Performance analysis of support vector machine combined with global encoding on detection of protein-protein interaction network of HIV virus
Abstract
Proteins are bio-macromolecules that have an important role in living organisms. This type of protein consists of a series of combinations of 20 amino acids. In living organisms, Protein-Protein Interactions (PPIs) have an important role in most biological processes so that by detecting protein interactions (PPIs) will be able to understand molecular mechanisms in biological systems. By using the calculation process and applying machine learning method, it will be more efficient than the experimental method that takes a long time and expensive cost. The novelty in this paper we use the Support Vector Machine (SVM) combined with Global Encoding (GE) to achieve better performance than previous methods and the dataset used is the interaction of HIV proteins with humans based on the sequence of amino acids. The results show that the proposed method is robust, feasible and can be used in detecting interactions of other proteins with an accuracy of up to 85 %.
- Publication:
-
Proceedings of the 3rd International Symposium on Current Progress in Mathematics and Sciences 2017 (ISCPMS2017)
- Pub Date:
- October 2018
- DOI:
- 10.1063/1.5064225
- Bibcode:
- 2018AIPC.2023b0228L