BioPubMiner: Machine Learning Component-Based Biomedical Information Analysis Platform

Abstract. In this paper we introduce BioPubMiner, a machine learning component-based platform for biomedical information analysis. BioPubMiner employs natural language processing techniques and machine learning based data mining techniques for mining useful biological information such as proteinprotein interaction from the massive literature. The system recognizes biological terms such as gene, protein, and enzymes and extracts their interactions described in the document through natural language processing. The extracted interactions are further analyzed with a set of features of each entity that were collected from the related public database to infer more interactions from the original interactions. The performance of entity and interaction extraction was tested with selected MEDLINE abstracts. The evaluation of inference proceeded using the protein interaction data of S.cerevisiae (bakers yeast) from MIPS and SGD.

• Type: Conference
• Year: 2004
• Where: CIT
• Authors: Jae-Hong Eom, Byoung-Tak Zhang
• Keywords: CIT 2004, Information Management, Language Processing Techniques, Machine Learning, Natural Language Processing