Increasing the prediction accuracy of PseAAC in protein-protein interactions
Küçük Resim Yok
Tarih
2011
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Prediction of protein-protein interactions is an important problem in biology. They are critical in coordinating various cellular processes and help understanding protein function and drug design. Extracting protein features from amino acid sequences is important in order to study protein-protein interactions. A number of feature extraction approaches for proteins have been introduced up to the present. PseAAC is one of the most used protein feature extractor. In this paper we modulated calculation steps of PSEAAC for extracting amino acid compositions and proposed a new method. The aim of our method is to adjust the weights of the composition values during feature extracting process. This means that bigger composition values will contribute to the classification process more than smaller ones. Our experimental results showed that our approach outperformed PseAAC and other methods listed in literature. © 2011 IADIS.
Açıklama
IADIS European Conference on Data Mining 2011, Part of the IADIS Multi Conference on Computer Science and Information Systems 2011, MCCSIS 2011 -- 24 July 2011 through 26 July 2011 -- Rome -- 91770
Anahtar Kelimeler
Protein-protein interactions, Pseudo amino acid composition, Support vector machine (SVM)
Kaynak
Proceedings of the IADIS European Conference on Data Mining 2011, Part of the IADIS Multi Conference on Computer Science and Information Systems 2011, MCCSIS 2011
WoS Q Değeri
Scopus Q Değeri
N/A
