Literature-mining for Genes Based Natural Language Processing and Biomedical Ontology
In the era of post-genomics, people attempt various methods to analyze genetic codes and gained a lot of achievements. As known to us, with the rapid development of high throughput biological technologies, an abundance of data about genes and gene functions has been obtained. Scientists now face the bottleneck that the increasing wealth of literature in biology and medicine makes it difficult for the researchers to keep up to date with ongoing research manually, so automated knowledge discovery and literature mining is extremely desirable. In this paper, we represent a literature-mining system which focuses on the potential relations between genes and relevant functions. The literature-mining system builds on two important existing resources: literature from PubMed, and biomedical ontology. This system extracts the relations between genes, gene and functions, gene and disease, and helps researchers accelerate their literature reading speed and focus on the literatures that they have a seriously interest in.
literature-mining natural language processing Gene Ontology Disease Ontology
Dan Zhang Yi Yuan Xiaodong Zhang Xiao Sun
State Key Laboratory of Bioelectronics， Southeast University, Nanjing 210096, China
国际会议
The 5th International Forum on Post-genome Technologies(5IFPT)(第五届国际后基因组生命科学技术学术论坛)
苏州
英文
2007-09-10（万方平台首次上网日期，不代表论文的发表时间）