Devignes Marie-Dominique, Benabderrahmane Sidahmed, Smaïl-Tabbone Malika, Napoli Amedeo, Poch Olivier
Lorraine University, Equipe Orpailleur, Campus Scientifique, Vandoeuvre les Nancy cedex, France.
Int J Comput Biol Drug Des. 2012;5(3-4):245-60. doi: 10.1504/IJCBDD.2012.049207. Epub 2012 Sep 24.
Functional classification aims at grouping genes according to their molecular function or the biological process they participate in. Evaluating the validity of such unsupervised gene classification remains a challenge given the variety of distance measures and classification algorithms that can be used. We evaluate here functional classification of genes with the help of reference sets: KEGG (Kyoto Encyclopaedia of Genes and Genomes) pathways and Pfam clans. These sets represent ground truth for any distance based on GO (Gene Ontology) biological process and molecular function annotations respectively. Overlaps between clusters and reference sets are estimated by the F-score method. We test our previously described IntelliGO semantic distance with hierarchical and fuzzy C-means clustering and we compare results with the state-of-the-art DAVID (Database for Annotation Visualisation and Integrated Discovery) functional classification method. Finally, study of best matching clusters to reference sets leads us to propose a set-difference method for discovering missing information.
功能分类旨在根据基因的分子功能或它们参与的生物学过程对基因进行分组。鉴于可以使用的多种距离度量和分类算法，评估这种无监督基因分类的有效性仍然是一项挑战。我们在此借助参考集评估基因的功能分类：KEGG（京都基因与基因组百科全书）通路和Pfam家族。这些集合分别代表基于GO（基因本体论）生物学过程和分子功能注释的任何距离的基本事实。通过F分数方法估计聚类与参考集之间的重叠。我们使用层次聚类和模糊C均值聚类测试我们之前描述的IntelliGO语义距离，并将结果与最先进的DAVID（注释可视化与综合发现数据库）功能分类方法进行比较。最后，对与参考集最佳匹配聚类的研究使我们提出一种用于发现缺失信息的集差方法。
