An SVM method using evolutionary information for the identification of allergenic proteins

Abstract

Abstract:This study presents an allergenic protein prediction system that appears to be capable of producing high sensitivity and specificity. The proposed system is based on support vector machine (SVM) using evolutionary information in the form of an amino acid position specific scoring matrix (PSSM). The performance of this system is assessed by a 10-fold crossvalidation experiment using a dataset consisting of 693 allergens and 1041 non-allergens obtained from Swiss-Prot and Structural Database of Allergenic Proteins (SDAP). The PSSM method produced an accuracy of 90.1% in comparison to the methods based on SVM using amino acid, dipeptide composition, pseudo (5-tier) amino acid composition that achieved an accuracy of 86.3, 86.5 and 82.1% respectively. The results show that evolutionary information can be useful to build more effective and efficient allergen prediction systems.

Navigating through the Jungle of Allergens: Features and Applications of Allergen Databases

“…In a study aiming at predicting allergenicity of proteins, Kumar and Shelokar [34] used a machine learning approach to distinguish allergenic from nonallergenic proteins. Their software classified proteins based on several sequence-related features.…”

Target Identification in Ory S1 Pollen Protein Allergen from Oryza sativa in the Course of Construction of Hypoallergenic Vaccines

“…The molecules developed for vaccination against allergy possess significantly reduced allergenicity in terms of IgE binding and therefore will not lead to anaphylactic reactions upon injection. This approach is probably feasible with every allergen with known amino acid sequence; irrespective of the source (pollen, food, mites) from which it may be derived [5] . Also, the products of agricultural biotechnology should be subjected to a careful and complete safety assessment for its allergenicity before commercialization.…”

Prediction of antibiotic resistance proteins from sequence-derived properties irrespective of sequence similarity

“…In this work, we employed support vector machines (SVMs) as such a method. SVMs have been successfully applied to the identification of novel enzymes [24], novel bacterial proteins [25] and various functional classes of proteins [26,27]. The capacity of SVMs to predict ARPs was evaluated using an independent set of proteins that were not included during model development.…”