Rcmde-gsd: Building Global Hierarchical Classifiers Using Differential Evolution for Predicting Gene Ontology Terms
نویسندگان
چکیده
In this work, we present a method to the building of a global hierarchical classification of the proteins functions for a structure of classes represented by a DAG (Directed Acyclic Graph), called RCMDE-GSD (Rule Construction Method Using Differential Evolution-Global Single DAG). Here, we compare RCMDE-GSD with hAntMiner, a method based on ACO (Ant Colony Optimization) algorithm and with HLCS, a method based on Learning Classifier Systems. In all the experiments, RCMDEGSD outperformed or had similar results with at least one of the other two algorithms. Using Kruskal Wallis test, we conclude that the difference between the three algorithms was nonsignificant. Keywords— Hierarchical classifiers; DAG; classes.
منابع مشابه
Trying Predicting Protein Function Using Machine-learned Hierarchical Classifiers
High performance and accurate protein function prediction is a challenging problem in Bioinformatics. Many contemporary ontologies, such as Gene Ontology, have a hierarchical structure that can be exploited to improve the prediction accuracy, and lower the computational cost of protein function prediction. The structure of the hierarchy is leveraged in two ways: First, a novel method of creatin...
متن کاملA Hierarchical Classification Ant Colony Algorithm for Predicting Gene Ontology Terms
This paper proposes a novel Ant Colony Optimisation algorithm for the hierarchical problem of predicting protein functions using the Gene Ontology (GO). The GO structure represents a challenging case of hierarchical classification, since its terms are organised in a direct acyclic graph fashion where a term can have more than one parent — in contrast to only one parent in tree structures. The p...
متن کاملOntology Engineering and Feature Construction for Predicting Friendship Links in the Live Journal Social Network
An ontology can be seen as an explicit description of the concepts and relationships that exist in a domain. In this paper, we address the problem of building an interest ontology and predicting potential friendship relations between users in the social network Live Journal, using features constructed based on the interest ontology. Previous work has shown that the accuracy of predicting friend...
متن کاملSubseries of Lecture Notes in Computer Science
This work proposes two versions of an Artificial Immune System (AIS) a relatively recent computational intelligence paradigm – for predicting protein functions described in the Gene Ontology (GO). The GO has functional classes (GO terms) specified in the form of a directed acyclic graph, which leads to a very challenging multi-label hierarchical classification problem where a protein can be ass...
متن کاملClassificador hierárquico multirrótulo usando uma rede neural competitiva
This thesis proposes a new algorithm based on Competitive Artificial Neural Networks for multi-label hierarchical classification using the global approach, in which the classifier processes and evaluates all classes in the hierarchy once. This approach, together with the multi-label prediction applied hierarchical directed acyclic graph is complex and challenging, since an example is associated...
متن کامل