Gene Ontology Evidence Sentence Retrieval Using Combinatorial Applications of Semantic Class and Rule Patterns

Jian Ming Chen, Yung-Chun Chang, Johnny Chi Yang Wu, Po Ting Lai, Hong-Jie Dai

研究成果: 書貢獻/報告類型會議貢獻


Gene Ontology (GO) provides helpful information with respect to biological process, molecular function and cellular component in annotating the relationships among gene, chemical and disease. Due to the complexity of GO knowledge, developing automated or semi-automated GO curation techniques remains to be a big challenge for database curators. In order to efficiently and precisely retrieve GO information from large amount of biomedical resources, we propose a GO evidence sentence retrieval system conducted via combinatorial applications of semantic class and rule patterns to automatically retrieve GO evidence sentences with specific gene mentions from full-length articles. Introduction Gene-oriented biomedical researches constitute the basis of advanced life science researches. Although the phenomenal growth of biomedical studies augmented our apprehension of complex biological mechanisms, the sharing and exchange of these results are hindered by the discrete terminologies and depictions. Therefore, the Gene Ontology (GO) initiative attempts to provide a universal representation of gene products and their correlated attributes. To promote research and tool development for the curation of GO database, BioCreative IV hosted a GO track, with an intention of retrieving GO evidence sentences for relevant genes (SubTask A) and predicting GO terms for relevant genes (SubTask B). In this work, we introduce a combinatorial approach toward the SubTask A of BioCreative IV. In our approach, the subtask is further divided into two subtasks: 1) candidate GO sentence retrieval, which selects the candidate GO sentences from a given full text, and 2) gene entity assignment, which assigns relevant gene mentions to a GO evidence sentence.
主出版物標題The Fourth BioCreAtIvE Challenge Evaluation Workshop
出版狀態已發佈 - 2013