A semi-supervised efficient learning approach to extract biological relationships from web-based biomedical digital library

Many biological results are published only in plain - text documents and these documents or their abstracts are collected in web-based digital libraries such as PubMed and BioMed Central. To expedite the progress of functional bioinformatics, it is important to efficiently process large amounts of these documents, to extract these results into a structured format, and to store them in a database so that these results can be retrieved and analyzed by biologists and medical researchers. Automated discovery and extraction of the biological knowledge from biomedical web documents has become essential because of the enormous amount of biomedical literature published each year. In this paper we present a semi-supervised efficient learning approach to automatically extract biological knowledge from the web-based digital libraries. Our method integrates ontology-based semantic tagging as well as information extraction and data mining together. Our method automatically learns the patterns based on a few user seed tuples and then extracts new tuples from the biomedical web documents based on the discovered patterns. A novel system, SPIE (Scalable and Portable Information Extraction), is implemented and tested on the PuBMed to find the chromatin protein - protein interaction. The experimental results indicate our approach is very effective in extracting biological knowledge from a huge collection of biomedical web documents.