Abstract
Due to the automated biological sequence analysis, the gigantic amount of biological data and knowledge produced has made great challenges for the biologists to process, analyze, and interpret the information and knowledge. Much biological research results of genomic sequences become available in certain electronic forms via Internet or Webs. The database Kyoto Encyclopedia of the Genes and Genomes (KEGG) provides the useful information about the biological pathway. However, the PubMed of the NCBI also consists of a gigantic size of the biological literature that possesses potential relevant information for interpreting the molecular interactions. We developed intelligent agent technology to integrate those databases using web service techniques and helped biologists to filtering the information and also extract knowledge directly from a large scale of biological literature. Including the biological pathway knowledge would be a promising extension for the information filtering and extraction. The research integrated sharable biomedical thesauri of WordNet, MeSH (Medical Subject Heading) to support the automatic semantic annotation. The pattern matching and sentence-parsing techniques are facilitated the ontology inference to extract the correct knowledge from the abstract. We evaluated the system based on the problems in Apoptosis pathway domain. It will be extended to the automated extraction of gene-gene and protein-protein interaction information from biological literature and developed the inference methods in understanding the gene networks.