改进的基因术语间语义相似度计算方法

目前,基于混合方法的相似度计算对影响语义相似度的因素分析不全面。针对这个问题，提出了基于多个影响术语语义相似度度量因素的综合方法。该方法结合语义层次，语义距离和局部语义密度，充分运用本体的语义信息来计算基因术语间的语义相似度。实验结果表明，该方法与人工打分的相关系数更高。

Improved computation method for semantic similarity between gene ontology terms

The current hybrid semantic similarity computation methods do not take full consideration of related factors.Concerning this problem,this paper proposed an integrated method based on multiple factors that affect the calculation of the semantic similarity of Gene Ontology(GO) terms.This method integrated the semantic level,semantic distance and local semantic density,and utilized the semantic information of ontology to fully compute the semantic similarity of gene terms.The experimental results show that the method has higher correlation coefficient with manual scoring than other methods.