{"title":"GrpClassifierEC: a novel classification approach based on the ensemble clustering space.","authors":"Loai Abdallah, Malik Yousef","doi":"10.1186/s13015-020-0162-7","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Advances in molecular biology have resulted in big and complicated data sets, therefore a clustering approach that able to capture the actual structure and the hidden patterns of the data is required. Moreover, the geometric space may not reflects the actual similarity between the different objects. As a result, in this research we use clustering-based space that convert the geometric space of the molecular to a categorical space based on clustering results. Then we use this space for developing a new classification algorithm.</p><p><strong>Results: </strong>In this study, we propose a new classification method named <i>GrpClassifierEC</i> that replaces the given data space with categorical space based on ensemble clustering (EC). The EC space is defined by tracking the membership of the points over multiple runs of clustering algorithms. Different points that were included in the same clusters will be represented as a single point. Our algorithm classifies all these points as a single class. The similarity between two objects is defined as the number of times that these objects were not belong to the same cluster. In order to evaluate our suggested method, we compare its results to the <i>k</i> nearest neighbors, Decision tree and Random forest classification algorithms on several benchmark datasets. The results confirm that the suggested new algorithm <i>GrpClassifierEC</i> outperforms the other algorithms.</p><p><strong>Conclusions: </strong>Our algorithm can be integrated with many other algorithms. In this research, we use only the k-means clustering algorithm with different k values. In future research, we propose several directions: (1) checking the effect of the clustering algorithm to build an ensemble clustering space. (2) Finding poor clustering results based on the training data, (3) reducing the volume of the data by combining similar points based on the EC.</p><p><strong>Availability and implementation: </strong>The KNIME workflow, implementing <i>GrpClassifierEC</i>, is available at https://malikyousef.com.</p>","PeriodicalId":50823,"journal":{"name":"Algorithms for Molecular Biology","volume":"15 ","pages":"3"},"PeriodicalIF":1.5000,"publicationDate":"2020-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1186/s13015-020-0162-7","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Algorithms for Molecular Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s13015-020-0162-7","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2020/1/1 0:00:00","PubModel":"eCollection","JCR":"Q4","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 1
Abstract
Background: Advances in molecular biology have resulted in big and complicated data sets, therefore a clustering approach that able to capture the actual structure and the hidden patterns of the data is required. Moreover, the geometric space may not reflects the actual similarity between the different objects. As a result, in this research we use clustering-based space that convert the geometric space of the molecular to a categorical space based on clustering results. Then we use this space for developing a new classification algorithm.
Results: In this study, we propose a new classification method named GrpClassifierEC that replaces the given data space with categorical space based on ensemble clustering (EC). The EC space is defined by tracking the membership of the points over multiple runs of clustering algorithms. Different points that were included in the same clusters will be represented as a single point. Our algorithm classifies all these points as a single class. The similarity between two objects is defined as the number of times that these objects were not belong to the same cluster. In order to evaluate our suggested method, we compare its results to the k nearest neighbors, Decision tree and Random forest classification algorithms on several benchmark datasets. The results confirm that the suggested new algorithm GrpClassifierEC outperforms the other algorithms.
Conclusions: Our algorithm can be integrated with many other algorithms. In this research, we use only the k-means clustering algorithm with different k values. In future research, we propose several directions: (1) checking the effect of the clustering algorithm to build an ensemble clustering space. (2) Finding poor clustering results based on the training data, (3) reducing the volume of the data by combining similar points based on the EC.
Availability and implementation: The KNIME workflow, implementing GrpClassifierEC, is available at https://malikyousef.com.
期刊介绍:
Algorithms for Molecular Biology publishes articles on novel algorithms for biological sequence and structure analysis, phylogeny reconstruction, and combinatorial algorithms and machine learning.
Areas of interest include but are not limited to: algorithms for RNA and protein structure analysis, gene prediction and genome analysis, comparative sequence analysis and alignment, phylogeny, gene expression, machine learning, and combinatorial algorithms.
Where appropriate, manuscripts should describe applications to real-world data. However, pure algorithm papers are also welcome if future applications to biological data are to be expected, or if they address complexity or approximation issues of novel computational problems in molecular biology. Articles about novel software tools will be considered for publication if they contain some algorithmically interesting aspects.