Šikić, Mile ; Jeren, Branko ; Vlahoviček, Kristian

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

Izvornik
Book of abstracts, The 2nd Opatija Meeting on Computational Solutions in the Life Sciences / Babić, Darko ; Došlić, Nađa ; Smith, David ; Tomić, Sanja, Vlahoviček, Kristian - Opatija : Centre for Computational Solutions in the Life Sciences, IRB, 2007, 87-87

ISBN
978-953-6690-69-5

Skup
The 2nd Opatija Meeting on Computational Solutions in the Life Sciences

Mjesto i datum
Opatija, Hrvatska, 04-09.09.2007

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Protein ; prediction ; interaction ; sequence ; random forest

Sažetak
Identifying the interface between two interacting proteins provides important clues to the function of a protein, and is becoming increasing relevant to drug discovery. Many studies indicate that the compositions of contacting residues are unique. Here, we describe a method using random forest that identifies protein-protein interfaces from sequence. For prediction we use a non-redundant set of 333 protein complexex. The AUC for random forest classifier is 0.76. When 75% of our predictions were right, we correctly predicted 34% of all interaction sites. In almost all proteins we correctly predicted at least one interaction site. Furthermore, when in prediction we included residues that are up to 5 residues far from our predicted size, we covered 65% of all interaction sites. These results strongly indicate that prediction of interaction sites from sequence alone is possible and comparable with results obtained using structure information. Incorporating predicted structural information like ASA, secondary structure, depth and protrusion index may improve our method.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika



POVEZANOST RADA


Projekt / tema
036-0362214-1987 - Modeliranje kompleksnih sustava (Branko Jeren, )

Ustanove
Fakultet elektrotehnike i računarstva, Zagreb