کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
442889 692417 2015 8 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Predicting activity approach based on new atoms similarity kernel function
ترجمه فارسی عنوان
پیش بینی رویکرد فعالیت بر اساس عملکرد هسته شباهت های جدید اتم
موضوعات مرتبط
مهندسی و علوم پایه شیمی شیمی تئوریک و عملی
چکیده انگلیسی


• We proposed new kernel functions to predict activity of molecule.
• Atoms coding system based on prime numbers is proposed.
• The proposed functions were tested on two datasets and competitive results were obtained.

Drug design is a high cost and long term process. To reduce time and costs for drugs discoveries, new techniques are needed. Chemoinformatics field implements the informational techniques and computer science like machine learning and graph theory to discover the chemical compounds properties, such as toxicity or biological activity. This is done through analyzing their molecular structure (molecular graph). To overcome this problem there is an increasing need for algorithms to analyze and classify graph data to predict the activity of molecules. Kernels methods provide a powerful framework which combines machine learning with graph theory techniques. These kernels methods have led to impressive performance results in many several chemoinformatics problems like biological activity prediction. This paper presents a new approach based on kernel functions to solve activity prediction problem for chemical compounds. First we encode all atoms depending on their neighbors then we use these codes to find a relationship between those atoms each other. Then we use relation between different atoms to find similarity between chemical compounds. The proposed approach was compared with many other classification methods and the results show competitive accuracy with these methods.

Figure optionsDownload high-quality image (125 K)Download as PowerPoint slide

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Molecular Graphics and Modelling - Volume 60, July 2015, Pages 55–62
نویسندگان
, , ,