کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
4496254 1623866 2014 7 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Accurate prediction of protein structural classes by incorporating predicted secondary structure information into the general form of Chou's pseudo amino acid composition
ترجمه فارسی عنوان
پیش بینی دقیق از کلاس های ساختاری پروتئین با استفاده از اطلاعات پیش بینی شده ساختار ساختاری به فرم کلی ترکیب شبه آمینو اسید چو
موضوعات مرتبط
علوم زیستی و بیوفناوری علوم کشاورزی و بیولوژیک علوم کشاورزی و بیولوژیک (عمومی)
چکیده انگلیسی


• Secondary structure-based approach of feature extraction is used.
• Segment-level features can improve prediction performance for α/β and α+β classes.
• The proposed novel features are quite relevant to protein secondary structure.
• The experimental results show that our method is an effective and promising tool.

Extracting good representation from protein sequence is fundamental for protein structural classes prediction tasks. In this paper, we propose a novel and powerful method to predict protein structural classes based on the predicted secondary structure information. At the feature extraction stage, a 13-dimensional feature vector is extracted to characterize general contents and spatial arrangements of the secondary structural elements of a given protein sequence. Specially, four segment-level features are designed to elevate discriminative ability for proteins from the α/βα/β and α+βα+β classes. After the features are extracted, a multi-class non-linear support vector machine classifier is used to implement protein structural classes prediction. We report extensive experiments comparing the proposed method to the state-of-the-art in protein structural classes prediction on three widely used low-similarity benchmark datasets: FC699, 1189 and 640. Our method achieves competitive performance on prediction accuracies, especially for the overall prediction accuracies which have exceeded the best reported results on all of the three datasets.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Theoretical Biology - Volume 344, 7 March 2014, Pages 12–18
نویسندگان
, , ,