ABSTRACT
The implementation of cancer genome scientific program has promoted the diagnosis, prevention and tar-get treatment of diseases at molecular level with massive cancer genome data accumulated. Effective mining and use of cancer genome data have thus become the focus in the field of cancer genome. The cancer genome was annotated and demonstrated according to the mining of high-throughput cancer genome data from American National Cancer Research Center, namely the disease-named entity and drug-named entity were identified from the gene function descriptive text and the mined high-throughput data were annotated from their clinical application, in order to help scientific workers to find the relationship between diseases, drugs and genes in scientific literature.