کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6369136 | 1623807 | 2016 | 8 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Machine learning approaches for discrimination of Extracellular Matrix proteins using hybrid feature space
ترجمه فارسی عنوان
روش های یادگیری ماشین برای تبعیض از پروتئین ماتریس خارج سلولی با استفاده از فضای ویژگی هیبرید
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
موضوعات مرتبط
علوم زیستی و بیوفناوری
علوم کشاورزی و بیولوژیک
علوم کشاورزی و بیولوژیک (عمومی)
چکیده انگلیسی
Extracellular Matrix (ECM) proteins are the vital type of proteins that are secreted by resident cells. ECM proteins perform several significant functions including adhesion, differentiation, cell migration and proliferation. In addition, ECM proteins regulate angiogenesis process, embryonic development, tumor growth and gene expression. Due to tremendous biological significance of the ECM proteins and rapidly increases of protein sequences in databases, it is indispensable to introduce a new high throughput computation model that can accurately identify ECM proteins. Various traditional models have been developed, but they are laborious and tedious. In this work, an effective and high throughput computational classification model is proposed for discrimination of ECM proteins. In this model, protein sequences are formulated using amino acid composition, pseudo amino acid composition (PseAAC) and di-peptide composition (DPC) techniques. Further, various combination of feature extraction techniques are fused to form hybrid feature spaces. Several classifiers were employed. Among these classifiers, K-Nearest Neighbor obtained outstanding performance in combination with the hybrid feature space of PseAAC and DPC. The obtained accuracy of our proposed model is 96.76%, which the highest success rate has been reported in the literature so far.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Theoretical Biology - Volume 403, 21 August 2016, Pages 30-37
Journal: Journal of Theoretical Biology - Volume 403, 21 August 2016, Pages 30-37
نویسندگان
Farman Ali, Maqsood Hayat,